Journal

Isabel O Gallegos, , Joe Barrow, Md Mehrab Tanjim, , Franck Dernoncourt, Tong Yu, Ruiyi Zhang, .

arXiv preprint arXiv:2309.00770, .

Rapid advancements of large language models (LLMs) have enabled the processing, understanding, and generation of human-like text, with increasing integration into systems that touch our social sphere. Despite this success, these models can learn, perpetuate, and amplify harmful social biases. In this paper, we present a comprehensive survey of (More...)
@inproceedings{gallegos2023bias,
   author={Gallegos and Rossi and Barrow and Tanjim and Kim and Dernoncourt and Yu and Zhang and Ahmed},
   title={Bias and Fairness in Large Language Models: A Survey},
   booktitle={arXiv preprint arXiv:2309.00770},
   year={2023},
}
Conference

Shashank Goel, Hritik Bansal, Sumit Bhatia, , Vishwa Vinay, Aditya Grover.

Advances in Neural Information Processing Systems (NeurIPS), .

Recent advances in contrastive representation learning over paired image-text data have led to models such as CLIP that achieve state-of-the-art performance for zero-shot classification and distributional robustness. Such models typically require joint reasoning in the image and text representation spaces for downstream inference tasks. Contrary to prior beliefs, we (More...)
@inproceedings{goel-neurips22,
   author={Shashank Goel and Hritik Bansal and Sumit Bhatia and Ryan A. Rossi and Vishwa Vinay and Aditya Grover},
   title={CyCLIP: Cyclic Contrastive Language-Image Pretraining},
   booktitle={Advances in Neural Information Processing Systems (NeurIPS)},
   year={2022},
}
Conference

Zihao Zhou, Xingyi Yang, , , Rose Yu.

Learning for Dynamics and Control Conference (L4DC), Pages 777-789, .

Learning the dynamics of spatiotemporal events is a fundamental problem. Neural point processes enhance the expressivity of point process models with deep neural networks. However, most existing methods only consider temporal dynamics without spatial modeling. We propose Deep Spatiotemporal Point Process (DeepSTPP), a deep dynamics model that integrates spatiotemporal (More...)
@inproceedings{zhou2022neural,
   author={Zihao Zhou and Xingyi Yang and Ryan Rossi and Handong Zhao and Rose Yu},
   title={Neural Point Process for Learning Spatiotemporal Event Dynamics},
   booktitle={Learning for Dynamics and Control Conference (L4DC)},
   year={2022},
   pages={777-789},
}
Conference

Yue Zhao, , Leman Akoglu.

Advances in Neural Information Processing Systems (NeurIPS), Volume 34, Pages 4489-4502, .

Given an unsupervised outlier detection task on a new dataset, how can we automatically select a good outlier detection algorithm and its hyperparameter(s) (collectively called a model)? In this work, we tackle the unsupervised outlier model selection (UOMS) problem, and propose MetaOD, a principled, data-driven approach to UOMS based (More...)
@article{zhao2021automatic,
   author={Yue Zhao and Ryan A. Rossi and Leman Akoglu},
   title={Automatic Unsupervised Outlier Model Selection},
   journal={Advances in Neural Information Processing Systems (NeurIPS)},
   volume={34},
   year={2021},
   pages={4489-4502},
}
Conference

Xin Qian, , Fan Du, , , Sana Malik, Tak Yeon Lee, .

ACM Transactions on the Web (TWEB), Volume 16, Pages 1-47, .

Visualization recommendation work has focused solely on scoring visualizations based on the underlying dataset and not the actual user and their past visualization feedback. These systems recommend the same visualizations for every user, despite that the underlying user interests, intent, and visualization preferences are likely to be fundamentally different, (More...)
@article{qian2022personalized,
   author={Xin Qian and Ryan A. Rossi and Fan Du and Sungchul Kim and Eunyee Koh and Sana Malik and Tak Yeon Lee and Nesreen K. Ahmed},
   title={Personalized Visualization Recommendation},
   journal={ACM Transactions on the Web (TWEB)},
   volume={16},
   number={3},
   year={2022},
   pages={1-47},
   publisher={ACM New York, NY},
}
@article{chen2022graph,
   author={Hongjie Chen and Ryan A. Rossi and Kanak Mahadik and Sungchul Kim and Hoda Eldardiry},
   title={Graph Deep Factors for Probabilistic Time-series Forecasting},
   journal={ACM Transactions on Knowledge Discovery from Data (TKDD)},
   year={2022},
}
Conference

Gaurav Verma, Vishwa Vinay, , Srijan Kumar.

EMNLP, .

As multimodal learning finds applications in a wide variety of high-stakes societal tasks, investigating their robustness becomes important. Existing work has focused on understanding the robustness of vision-and-language models to imperceptible variations on benchmark tasks. In this work, we investigate the robustness of multimodal classifiers to cross-modal dilutions - (More...)
@article{verma2022robustness,
   author={Gaurav Verma and Vishwa Vinay and Ryan A. Rossi and Srijan Kumar},
   title={Robustness of Fusion-based Multimodal Classifiers to Cross-Modal Content Dilutions},
   journal={EMNLP},
   year={2022},
}
Conference

Aravind Reddy, , Zhao Song, , , Nedim Lipka, , , .

Proceedings of the 39th International Conference on Machine Learning (ICML), Pages 18463-18482, .

In this paper, we initiate the study of one-pass algorithms for solving the maximum-a-posteriori (MAP) inference problem for Non-symmetric Determinantal Point Processes (NDPPs). In particular, we formulate streaming and online versions of the problem and provide one-pass algorithms for solving these problems. In our streaming setting, data points arrive (More...)
@inproceedings{icml22-OnlineNDPPs,
   author={Aravind Reddy and Ryan A. Rossi and Zhao Song and Anup Rao and Tung Mai and Nedim Lipka and Gang Wu and Eunyee Koh and Nesreen Ahmed},
   title={One-Pass Algorithms for MAP Inference of Nonsymmetric Determinantal Point Processes},
   booktitle={Proceedings of the 39th International Conference on Machine Learning (ICML)},
   year={2022},
   pages={18463-18482},
}
Conference

Namyong Park, , , Iftikhar Ahamath Burhanuddin, , Fan Du, , Christos Faloutsos.

Proceedings of the ACM Web Conference (WWW), Pages 1115-1126, .

@inproceedings{park2022cgc,
   author={Namyong Park and Ryan Rossi and Eunyee Koh and Iftikhar Ahamath Burhanuddin and Sungchul Kim and Fan Du and Nesreen Ahmed and Christos Faloutsos},
   title={CGC: Contrastive Graph Clustering for Community Detection and Tracking},
   booktitle={Proceedings of the ACM Web Conference (WWW)},
   year={2022},
   pages={1115-1126},
}
Conference

Enayat Ullah, , , , Raman Arora.

Conference on Learning Theory (COLT), Pages 4126-4142, .

@inproceedings{ullah2021machine,
   author={Enayat Ullah and Tung Mai and Anup Rao and Ryan A. Rossi and Raman Arora},
   title={Machine Unlearning via Algorithmic Stability},
   booktitle={Conference on Learning Theory (COLT)},
   year={2021},
   pages={4126-4142},
}
Conference

Mustafa Abdallah, , , , , Saurabh Bagchi.

Proceedings of the 31st ACM International Conference on Information \& Knowledge Management (CIKM), Pages 5-14, .

@inproceedings{abdallah2022autoforecast,
   author={Mustafa Abdallah and Ryan Rossi and Kanak Mahadik and Sungchul Kim and Handong Zhao and Saurabh Bagchi},
   title={AutoForecast: Automatic Time-Series Forecasting Model Selection},
   booktitle={Proceedings of the 31st ACM International Conference on Information \& Knowledge Management (CIKM)},
   year={2022},
   pages={5-14},
}
Conference

Duc Hoang, Haotao Wang, , , , , Zhangyang Wang.

Proceedings of the 31st ACM International Conference on Information \& Knowledge Management, Pages 727-736, .

@inproceedings{hoang2022automars,
   author={Duc Hoang and Haotao Wang and Handong Zhao and Ryan Rossi and Sungchul Kim and Kanak Mahadik and Zhangyang Wang},
   title={AutoMARS: Searching to Compress Multi-Modality Recommendation Systems},
   booktitle={Proceedings of the 31st ACM International Conference on Information \& Knowledge Management},
   year={2022},
   pages={727-736},
}
Conference

Chang Xiao, , .

Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology (UIST), .

@inproceedings{xiao2022imarker,
   author={Chang Xiao and Ryan Rossi and Eunyee Koh},
   title={iMarker: Instant and True-to-scale AR with Invisible Markers},
   booktitle={Proceedings of the 35th Annual ACM Symposium on User Interface Software and Technology (UIST)},
   year={2022},
}
Conference

Weixin Jiang, , Vishy Swaminathan, Stefano Petrangeli, Haoliang Wang, , Nedim Lipka.

ISM, .

@inproceedings{jiang2022compression,
   author={Weixin Jiang and Gang Wu and Vishy Swaminathan and Stefano Petrangeli and Haoliang Wang and Ryan A. Rossi and Nedim Lipka},
   title={Task-Oriented Near-Lossless Burst Compression},
   booktitle={ISM},
   year={2022},
}
Conference

Galen Weld, Peter West, Maria Glenski, , , Tim Althoff.

Proceedings of the International AAAI Conference on Web and Social Media (ICWSM), Volume 16, Pages 1109-1120, .

@inproceedings{weld2022adjusting,
   author={Galen Weld and Peter West and Maria Glenski and David Arbour and Ryan A. Rossi and Tim Althoff},
   title={Adjusting for confounders with text: Challenges and an empirical evaluation framework for causal inference},
   booktitle={Proceedings of the International AAAI Conference on Web and Social Media (ICWSM)},
   volume={16},
   year={2022},
   pages={1109-1120},
}
Conference

Hongjie Chen, , , .

2021 IEEE International Conference on Big Data (IEEE BigData), Pages 1359-1368, .

@inproceedings{chen2021context,
   author={Hongjie Chen and Ryan A. Rossi and Kanak Mahadik and Hoda Eldardiry},
   title={Context Integrated Relational Spatio-Temporal Resource Forecasting},
   booktitle={2021 IEEE International Conference on Big Data (IEEE BigData)},
   year={2021},
   pages={1359-1368},
}
Conference

, , , .

Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining, Pages 410-420, .

@inproceedings{jin2022generalizing,
   author={Di Jin and Sungchul Kim and Ryan A. Rossi and Danai Koutra},
   title={On Generalizing Static Node Embedding to Dynamic Settings},
   booktitle={Proceedings of the Fifteenth ACM International Conference on Web Search and Data Mining},
   year={2022},
   pages={410-420},
}
Conference

Can Qin, , , Tong Yu, , Yun Fu.

Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD), Pages 1401-1409, .

@inproceedings{qin2022external,
   author={Can Qin and Sungchul Kim and Handong Zhao and Tong Yu and Ryan A. Rossi and Yun Fu},
   title={External Knowledge Infusion for Tabular Pre-training Models with Dual-adapters},
   booktitle={Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)},
   year={2022},
   pages={1401-1409},
}
Conference

Sejoon Oh, Ankur Bhardwaj, Jongseok Han, , , Srijan Kumar.

Proceedings of the 31st ACM International Conference on Information \& Knowledge Management, Pages 4364-4368, .

@inproceedings{oh2022implicit,
   author={Sejoon Oh and Ankur Bhardwaj and Jongseok Han and Sungchul Kim and Ryan A. Rossi and Srijan Kumar},
   title={Implicit Session Contexts for Next-Item Recommendations},
   booktitle={Proceedings of the 31st ACM International Conference on Information \& Knowledge Management},
   year={2022},
   pages={4364-4368},
}
Conference

Swapneel Mehta, , Xiang Chen, Saayan Mitra, Viswanathan Swaminathan, , Ali Aminian, Han Guo, Kshitiz Garg.

IEEE International Symposium on Multimedia (ISM), Pages 174-181, .

@inproceedings{mehta2021open,
   author={Mehta and Sarkhel and Chen and Mitra and Swaminathan and Rossi and Aminian and Guo and Garg},
   title={Open-Domain Trending Hashtag Recommendation for Videos},
   booktitle={IEEE International Symposium on Multimedia (ISM)},
   year={2021},
   pages={174-181},
}
Conference

Abhraneel Sarma, Shunan Guo, Jane Hoffswell, , Fan Du, , Matthew Kay.

IEEE VIS, .

@article{sarma2022evaluating,
   author={Abhraneel Sarma and Shunan Guo and Jane Hoffswell and Ryan Rossi and Fan Du and Eunyee Koh and Matthew Kay},
   title={Evaluating the Use of Uncertainty Visualisations for Imputations of Data Missing At Random in Scatterplots},
   journal={IEEE VIS},
   year={2022},
}
Conference

Fayokemi Ojo, , Jane Hoffswell, Shunan Guo, Fan Du, , Chang Xiao, .

Proceedings of the ACM Web Conference (WWW), Pages 2810–2818, .

In this work, we develop a Graph Neural Network (GNN) framework for the problem of personalized visualization recommendation. The GNN-based framework first represents the large corpus of datasets and visualizations from users as a large heterogeneous graph. Then, it decomposes a visualization into its data and visual components, and (More...)
@inproceedings{WWW22-VisGNN,
   author={Fayokemi Ojo and Ryan A. Rossi and Jane Hoffswell and Shunan Guo and Fan Du and Sungchul Kim and Chang Xiao and Eunyee Koh},
   title={VisGNN: Personalized Visualization Recommendation via Graph Neural Networks},
   booktitle={Proceedings of the ACM Web Conference (WWW)},
   year={2022},
   pages={2810–2818},
}
Conference

Hyeok Kim, , Fan Du, , Shunan Guo, Jessica Hullman, Jane Hoffswell.

ACM Human Factors in Computing Systems (CHI), .

@inproceedings{2022-cicero-responsive-grammar,
   author={Hyeok Kim and Ryan Rossi and Fan Du and Eunyee Koh and Shunan Guo and Jessica Hullman and Jane Hoffswell},
   title={Cicero: A Declarative Grammar for Responsive Visualization},
   booktitle={ACM Human Factors in Computing Systems (CHI)},
   year={2022},
}
Conference

Zhuohao Zhang, Sana Malik, Shunan Guo, Jane Hoffswell, , Fan Du, .

EuroVis Workshop on Visual Analytics (EuroVA), .

@inproceedings{2022-codas-ba-report-authoring,
   author={Zhuohao Zhang and Sana Malik and Shunan Guo and Jane Hoffswell and Ryan Rossi and Fan Du and Eunyee Koh},
   title={CODAS: Integrating Business Analytics and Report Authoring},
   booktitle={EuroVis Workshop on Visual Analytics (EuroVA)},
   year={2022},
}
Conference

Zhuohao Zhang, Sana Malik, Shunan Guo, Jane Hoffswell, , Fan Du, .

EuroVis Workshop on Visual Analytics (EuroVA), .

@inproceedings{zhang2022understanding,
   author={Zhuohao Zhang and Sana Malik and Shunan Guo and Jane Hoffswell and Ryan A. Rossi and Fan Du and Eunyee Koh},
   title={Understanding Business Analysts’ Needs for Data Report Authoring},
   booktitle={EuroVis Workshop on Visual Analytics (EuroVA)},
   year={2022},
   publisher={The Eurographics Association},
}
Conference

Sejoon Oh, , , Srijan Kumar.

Proceedings of the 30th ACM International Conference on Information & Knowledge Management (CIKM), Pages 1386-1395, .

@inproceedings{oh2021influence,
   author={Sejoon Oh and Sungchul Kim and Ryan A. Rossi and Srijan Kumar},
   title={Influence-guided Data Augmentation for Neural Tensor Completion},
   booktitle={Proceedings of the 30th ACM International Conference on Information & Knowledge Management (CIKM)},
   year={2021},
   pages={1386-1395},
}
Conference

, , , , , .

Proceedings of the 30th ACM International Conference on Information & Knowledge Management (CIKM), Pages 4085-4093, .

@inproceedings{rossi2021closing,
   author={Ryan A. Rossi and Anup Rao and Sungchul Kim and Eunyee Koh and Nesreen K. Ahmed and Gang Wu},
   title={From Closing Triangles to Higher-Order Motif Closures for Better Unsupervised Online Link Prediction},
   booktitle={Proceedings of the 30th ACM International Conference on Information & Knowledge Management (CIKM)},
   year={2021},
   pages={4085-4093},
}
Conference

Saed Rezayi, Nedim Lipka, Vishwa Vinay, , Franck Dernoncourt, Tracy H. King, .

IEEE International Conference on Big Data (IEEE BigData), Pages 510-518, .

@inproceedings{rezayi2021framework,
   author={Saed Rezayi and Nedim Lipka and Vishwa Vinay and Ryan A. Rossi and Franck Dernoncourt and Tracy H. King and Sheng Li},
   title={A Framework for Knowledge-Derived Query Suggestions},
   booktitle={IEEE International Conference on Big Data (IEEE BigData)},
   year={2021},
   pages={510-518},
}
Conference

Hyeok Kim, , Abhraneel Sarma, Dominik Moritz, Jessica Hullman.

IEEE VIS, Pages 129-139, .

Authors often transform a large screen visualization for smaller displays through rescaling, aggregation and other techniques when creating visualizations for both desktop and mobile devices (i.e., responsive visualization). However, transformations can alter relationships or patterns implied by the large screen view, requiring authors to reason carefully about what information (More...)
@inproceedings{kim2021automated,
   author={Hyeok Kim and Ryan Rossi and Abhraneel Sarma and Dominik Moritz and Jessica Hullman},
   title={An automated Approach to Reasoning about Task-oriented Insights in Responsive Visualization},
   booktitle={IEEE VIS},
   year={2021},
   pages={129-139},
}
Conference

, , , , .

International Conference on Machine Learning (ICML), .

Linear quadratic regulator (LQR) is one of the most popular frameworks to tackle continuous Markov decision process tasks. With its fundamental theory and tractable optimal policy, LQR has been revisited and analyzed in recent years, in terms of reinforcement learning scenarios such as the model-free or model-based setting. In (More...)
@inproceedings{park-icml20,
   author={Youngsuk Park and Ryan A. Rossi and Zheng Wen and Gang Wu and Handong Zhao},
   title={Structured Policy Iteration for Linear Quadratic Regulator},
   booktitle={International Conference on Machine Learning (ICML)},
   year={2020},
}
Conference

Xinyi Zheng, , , Dominik Moritz.

CIKM, Pages 3694-3704, .

The rapid development of network science and technologies depends on shareable datasets. Currently, there is no standard practice for reporting and sharing network datasets. Some network dataset providers only share links, while others provide some contexts or basic statistics. As a result, critical information may be unintentionally dropped, and (More...)
@inproceedings{zheng2022network,
   author={Xinyi Zheng and Ryan A. Rossi and Nesreen K. Ahmed and Dominik Moritz},
   title={Network Report: A Structured Description for Network Datasets},
   booktitle={CIKM},
   year={2022},
   pages={3694-3704},
}

, Richard Alo, Catherine Amelink, Young Yun Baek, Aashish Chudhary, Kristy Collins, Albert Esterline, , , , Ron Kenyon, , , Dustin Machi, , , Yasuo Miyasaki, , , , , , .

Gateways, .

Networks have entered the mainstream lexicon over the last ten years. This coincides with the pervasive use of networks in a host of disciplines of interest to industry and academia, including biology, neurology, genomics, psychology, social sciences, economics, psychology, and cyber-physical systems and infrastructure. Several dozen journals and conferences regularly contain articles related to networks. (More...)
@inproceedings{CINES,
   author={Nesreen Ahmed and Richard Alo and Catherine Amelink and Young Yun Baek and Aashish Chudhary and Kristy Collins and Albert Esterline and Edward Fox and Geoffrey Fox and Aric Hagberg and Ron Kenyon and Chris J. Kuhlman and Jure Leskovec and Dustin Machi and Madhav V. Marathe and Nataragan Meghanathan and Yasuo Miyasaki and Judy Qiu and Naren Ramakrishnan and S. S. Ravi and Ryan Rossi and Roc Sosic and Gregor von Laszewski},
   title={net.science: A Cyberinfrastructure for Sustained Innovation in Network Science and Engineering},
   booktitle={Gateways},
   year={2020},
}
Journal

, , , , , .

Transactions on Knowledge Discovery from Data (TKDD), Pages 36, .

Structural roles define sets of structurally similar nodes that are more similar to nodes inside the set than outside, whereas communities define sets of nodes with more connections inside the set than outside. Roles based on structural similarity and communities based on proximity are fundamentally different but important complementary (More...)
@inproceedings{rossi20tkdd-roles,
   author={Ryan A. Rossi and Di Jin and Sungchul Kim and Nesreen K. Ahmed and Danai Koutra and John Boaz Lee},
   title={On Proximity and Structural Role-based Embeddings in Networks: Misconceptions, Techniques, and Applications},
   booktitle={Transactions on Knowledge Discovery from Data (TKDD)},
   year={2020},
   pages={36},
}
Workshop/symposia

Zening Qu, Fan Du, , Bill Howe.

NL VIZ: Workshop on Exploring Opportunities and Challenges for Natural Language Techniques to Support Visual Analysis, .

We envision Lily, a mixed-initiative collaborative authoring platform for anyone to direct, in their own words, data fusing, analysis, visualization design, and storytelling, end-to-end. We foresee one lightweight user interface that flexibly accepts novice or expert language, concise or elaborate, declarative or imperative -- that encodes coarse- or fine-grain (More...)
@inproceedings{qu2021vis,
   author={Zening Qu and Fan Du and Ryan A. Rossi and Bill Howe},
   title={Aunt Lily Can Say Her Visualizations: Directing Analysis, Design, and Storytelling in Natural Language},
   booktitle={NL VIZ: Workshop on Exploring Opportunities and Challenges for Natural Language Techniques to Support Visual Analysis},
   year={2021},
}
Journal

, , .

Journal of Machine Learning Research (JMLR), .

In this work, we present a theoretical analysis framework for relational ensemble models. We show that ensembles of collective classifiers can improve predictions for graph data by reducing errors due to variance in both learning \emph{and} inference. In addition, we propose a relational ensemble framework that combines a relational (More...)
@inproceedings{jmlr20,
   author={Hoda Eldardiry and Jennifer Neville and Ryan A. Rossi},
   title={Ensemble Learning for Relational Data},
   booktitle={Journal of Machine Learning Research (JMLR)},
   year={2020},
}
Journal

, , Aldo Carranza, , , , .

Transactions on Knowledge Discovery from Data (TKDD), Pages 43, .

In this paper, we introduce a generalization of graphlets to heterogeneous networks called typed graphlets. Informally, typed graphlets are small typed induced subgraphs. Typed graphlets generalize graphlets to rich heterogeneous networks as they explicitly capture the higher-order typed connectivity patterns in such networks. To address this problem, we describe (More...)
@inproceedings{rossi-heterogeneous-graphlets-tkdd,
   author={Ryan A. Rossi and Nesreen K. Ahmed and Aldo Carranza and David Arbour and Anup Rao and Sungchul Kim and Eunyee Koh},
   title={Heterogeneous Graphlets},
   booktitle={Transactions on Knowledge Discovery from Data (TKDD)},
   year={2020},
   pages={43},
}

, , , , , .

arXiv:1908.08572, .

Roles are sets of structurally similar nodes that are more similar to nodes inside the set than outside, whereas communities are sets of nodes with more connections inside the set than outside (based on proximity/closeness, density). Roles and communities are fundamentally different but important complementary notions. Recently, the notion (More...)
@inproceedings{from-comm-to-structural-role-embeddings,
   author={Ryan A. Rossi and Di Jin and Sungchul Kim and Nesreen K. Ahmed and Danai Koutra and John Boaz Lee},
   title={From Community to Role-based Graph Embeddings},
   booktitle={arXiv:1908.08572},
   year={2019},
}

, , .

arXiv:1910.08657, .

Temporal networks representing a stream of timestamped edges are seemingly ubiquitous in the real-world. However, the massive size and continuous nature of these networks make them fundamentally challenging to analyze and leverage for descriptive and predictive modeling tasks. In this work, we propose a general framework for temporal network (More...)
@inproceedings{ahmed19-temporal-network-sampling,
   author={Nesreen K. Ahmed and Nick Duffield and Ryan A. Rossi},
   title={Temporal Network Sampling},
   booktitle={arXiv:1910.08657},
   year={2019},
}
Conference

, , , , , .

Proceedings of the ACM International Conference on Web Search and Data Mining (WSDM), Pages 1-9, .

The success of many graph-based machine learning tasks highly depends on an appropriate representation learned from the graph data. Most work has focused on learning node embeddings that preserve proximity as opposed to structural role-based embeddings that preserve the structural similarity among nodes. These methods fail to capture higher-order (More...)
@inproceedings{rossi-wsdm20,
   author={Ryan A. Rossi and Nesreen K. Ahmed and Eunyee Koh and Sungchul Kim and Anup Rao and Yasin Abbasi-Yadkori},
   title={A Structural Graph Representation Learning Framework},
   booktitle={Proceedings of the ACM International Conference on Web Search and Data Mining (WSDM)},
   year={2020},
   pages={1-9},
}
Conference

Gromit Yeuk-Yin Chan, Fan Du, , , , Cl\'{a}udio T. Silva, Juliana Freire.

Proceedings of The Web Conference (WWW), Pages 1-11, .

Online visitor behaviors are often modeled as a large sparse matrix, where rows represent visitors and columns represent behavior. To discover customer segments with different hierarchies, marketers often need to cluster the data in different splits. Such analyses require the clustering algorithm to provide real-time responses on user (More...)
@inproceedings{gromit-www20,
   author={Gromit Yeuk-Yin Chan and Fan Du and Ryan A. Rossi and Anup Rao and Eunyee Koh and Cl\'{a}udio T. Silva and Juliana Freire},
   title={Real-Time Clustering for Large Sparse Online Visitor Data},
   booktitle={Proceedings of The Web Conference (WWW)},
   year={2020},
   pages={1-11},
}
Conference

, , , .

Proceedings of The Web Conference (WWW), .

Typed graphlets are small typed (labeled, colored) induced subgraphs and were recently shown to be the fundamental building blocks of rich complex heterogeneous networks. In many applications, speed is more important than accuracy, and it is sufficient to trade-off a tiny amount of accuracy for a significantly faster method. (More...)
@inproceedings{typed-graphlet-estimation-www20,
   author={Ryan A. Rossi and Anup Rao and Tung Mai and Nesreen K. Ahmed},
   title={Fast and Accurate Estimation of Typed Graphlets},
   booktitle={Proceedings of The Web Conference (WWW)},
   year={2020},
}
Conference

, , , , .

Proceedings of The Web Conference (WWW), .

This work introduces higher-order ranking and link prediction methods based on closing higher-order network motifs. In particular, we propose the general notion of a motif closure that goes beyond simple triangle closures and demonstrate that these new motif closures often outperform triangle-based methods. This result implies that one should (More...)
@inproceedings{motif-closures-www20,
   author={Ryan A. Rossi and Anup Rao and Sungchul Kim and Eunyee Koh and Nesreen K. Ahmed},
   title={From Closing Triangles to Closing Higher-Order Motifs},
   booktitle={Proceedings of The Web Conference (WWW)},
   year={2020},
}
Conference

, , , .

Proceedings of The Web Conference (WWW), .

While there has been a lot of research on graph clustering (community detection), most work (i) does not address the hierarchical community detection problem or are (ii) inefficient for large networks. In this work, we describe an approach called hLP that addresses both these limitations. Notably, hLP is fast (More...)
@inproceedings{hierarchical-clustering-www20,
   author={Ryan A. Rossi and Nesreen K. Ahmed and Eunyee Koh and Sungchul Kim},
   title={Fast Hierarchical Graph Clustering in Linear-Time},
   booktitle={Proceedings of The Web Conference (WWW)},
   year={2020},
}
Conference

, , , , .

Proceedings of the Thirty-First Annual ACM-SIAM Symposium on Discrete Algorithms (SODA), Pages 1-20, .

In this paper, we study the problem of finding a maximum matching in the semi-streaming model when edges arrive in random order. In the semi-streaming model, an algorithm receives a stream of edges and it is allowed to have a memory of (More...)(n) where n is the number of vertices in the graph. A recent work shows that there exists a streaming algorithm with the approximation ratio of 23 that uses ˜O(n1.5) memory. However, their memory is much larger than the memory constraint of the semi-streaming algorithms. In this work, we further investigate this problem in the semi-streaming model, and we give the first better-than-0.5 approximation algorithm in the semi-streaming model. Our main results are as follow. We show that there exists a single-pass deterministic semi-streaming algorithm that finds a 35(=0.6) approximation of the maximum matching in bipartite graphs using ˜O(n) memory. This result outperforms the state-of-the-art result that finds a 0.539 approximation of the maximum matching using ˜O(n) memory. By giving a black-box reduction from finding a matching in general graphs to finding a matching in bipartite graphs, we show there exists a single-pass deterministic semi-streaming algorithm that finds a 611(0.545) approximation of the maximum matching in general graphs, improving upon the state-of-art result 0.506 approximation. Our work is the first better-than-0.5 approximation algorithm for this problem in the semi-streaming model.
@inproceedings{farhadi2020stream-matching,
   author={Alireza Farhadi and MohammadTaghi Hajiaghayi and Tung Mai and Anup Rao and Ryan A. Rossi},
   title={Approximate Maximum Matching in Random Streams},
   booktitle={Proceedings of the Thirty-First Annual ACM-SIAM Symposium on Discrete Algorithms (SODA)},
   year={2020},
   pages={1-20},
}

, , .

AAAI StarAI, .

In this work, we formalize the problem of causal inference over graph-based relational time-series data where each node in the graph has one or more time-series associated to it. We propose causal inference models for this problem that leverage both the graph topology and time-series to accurately estimate local (More...)
@inproceedings{causality-aaai20,
   author={Ryan A. Rossi and Somdeb Sarkhel and Nesreen K. Ahmed},
   title={Inferring Individual Level Causal Models from Graph-based Relational Time Series},
   booktitle={AAAI StarAI},
   year={2020},
}
Conference

, , , , , .

28th ACM International Conference on Information and Knowledge Management (CIKM), .

The success of deep convolutional neural networks in the domains of computer vision and speech recognition has led researchers to investigate generalizations of the said architecture to graph-structured data. A recently-proposed method called Graph Convolutional Networks has been able to achieve state-of-the-art results in the task of node classification. (More...)
@inproceedings{lee19-motif-attention,
   author={John Boaz Lee and Ryan Rossi and Xiangnan Kong and Sungchul Kim and Eunyee Koh and Anup Rao},
   title={Graph Convolutional Networks with Motif-based Attention},
   booktitle={28th ACM International Conference on Information and Knowledge Management (CIKM)},
   year={2019},
}
Conference

, , Matt Kapilevich, , , .

UAI, .

One Permutation Hashing (OPH) is a significantly more efficient alternative to the popular minwise hashing. To produce a sketch of size k, OPH requires just one hash function whereas the classical minwise hashing requires (More...)
@inproceedings{mai-uai19,
   author={Tung Mai and Anup Rao and Matt Kapilevich and Ryan A. Rossi and Yasin Abbasi-Yadkori and Ritwik Sinha},
   title={On Densification for Minwise Hashing},
   booktitle={UAI},
   year={2019},
}
Journal

, .

Social Network Analysis and Mining (SNAM), Volume 9, Pages 51, .

Complex networks arise in many domains and often represent phenomena such as brain activity, social relationships, molecular interactions, hyperlinks, and re-tweets. In this work, we study the problem of predicting the category (domain) of arbitrary networks. This includes complex networks from different domains as well as synthetically generated graphs (More...)
@article{rossi2019complex,
   author={Ryan A. Rossi and Nesreen K. Ahmed},
   title={Complex networks are structurally distinguishable by domain},
   journal={Social Network Analysis and Mining (SNAM)},
   volume={9},
   number={1},
   year={2019},
   pages={51},
   publisher={Springer},
}
Journal

, Giang Nguyen, , , , .

arXiv, .

Networks evolve continuously over time with the addition, deletion, and changing of links and nodes. Such temporal networks (or edge streams) consist of a sequence of timestamped edges and are seemingly ubiquitous. Despite the importance of accurately modeling the temporal information, most embedding methods ignore it entirely or approximate (More...)
@inproceedings{ctdne-journal,
   author={John Boaz Lee and Giang Nguyen and Ryan A. Rossi and Nesreen K. Ahmed and Eunyee Koh and Sungchul Kim},
   title={Temporal Network Representation Learning},
   booktitle={arXiv},
   year={2019},
}
Conference

, , , , , .

KDD, .

An important reason behind the prevalence of node representation learning is their superiority in downstream machine learning tasks on graphs. However, storing the vector-based node representation of massive real-world graphs often requires space that is orders of magnitude larger. To alleviate this issue, we introduce the problem of latent (More...)
@inproceedings{latent-network-summ-kdd19,
   author={Di Jin and Ryan A. Rossi and Eunyee Koh and Sungchul Kim and Anup Rao and Danai Koutra},
   title={Latent Network Summarization: Bridging Network Embedding and Summarization},
   booktitle={KDD},
   year={2019},
}

Charles Chen, Ruiyi Zhang, , , Scott Cohen, .

IEEE Winter Conference on Applications of Computer Vision (WACV), .

Figures, such as line plots, pie charts, bar charts, are widely used to convey important information in a concise format. In this work, we investigate the problem of figure caption generation where the goal is to automatically generate a natural language description for a given figure. While natural image (More...)
@inproceedings{chen20-fig-caption-generation,
   author={Charles Chen and Ruiyi Zhang and Eunyee Koh and Sungchul Kim and Scott Cohen and Ryan A. Rossi},
   title={Figure Captioning with Reasoning and Sequence-Level Training},
   booktitle={IEEE Winter Conference on Applications of Computer Vision (WACV)},
   year={2020},
}
Workshop/symposia

, , Aldo Carranza, , , , .

MLG KDD, Pages 8, .

In this work, we generalize the notion of network motifs (graphlets) to heterogeneous networks by introducing the notion of a small induced typed subgraph called typed graphlet. Typed graphlets generalize graphlets to rich heterogeneous networks as they explicitly capture the higher-order typed connectivity patterns in such networks. To address (More...)
@inproceedings{rossi-heterogeneous-graphlets,
   author={Ryan A. Rossi and Nesreen K. Ahmed and Aldo Carranza and David Arbour and Anup Rao and Sungchul Kim and Eunyee Koh},
   title={Heterogeneous Graphlets},
   booktitle={MLG KDD},
   year={2019},
   pages={8},
}
Conference

, , , .

ECML/PKDD, Pages 22, .

Identity stitching, the task of identifying and matching various online references (e.g., sessions over different devices and timespans) to the same user in real-world web services, is crucial for personalization and recommendations. However, traditional user stitching approaches, such as grouping or blocking, require quadratic pairwise comparisons between a massive (More...)
@inproceedings{node2bits-ECML19,
   author={Di Jin and Mark Heimann and Ryan A. Rossi and Danai Koutra},
   title={Node2BITS: Compact Time- and Attribute-aware Node Representations for User Stitching},
   booktitle={ECML/PKDD},
   year={2019},
   pages={22},
}
Journal

, , .

IEEE Transactions on Knowledge and Data Engineering (TKDE), Pages 14, .

This paper presents a general inductive graph representation learning framework called DeepGL for learning deep node and edge features that generalize across-networks. In particular, DeepGL begins by deriving a set of base features from the graph (e.g., graphlet features) and automatically learns a multi-layered hierarchical graph representation where each (More...)
@inproceedings{rossi-TKDE18,
   author={Ryan A. Rossi and Rong Zhou and Nesreen K. Ahmed},
   title={Deep Inductive Graph Representation Learning},
   booktitle={IEEE Transactions on Knowledge and Data Engineering (TKDE)},
   year={2018},
   pages={14},
}
@inproceedings{socc19-lqr-cloud,
   author={Youngsuk Park and Kanak Mahadik and Ryan A. Rossi and Nesreen K. Ahmed and Gang Wu and Handong Zhao},
   title={Linear Quadratic Regulator for Resource-Efficient Cloud Services},
   booktitle={Proceedings of the ACM Symposium on Cloud Computing (SoCC)},
   year={2019},
   pages={488–489},
}

, , , .

arXiv:1906.06432, .

Community detection in graphs has many important and fundamental applications including in distributed systems, compression, image segmentation, divide-and-conquer graph algorithms such as nested dissection, document and word clustering, circuit design, among many others. Finding these densely connected regions of graphs remains an important and challenging problem. Most work has (More...)
@inproceedings{rossi19-hLP,
   author={Ryan A. Rossi and Nesreen K. Ahmed and Eunyee Koh and Sungchul Kim},
   title={Linear-time Hierarchical Community Detection},
   booktitle={arXiv:1906.06432},
   year={2019},
}

, , , , , .

arXiv:1906.05059, .

In this paper, we introduce the notion of motif closure and describe higher-order ranking and link prediction methods based on the notion of closing higher-order network motifs. The methods are fast and efficient for real-time ranking and link prediction-based applications such as web search, online advertising, and recommendation. In (More...)
@inproceedings{rossi19-motif-closures,
   author={Ryan A. Rossi and Anup Rao and Sungchul Kim and Eunyee Koh and Nesreen K. Ahmed and Gang Wu},
   title={Higher-Order Ranking and Link Prediction: From Closing Triangles to Closing Higher-Order Motifs},
   booktitle={arXiv:1906.05059},
   year={2019},
}

, , , , , .

arXiv:1811.04461, .

An important reason behind the prevalence of node representation learning is their superiority in downstream machine learning tasks on graphs. However, storing the vector-based node representation of massive real-world graphs often requires space that is orders of magnitude larger. To alleviate this issue, we introduce the problem of latent (More...)
@inproceedings{jin18-latent-network-summ,
   author={Di Jin and Ryan A. Rossi and Danai Koutra and Eunyee Koh and Sungchul Kim and Anup Rao},
   title={Bridging Network Embedding and Graph Summarization},
   booktitle={arXiv:1811.04461},
   year={2018},
}
Journal

, , , , .

Transactions on Knowledge Discovery from Data (TKDD), Pages 19, .

Graph-structured data arise naturally in many different application domains. By representing data as graphs, we can capture entities (i.e., nodes) as well as their relationships (i.e., edges) with each other. Many useful insights can be derived from graph-structured data as demonstrated by an ever-growing body of work focused on (More...)
@inproceedings{lee18-attention-survey,
   author={John Boaz Lee and Ryan A. Rossi and Sungchul Kim and Nesreen K. Ahmed and Eunyee Koh},
   title={Attention Models in Graphs: A Survey},
   booktitle={Transactions on Knowledge Discovery from Data (TKDD)},
   year={2019},
   pages={19},
}
Conference

, , , , , .

WSDM, Pages 9, .

Understanding user behavior and predicting future behavior on the web is critical for providing seamless user experiences as well as increasing revenue of service providers. Recently, thanks to the remarkable success of recurrent neural networks (RNNs), it has been widely used for modeling sequences of user behaviors. However, although (More...)
@inproceedings{kim-wsdm19,
   author={Donghyun Kim and Sungchul Kim and Handong Zhao and Sheng Li and Ryan A. Rossi and Eunyee Koh},
   title={Domain Switch-Aware Holistic Recurrent Neural Network for Modeling Multi-Domain User Behavior},
   booktitle={WSDM},
   year={2019},
   pages={9},
}

, , , .

arXiv:1810.02959, Pages 15, .

Higher-order connectivity patterns such as small induced sub-graphs called graphlets (network motifs) are vital to understand the important components (modules/functional units) governing the configuration and behavior of complex networks. Existing work in higher-order clustering has focused on simple homogeneous graphs with a single node/edge type. However, heterogeneous graphs consisting (More...)
@inproceedings{higher-order-clustering-heter,
   author={Aldo G. Carranza and Ryan A. Rossi and Anup Rao and Eunyee Koh},
   title={Higher-order Spectral Clustering for Heterogeneous Graphs},
   booktitle={arXiv:1810.02959},
   year={2018},
   pages={15},
}

, , Aldo Carranza, , , , .

arXiv:1901.10026, Pages 18, .

Many real-world applications give rise to large heterogeneous networks where nodes and edges can be of any arbitrary type (e.g., user, web page, location). Special cases of such heterogeneous graphs include homogeneous graphs, bipartite, k-partite, signed, labeled graphs, among many others. In this work, we generalize the notion of (More...)
@inproceedings{rossi-heterogeneous-motifs,
   author={Ryan A. Rossi and Nesreen K. Ahmed and Aldo Carranza and David Arbour and Anup Rao and Sungchul Kim and Eunyee Koh},
   title={Heterogeneous Network Motifs},
   booktitle={arXiv:1901.10026},
   year={2019},
   pages={18},
}

Neural caption generation over figures

Charles Chen, Ruiyi Zhang, , , Scott Cohen, Tong Yu, , .

Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp/ISWC), Pages 482-485, .

Figures are human-friendly but difficult for computers to process automatically. In this work, we investigate the problem of figure captioning. The goal is to automatically generate a natural language description of a given figure. We create a new dataset for figure captioning, FigCAP. To achieve accurate generation of labels (More...)
@inproceedings{chen19-neural-fig-caption-generation,
   author={Charles Chen and Ruiyi Zhang and Sungchul Kim and Eunyee Koh and Scott Cohen and Tong Yu and Ryan A. Rossi and Razvan Bunescu},
   title={Neural caption generation over figures},
   booktitle={Proceedings of the 2019 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp/ISWC)},
   year={2019},
   pages={482-485},
}
Conference

, , .

KDD, Pages 1-9, .

Graph classification is a problem with practical applications in many different domains. To solve this problem, one usually calculates certain graph statistics (i.e., graph features) that help discriminate between graphs of different classes. When calculating such features, most existing approaches process the entire graph. In a graphlet-based approach, for (More...)
@inproceedings{lee18-kdd-graph-attention,
   author={John Boaz Lee and Ryan A. Rossi and Xiangnan Kong},
   title={Graph Classification using Structural Attention},
   booktitle={KDD},
   year={2018},
   pages={1-9},
}

, , , , , .

arXiv:1809.07697, Pages 1-8, .

Following the success of deep convolutional networks in various vision and speech related tasks, researchers have started investigating generalizations of the well-known technique for graph-structured data. A recently-proposed method called Graph Convolutional Networks has been able to achieve state-of-the-art results in the task of node classification. However, since the (More...)
@inproceedings{lee18-higher-order-GCNs,
   author={John Boaz Lee and Ryan A. Rossi and Xiangnan Kong and Sungchul Kim and Eunyee Koh and Anup Rao},
   title={Higher-order Graph Convolutional Networks},
   booktitle={arXiv:1809.07697},
   year={2018},
   pages={1-8},
}
Conference

Giang Hoang Nguyen, , , , , .

IEEE BigData, Pages 1085-1092, .

Networks evolve continuously over time with the addition, deletion, and changing of links and nodes. Although many networks contain this type of temporal information, the majority of research in network representation learning has focused on static snapshots of the graph and has largely ignored the temporal dynamics of the (More...)
@inproceedings{ctdne-bigdata18,
   author={Giang Hoang Nguyen and John Boaz Lee and Ryan A. Rossi and Nesreen K. Ahmed and Eunyee Koh and Sungchul Kim},
   title={Dynamic Network Embeddings: From Random Walks to Temporal Random Walks},
   booktitle={IEEE BigData},
   year={2018},
   pages={1085-1092},
}
Conference

, , .

IEEE International Conference on Data Mining (ICDM), Pages 6, .

Higher-order network modeling and analysis are vital to understanding the structures governing the configuration and behavior of complex networks. While network motifs are known to be fundamental building blocks of complex networks, the higher-order configuration and organization of complex networks remain widely unknown. In this work, we develop interactive (More...)
@inproceedings{rossi18icdm,
   author={Ryan A. Rossi and Nesreen K. Ahmed and Eunyee Koh},
   title={Interactive Higher-order Network Analysis},
   booktitle={IEEE International Conference on Data Mining (ICDM)},
   year={2018},
   pages={6},
}
Conference

, , , .

IEEE BigData, Pages 10, .

Relational machine learning has become increasingly important due to the recent proliferation and ubiquity of network data. However, existing methods are not designed for interactive learning and have many unrealistic assumptions that greatly limit their utility in practice. For instance, most existing work has focused on graphs with high (More...)
@inproceedings{rossi18-bigdata,
   author={Ryan A. Rossi and Rong Zhou and Nesreen K. Ahmed and Hoda Eldardiry},
   title={Relational Similarity Machines (RSM): A Similarity-based Learning Framework for Graphs},
   booktitle={IEEE BigData},
   year={2018},
   pages={10},
}
Conference

Charles Chen, , , , , , .

CIKM, Pages 1-10, .

The rapid growth of mobile devices has resulted in the generation of a large number of user behavior logs that contain latent intentions and user interests. However, exploiting such data in real-world applications is still difficult for service providers due to the complexities of user behavior over a sheer (More...)
@inproceedings{chen-cikm18,
   author={Charles Chen and Sungchul Kim and Hung Bui and Ryan A. Rossi and Branislav Kveton and Eunyee Koh and Razvan Bunescu},
   title={Predictive Analysis by Leveraging Temporal User Behavior and User Embeddings},
   booktitle={CIKM},
   year={2018},
   pages={1-10},
}
Conference

, , .

Proceedings of the 27th International Conference Companion on World Wide Web (WWW), .

This paper describes a general framework for learning Higher-Order Network Embeddings (HONE) from graph data based on network motifs. The HONE framework is highly expressive and flexible with many interchangeable components. The experimental results demonstrate the effectiveness of learning higher-order network representations. In all cases, HONE outperforms recent embedding (More...)
@inproceedings{rossi-WWW18,
   author={Ryan A. Rossi and Nesreen K. Ahmed and Eunyee Koh},
   title={Higher-Order Network Representation Learning},
   booktitle={Proceedings of the 27th International Conference Companion on World Wide Web (WWW)},
   year={2018},
}
Workshop/symposia

, , .

Proceedings of the 3rd International Workshop on Learning Representations for Big Networks (WWW BigNet), Pages 8, .

This paper presents a general graph representation learning framework called DeepGL for learning deep node and edge representations from large (attributed) graphs. In particular, DeepGL begins by deriving a set of base features (e.g., graphlet features) and automatically learns a multi-layered hierarchical graph representation where each successive layer leverages the (More...)
@inproceedings{rossi-WWW18-BigNet,
   author={Ryan A. Rossi and Rong Zhou and Nesreen K. Ahmed},
   title={Deep Inductive Network Representation Learning},
   booktitle={Proceedings of the 3rd International Workshop on Learning Representations for Big Networks (WWW BigNet)},
   year={2018},
   pages={8},
}
Workshop/symposia

, , , , , , .

DLG KDD, .

Random walks are at the heart of many existing network embedding methods. However, such methods have many limitations that arise from the use of traditional random walks, e.g., the embeddings resulting from these methods primarily capture proximity (communities) among the vertices as opposed to structural similarity (roles). In this (More...)
@inproceedings{role2vec,
   author={Nesreen K. Ahmed and Ryan A. Rossi and John Boaz Lee and Theodore L. Willke and Rong Zhou and Xiangnan Kong and Hoda Eldardiry},
   title={role2vec: Role-based Network Embeddings},
   booktitle={DLG KDD},
   year={2019},
}
Journal

, , .

IEEE Transactions on Neural Networks and Learning Systems (TNNLS), Pages 44-57, .

Graphlets are induced subgraphs of a large network and are important for understanding and modeling complex networks. Despite their practical importance, graphlets have been severely limited to applications and domains with relatively small graphs. Most previous work has focused on exact algorithms, however, it is often too expensive to (More...)
@inproceedings{rossi18tnnls,
   author={Ryan A. Rossi and Rong Zhou and Nesreen K. Ahmed},
   title={Estimation of Graphlet Counts in Massive Networks},
   booktitle={IEEE Transactions on Neural Networks and Learning Systems (TNNLS)},
   year={2018},
   pages={44-57},
}
Workshop/symposia

Giang Hoang Nguyen, , , , , .

Proceedings of the 3rd International Workshop on Learning Representations for Big Networks (WWW BigNet), .

Networks evolve continuously over time with the addition, deletion, and changing of links and nodes. Although many networks contain this type of temporal information, the majority of research in network representation learning has focused on static snapshots of the graph and has largely ignored the temporal dynamics of the (More...)
@inproceedings{nguyen-WWW18,
   author={Giang Hoang Nguyen and John Boaz Lee and Ryan A. Rossi and Nesreen K. Ahmed and Eunyee Koh and Sungchul Kim},
   title={Continuous-Time Dynamic Network Embeddings},
   booktitle={Proceedings of the 3rd International Workshop on Learning Representations for Big Networks (WWW BigNet)},
   year={2018},
}
Workshop/symposia

, , , , , , .

StarAI IJCAI, .

Random walks are at the heart of many existing network embedding methods. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied to vertex identity. (More...)
@inproceedings{role2vec-ijcai18,
   author={Nesreen K. Ahmed and Ryan A. Rossi and Rong Zhou and John Boaz Lee and Xiangnan Kong and Theodore L. Willke and Hoda Eldardiry},
   title={Learning Role-based Graph Embeddings},
   booktitle={StarAI IJCAI},
   year={2018},
}

, , , , , .

arXiv:1801.09303, .

This paper describes a general framework for learning Higher-Order Network Embeddings (HONE) from graph data based on network motifs. The HONE framework is highly expressive and flexible with many interchangeable components. The experimental results demonstrate the effectiveness of learning higher-order network representations. In all cases, HONE outperforms recent embedding (More...)
@inproceedings{rossi-HONE-arxiv,
   author={Ryan A. Rossi and Nesreen K. Ahmed and Eunyee Koh and Sungchul Kim and Anup Rao and Yasin Abbasi-Yadkori},
   title={HONE: Higher-Order Network Embeddings},
   booktitle={arXiv:1801.09303},
   year={2018},
}
Journal

, .

Journal of Big Data, Volume 5, Pages 14, .

Massive graphs are ubiquitous and at the heart of many real-world applications ranging from the World Wide Web to social networks. As a result, techniques for compressing graphs have become increasingly important. In this work, we propose a graph compression and encoding framework called GraphZIP based on the observation (More...)
@article{rossi2018compressing-graphs-cliques,
   author={Ryan A. Rossi and Rong Zhou},
   title={GraphZIP: A Clique-based Sparse Graph Compression Method},
   journal={Journal of Big Data},
   volume={5},
   number={1},
   year={2018},
   pages={14},
}
Journal

.

Knowledge Engineering Review (KER), Volume 33, Pages e1, .

Networks encode dependencies between entities (people, computers, proteins) and allow us to study phenomena across social, technological, and biological domains. These networks naturally evolve over time by the addition, deletion, and changing of links, nodes, and attributes. Despite the importance of modeling these dynamics, existing work in relational machine (More...)
@article{rossi2018ker,
   author={Ryan A. Rossi},
   title={Relational Time Series Forecasting},
   journal={Knowledge Engineering Review (KER)},
   volume={33},
   year={2018},
   pages={e1},
   publisher={Cambridge University Press},
}
Journal

, , , .

ACM Transactions on Intelligent Systems and Technology, Pages 1-30, .

This paper presents a platform for interactive graph mining and relational machine learning called GraphVis. The platform combines interactive visual representations with state-of-the-art graph mining and relational machine learning techniques to aid in revealing important insights quickly as well as learning an appropriate and highly predictive model for a (More...)
@article{rossi2017graphvis,
   author={Ryan A. Rossi and Nesreen K. Ahmed and Hoda Eldardiry and Rong Zhou},
   title={Interactive Visual Graph Mining and Learning},
   journal={ACM Transactions on Intelligent Systems and Technology},
   year={2018},
   pages={1-30},
}
Workshop/symposia

, , , , , , .

WiML NIPS, .

Learning a useful feature representation from graph data lies at the heart and success of many machine learning tasks such as classification, anomaly detection, link prediction, among many others. Many existing techniques use random walks as a basis for learning features or estimating the parameters of a graph model (More...)
@inproceedings{ahmed17learning-attr-graphs,
   author={Nesreen K. Ahmed and Ryan A. Rossi and Rong Zhou and John Boaz Lee and Xiangnan Kong and Theodore L. Willke and Hoda Eldardiry},
   title={Inductive Representation Learning in Large Attributed Graphs},
   booktitle={WiML NIPS},
   year={2017},
}

, , .

arXiv:1709.06075, Pages 1-8, .

Graph classification is a problem with practical applications in many different domains. Most of the existing methods take the entire graph into account when calculating graph features. In a graphlet-based approach, for instance, the entire graph is processed to get the total count of different graphlets or sub-graphs. In (More...)
@inproceedings{lee17-Deep-Graph-Attention,
   author={John Boaz Lee and Ryan Rossi and Xiangnan Kong},
   title={Deep Graph Attention Model},
   booktitle={arXiv:1709.06075},
   year={2017},
   pages={1-8},
}

, , , , , , .

arXiv:1709.04596, Pages 1-8, .

Random walks are at the heart of many existing deep learning algorithms for graph data. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied (More...)
@inproceedings{ahmed17Gen-Deep-Graph-Learning,
   author={Nesreen K. Ahmed and Ryan A. Rossi and Rong Zhou and John Boaz Lee and Xiangnan Kong and Theodore L. Willke and Hoda Eldardiry},
   title={A Framework for Generalizing Graph-based Representation Learning Methods},
   booktitle={arXiv:1709.04596},
   year={2017},
   pages={1-8},
}

, , , , , , .

arXiv:1709.04596, Pages 1-8, .

Random walks are at the heart of many existing deep learning algorithms for graph data. However, such algorithms have many limitations that arise from the use of random walks, e.g., the features resulting from these methods are unable to transfer to new nodes and graphs as they are tied (More...)
@inproceedings{ahmed17attrRandomWalks,
   author={Nesreen K. Ahmed and Ryan A. Rossi and Rong Zhou and John Boaz Lee and Xiangnan Kong and Theodore L. Willke and Hoda Eldardiry},
   title={Generalizing Deep Learning in Graphs using Attributed Random Walks},
   booktitle={arXiv:1709.04596},
   year={2017},
   pages={1-8},
}

James P. Canning, Emma E. Ingram, Sammantha Nowak-Wolff, Adriana M. Ortiz, , , Karl R. B. Schmitt, .

International Conference on Complex Networks (CompleNet), .

To the best of our knowledge, this paper presents the first large-scale study that tests whether network categories (e.g., social networks vs. web graphs) are distinguishable from one another (using both (More...)
@inproceedings{network-classification,
   author={James P. Canning and Emma E. Ingram and Sammantha Nowak-Wolff and Adriana M. Ortiz and Nesreen K. Ahmed and Ryan A. Rossi and Karl R. B. Schmitt and Sucheta Soundarajan},
   title={Network Classification and Categorization},
   booktitle={International Conference on Complex Networks (CompleNet)},
   year={2018},
}
Conference

, , , .

VLDB, Pages 1430-1441, .

We propose Graph Priority Sampling (GPS), a new paradigm for order-based reservoir sampling from massive streams of graph edges. GPS provides a general way to weight edge sampling according to auxiliary and/or size variables so as to accomplish various estimation goals of graph properties. In the context of subgraph (More...)
@inproceedings{ahmed17streams,
   author={Nesreen K. Ahmed and Nick Duffield and Theodore L. Willke and Ryan A. Rossi},
   title={On Sampling from Massive Graph Streams},
   booktitle={VLDB},
   year={2017},
   pages={1430-1441},
}

, , .

arXiv:1704.08829, Pages 1-11, .

This paper presents a general graph representation learning framework called DeepGL for learning deep node and edge representations from large (attributed) graphs. In particular, DeepGL begins by deriving a set of base features (e.g., graphlet features) and automatically learns a multi-layered hierarchical graph representation where each successive layer leverages the (More...)
@inproceedings{rossi-deepGL-arxiv,
   author={Ryan A. Rossi and Rong Zhou and Nesreen K. Ahmed},
   title={Deep Feature Learning for Graphs},
   booktitle={arXiv:1704.08829},
   year={2017},
   pages={1-11},
}
Conference

, , , .

International Joint Conference on Neural Networks (IJCNN), Pages 1-8, .

Multi-label classification is an important learning problem with many applications. In this work, we propose a similarity-based approach for multi-label learning called SML. We also introduce a similarity-based approach for predicting the label set size. SML is amenable to streaming data and online learning, naturally able to handle changes (More...)
@inproceedings{rossi18-sml,
   author={Ryan A. Rossi and Nesreen K. Ahmed and Hoda Eldardiry and Rong Zhou},
   title={Similarity-based Multi-label Learning},
   booktitle={International Joint Conference on Neural Networks (IJCNN)},
   year={2018},
   pages={1-8},
}

, , .

arXiv:1701.01772, Pages 1-14, .

Graphlets are induced subgraphs of a large network and are important for understanding and modeling complex networks. Despite their practical importance, graphlets have been severely limited to applications and domains with relatively small graphs. Most previous work has focused on exact algorithms, however, it is often too expensive to (More...)
@inproceedings{rossi17graphlet-est,
   author={Ryan A. Rossi and Rong Zhou and Nesreen K. Ahmed},
   title={Estimation of Graphlet Statistics},
   booktitle={arXiv:1701.01772},
   year={2017},
   pages={1-14},
}
Conference

, , , .

PAKDD, Pages 1-12, .

Previous work in network analysis has focused on modeling the roles of nodes in graphs. In this paper, we introduce edge role discovery and propose a framework for learning and extracting edge roles from large graphs. We also propose a general class of higher-order role models that leverage network motifs. (More...)
@inproceedings{ahmed2017roles,
   author={Nesreen K. Ahmed and Ryan A. Rossi and Theodore L. Willke and Rong Zhou},
   title={Edge Role Discovery via Higher-order Structures},
   booktitle={PAKDD},
   year={2017},
   pages={1-12},
   publisher={Springer},
}

, , , .

arXiv preprint arXiv:1610.00844, .

Previous work in network analysis has focused on modeling the mixed-memberships of node roles in the graph, but not the roles of edges. We introduce the edge role discovery problem and present a generalizable framework for learning and extracting edge roles from arbitrary graphs automatically. Furthermore, while existing node-centric role models have mainly focused on (More...)
@article{ahmed2016revisiting,
   author={Nesreen K. Ahmed and Ryan A. Rossi and Theodore L. Willke and Rong Zhou},
   title={Revisiting Role Discovery in Networks: From Node to Edge Roles},
   journal={arXiv preprint arXiv:1610.00844},
   year={2016},
}
Workshop/symposia

, , , .

Proceedings of the AAAI PAIR (Plan, Activity, and Intent Recognition) Workshop, Pages 1-7, .

Previous work in network analysis has focused on model- ing node roles in the graph. In this work, we introduce edge role discovery and develop a general framework for modeling edge roles in large networks. In addition, a general class of higher-order role discovery methods are proposed that lever- (More...)
@inproceedings{ahmed17aaai,
   author={Nesreen K. Ahmed and Ryan A. Rossi and Theodore L. Willke and Rong Zhou},
   title={A Higher-order Latent Space Network Model},
   booktitle={Proceedings of the AAAI PAIR (Plan, Activity, and Intent Recognition) Workshop},
   year={2017},
   pages={1-7},
}
Conference

, , .

Proceedings of the IEEE International Conference on BigData, Pages 586-595, .

Graphlets represent small induced subgraphs and are becoming increasingly important for a variety of applications. Despite the importance of the local subgraph (graphlet) counting problem, existing work focuses mainly on counting graphlets globally over the entire graph. These global counts have been used for tasks such as graph classification (More...)
@inproceedings{ahmed16bigdata,
   author={Nesreen K. Ahmed and Theodore L. Willke and Ryan A. Rossi},
   title={Estimation of Local Subgraph Counts},
   booktitle={Proceedings of the IEEE International Conference on BigData},
   year={2016},
   pages={586-595},
}
Journal

, , , , .

Knowledge and Information Systems (KAIS), Pages 689-722, .

From social science to biology, numerous applications often rely on graphlets for intuitive and meaningful characterization of networks. While graphlets have witnessed a tremendous success and impact in a variety of domains, there has yet to be a fast and e!cient framework for computing the frequencies (More...)
@article{ahmed2016kais,
   author={Nesreen K. Ahmed and Jennifer Neville and Ryan A. Rossi and Nick Duffield and Theodore L. Willke},
   title={Graphlet Decomposition: Framework, Algorithms, and Applications},
   journal={Knowledge and Information Systems (KAIS)},
   year={2016},
   pages={689-722},
}
Workshop/symposia

, , .

Proceedings of the 12th International Workshop on Mining and Learning with Graphs (MLG), Pages 1-8, .

This paper proposes Relational Similarity Machines (RSM): a fast, accurate, and flexible relational learning framework for supervised and semi-supervised learning tasks. Despite the importance of relational learning, most existing methods are unable to handle large noisy attributed networks with low or even modest levels of relational autocorrelation. Furthermore, they (More...)
@inproceedings{rossi16rsm,
   author={Ryan A. Rossi and Rong Zhou and Nesreen K. Ahmed},
   title={Relational Similarity Machines},
   booktitle={Proceedings of the 12th International Workshop on Mining and Learning with Graphs (MLG)},
   year={2016},
   pages={1-8},
}
Conference

, .

ACM International Conference on Information and Knowledge Management (CIKM), Pages 1783-1792, .

Massively parallel architectures such as the GPU are becoming increasingly important due to the recent proliferation of data. In this paper, we propose a key class of hybrid parallel graphlet algorithms that leverages multiple CPUs and GPUs simultaneously for computing k-vertex induced subgraph statistics (called graphlets). In addition (More...)
@inproceedings{rossi16cikm,
   author={Ryan A. Rossi and Rong Zhou},
   title={Leveraging Multiple GPUs and CPUs for Graphlet Counting in Large Networks},
   booktitle={ACM International Conference on Information and Knowledge Management (CIKM)},
   year={2016},
   pages={1783-1792},
}

, , .

KDD BigMine, Pages 16, .

Graphlets represent small induced subgraphs and are becoming increasingly important for a variety of applications. Despite the importance of the local graphlet problem, existing work focuses mainly on counting graphlets globally over the entire graph. These global counts have been used for tasks such as graph classification as well (More...)
@inproceedings{ahmed16bigmine,
   author={Nesreen Ahmed and Ted Willke and Ryan A. Rossi},
   title={Exact and Estimation of Local Edge-centric Graphlet Counts},
   booktitle={KDD BigMine},
   year={2016},
   pages={16},
}
Journal

, .

Social Network Analysis and Mining (SNAM), Pages 30, .

Relational learning methods for heterogeneous network data are becoming increasingly important for many real-world applications. However, existing relational learning approaches are sequential, inefficient, unable to scale to large heterogeneous networks, as well as many other limitations related to convergence, parameter tuning, etc. In (More...)
@inproceedings{rossi16factorization,
   author={Ryan A. Rossi and Rong Zhou},
   title={Parallel Collective Factorization for Modeling Large Heterogeneous Networks},
   booktitle={Social Network Analysis and Mining (SNAM)},
   year={2016},
   pages={30},
}
Conference

, , , .

ICDM, Pages 1-10, .

From social science to biology, numerous applications often rely on graphlets for intuitive and meaningful characterization of networks at both the global macro-level as well as the local micro-level. While graphlets have witnessed a tremendous success and impact in a variety of domains, there has yet to be a (More...)
@inproceedings{ahmed2015icdm,
   author={Nesreen K. Ahmed and Jennifer Neville and Ryan A. Rossi and Nick Duffield},
   title={Efficient Graphlet Counting for Large Networks},
   booktitle={ICDM},
   year={2015},
   pages={1-10},
}
Conference

, .

Proceedings of the AAAI Conference on Artificial Intelligence, Pages 4383-4384, .

This paper introduces the Interactive Relational Machine Learning (iRML) paradigm in which users interactively design relational models by specifying the various components, constraints, and relational data representation, as well as perform evaluation, analyze errors, and make adjustments and refinements in a closed-loop. iRML requires fast real-time learning and inference (More...)
@inproceedings{rossi2016aaai,
   author={Ryan Rossi and Rong Zhou},
   title={Toward Interactive Relational Learning},
   booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
   year={2016},
   pages={4383-4384},
}
Journal

, .

SIGKDD Explor., Volume 17, Pages 37-41, .

Scientific data repositories have historically made data widely accessible to the scientific community, and have led to better research through comparisons, reproducibility, as well as further discoveries and insights. Despite the growing importance and utilization of data repositories in many scientific disciplines, the design of existing data repositories has (More...)
@article{nr-sigkdd16,
   author={Ryan A. Rossi and Nesreen K. Ahmed},
   title={An Interactive Data Repository with Visual Analytics},
   journal={SIGKDD Explor.},
   volume={17},
   number={2},
   year={2016},
   pages={37-41},
   publisher={ACM},
}
Conference

, .

IEEE International Conference on Data Science and Advanced Analytics (DSAA), Pages 1-10, .

Relational models for heterogeneous network data are becoming increasingly important for many real-world applications. However, existing relational learning approaches are not parallel, have scalability issues, and thus unable to handle large heterogeneous network data. In this paper, we propose Parallel Collective Matrix Factorization (PCMF) that serves as a fast (More...)
@inproceedings{rossi2015dsaa-pcmf,
   author={Ryan A. Rossi and Rong Zhou},
   title={Scalable Relational Learning for Large Heterogeneous Networks},
   booktitle={IEEE International Conference on Data Science and Advanced Analytics (DSAA)},
   year={2015},
   pages={1-10},
}
Conference

, .

International AAAI Conference on Web and Social Media (ICWSM), Pages 566-569, .

We present a web-based network visual analytics platform called GraphVis that combines interactive visualizations with analytic techniques to reveal important patterns and insights for sense making, reasoning, and decision-making. The platform is designed with simplicity in mind and allows users to visualize and explore networks in seconds with a (More...)
@inproceedings{ahmed-icwsm15,
   author={Nesreen K. Ahmed and Ryan A. Rossi},
   title={Interactive Visual Graph Analytics on the Web},
   booktitle={International AAAI Conference on Web and Social Media (ICWSM)},
   year={2015},
   pages={566-569},
}
Conference

, .

Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI), .

Network Repository (NR) is the first interactive data repository with a web-based platform for visual interactive analytics. Unlike other data repositories (e.g., UCI ML Data Repository, and SNAP), the network data repository (networkrepository.com) allows users to not only download, but to interactively analyze and visualize such data using our (More...)
@inproceedings{nr-aaai15,
   author={Ryan A. Rossi and Nesreen K. Ahmed},
   title={The Network Data Repository with Interactive Graph Analytics and Visualization},
   booktitle={Proceedings of the Twenty-Ninth AAAI Conference on Artificial Intelligence (AAAI)},
   year={2015},
}
Journal

, , .

SIAM Journal on Scientific Computing (SISC), Volume 37, Pages 28, .

We present a fast, parallel maximum clique algorithm for large sparse graphs that is designed to exploit characteristics of social and information networks. The method exhibits a roughly linear runtime scaling over real-world networks ranging from a thousand to a hundred million nodes. In a test on a social (More...)
@article{rossi2015pmc-sisc,
   author={Ryan A. Rossi and David F. Gleich and Assefaw H. Gebremedhin},
   title={Parallel Maximum Clique Algorithms with Applications to Network Analysis},
   journal={SIAM Journal on Scientific Computing (SISC)},
   volume={37},
   number={5},
   year={2015},
   pages={28},
   publisher={Society for Industrial and Applied Mathematics (SIAM)},
}
Journal

, .

IEEE Transactions on Knowledge and Data Engineering (TKDE), Volume 27, Pages 1112-1131, .

Roles represent node-level connectivity patterns such as star-center, star-edge nodes, near-cliques or nodes that act as bridges to different regions of the graph. Intuitively, two nodes belong to the same role if they are structurally similar. Roles have been mainly of interest to sociologists, but more recently, roles have (More...)
@article{rossi2015roles,
   author={Ryan A. Rossi and Nesreen K. Ahmed},
   title={Role Discovery in Networks},
   journal={IEEE Transactions on Knowledge and Data Engineering (TKDE)},
   volume={27},
   number={4},
   year={2015},
   pages={1112-1131},
   publisher={IEEE},
}
Journal

, .

Social Network Analysis and Mining, Volume 4, Pages 37, .

Given a large social or information network, how can we partition the vertices into sets (i.e., colors) such that no two vertices linked by an edge are in the same set while minimizing the number of sets used. Despite the obvious practical importance of graph coloring, existing works have not systematically investigated or designed methods (More...)
@article{rossi2014coloring,
   author={Ryan A. Rossi and Nesreen K. Ahmed},
   title={Coloring Large Complex Networks},
   journal={Social Network Analysis and Mining},
   volume={4},
   number={1},
   year={2014},
   pages={37},
}
Conference

.

Advances in Knowledge Discovery and Data Mining (PAKDD), Pages 310-322, .

Large triangle cores represent dense subgraphs for which each edge has at least k − 2 triangles (same as cliques). This paper presents a fast algorithm for computing the triangle core decomposition on big graphs. The proposed triangle core algorithm adapts both the computations and representation based on the properties of the graph. In (More...)
@inproceedings{rossi2014pakdd,
   author={Ryan A. Rossi},
   title={Fast Triangle Core Decomposition for Mining Large Graphs},
   booktitle={Advances in Knowledge Discovery and Data Mining (PAKDD)},
   year={2014},
   pages={310-322},
   publisher={Springer},
}
Conference

, , .

Networking, Pages 1-9, .

The topology of a network (connectivity of autonomous systems (ASes) or routers) has significant implications on the design of protocols and applications, and on the placement of services and data centers. Researchers and practitioners alike need realistic topologies for their simulation, emulation, and testbed experiments. In this work, we propose a multilevel framework for analyzing (More...)
@inproceedings{rossi2013topology,
   author={Ryan A. Rossi and Sonia Fahmy and Nilothpal Talukder},
   title={A Multi-Level Approach for Evaluating Internet Topology Generators},
   booktitle={Networking},
   year={2013},
   pages={1-9},
}
Conference

, , , Mostofa A. Patwary.

Proceedings of the 23rd International Conference on World Wide Web (WWW), .

We propose a fast, parallel maximum clique algorithm for large sparse graphs that is designed to exploit characteristics of social and information networks. Despite clique’s status as an NP-hard problem with poor approximation guarantees, our method exhibits nearly linear runtime scaling over realworld networks ranging from 1000 to 100 million nodes. In a test on (More...)
@inproceedings{rossi2014pmc-www,
   author={Ryan A. Rossi and David F. Gleich and Assefaw H. Gebremedhin and Mostofa A. Patwary},
   title={Fast Maximum Clique Algorithms for Large Graphs},
   booktitle={Proceedings of the 23rd International Conference on World Wide Web (WWW)},
   year={2014},
}
Workshop/symposia

, , .

SIAM Workshop on Network Science, Pages 1-2, .

Consider a graph G = (V, E). A k-core of G is a maximal induced subgraph of G where each vertex has degree at least k. There is a linear time O(|E|+|V |) time algorithm to compute the maximum k such that a vertex is in a k-core for all vertices (More...)
@inproceedings{rossi2013trianglecores,
   author={Ryan A. Rossi and David F. Gleich and Assefaw H. Gebremedhin},
   title={Triangle Core Decomposition and Maximum Cliques},
   booktitle={SIAM Workshop on Network Science},
   year={2013},
   pages={1-2},
}
Journal

, .

Internet Mathematics, Volume 10, Pages 188-217, .

We propose a dynamical system that captures changes to the network centrality of nodes as external interest in those nodes varies. We derive this system by adding time-dependent teleportation to the PageRank score. The result is not a single set of importance scores, but rather a time-dependent set. These can be converted (More...)
@article{rossi2014dynamical,
   author={David F. Gleich and Ryan A. Rossi},
   title={A Dynamical System for PageRank with Time-Dependent Teleportation},
   journal={Internet Mathematics},
   volume={10},
   number={1-2},
   year={2014},
   pages={188-217},
}
Conference

, , , Keith Henderson.

Proceedings of the Sixth ACM International Conference on Web Search and Data Mining (WSDM), Pages 667-676, .

Given a large time-evolving graph, how can we model and characterize the temporal behaviors of individual nodes (and network states)? How can we model the behavioral transition patterns of nodes? We propose a temporal behavior model that captures the "roles" of nodes in the graph and how they evolve (More...)
@inproceedings{rossi2013modeling,
   author={Ryan A. Rossi and Brian Gallagher and Jennifer Neville and Keith Henderson},
   title={Modeling Dynamic Behavior in Large Evolving Graphs},
   booktitle={Proceedings of the Sixth ACM International Conference on Web Search and Data Mining (WSDM)},
   year={2013},
   pages={667-676},
   publisher={ACM},
}
Journal

, , , .

Journal of Artificial Intelligence Research (JAIR), Volume 45, Pages 363-441, .

Relational data representations have become an increasingly important topic due to the recent proliferation of network datasets (e.g., social, biological, information networks) and a corresponding increase in the application of Statistical Relational Learning (SRL) algorithms to these domains. In this article, we examine and categorize techniques for transforming graph-based relational data to improve (More...)
@article{rossi2012transforming,
   author={Ryan A. Rossi and Luke K. McDowell and David W. Aha and Jennifer Neville},
   title={Transforming Graph Data for Statistical Relational Learning},
   journal={Journal of Artificial Intelligence Research (JAIR)},
   volume={45},
   year={2012},
   pages={363-441},
   publisher={AAAI Press},
}

, .

Algorithms and Models for the Web Graph, Volume 7323, Pages 126-137, .

The importance of nodes in a network constantly fluctuates based on changes in the network structure as well as changes in external interest. We propose an evolving teleportation adaptation of the PageRank method to capture how changes in external interest influence the importance of a node. This framework seamlessly generalizes PageRank because the importance (More...)
@article{rossi2012dynamic,
   author={Ryan A. Rossi and David F. Gleich},
   title={Dynamic PageRank using Evolving Teleportation},
   journal={Algorithms and Models for the Web Graph},
   volume={7323},
   series={Lecture Notes in Computer Science},
   editor={Anthony Bonato and Jeannette Janssen},
   year={2012},
   pages={126-137},
   publisher={Springer},
}

, , , .

arXiv:1204.0033, .

Relational data representations have become an increasingly important topic due to the recent proliferation of network datasets (e.g., social, biological, information networks) and a corresponding increase in the application of statistical relational learning (SRL) algorithms to these domains. In this article, we examine a range of representation issues for (More...)
@article{rossi2012relational-rep-learning,
   author={Ryan A. Rossi and Luke K. McDowell and David W. Aha and Jennifer Neville},
   title={Transforming graph representations for statistical relational learning},
   journal={arXiv:1204.0033},
   year={2012},
}

, .

arXiv:1111.5312, .

Temporal networks are ubiquitous and evolve over time by the addition, deletion, and changing of links, nodes, and attributes. Although many relational datasets contain temporal information, the majority of existing techniques in relational learning focus on static snapshots and ignore the temporal dynamics. We propose a framework for discovering (More...)
@article{rossi11representations,
   author={Ryan A. Rossi and Jennifer Neville},
   title={Representations and Ensemble Methods for Dynamic Relational Classification},
   journal={arXiv:1111.5312},
   year={2011},
}

, , , Keith Henderson.

Proceedings of the 21st International Conference Companion on World Wide Web (WWW), Pages 997-1006, .

To understand the structural dynamics of a large-scale social, biological or technological network, it may be useful to discover behavioral roles representing the main connectivity patterns present over time. In this paper, we propose a scalable non-parametric approach to automatically learn the structural dynamics of the network and individual nodes. Roles may represent structural or (More...)
@inproceedings{rossi2012role,
   author={Ryan A. Rossi and Brian Gallagher and Jennifer Neville and Keith Henderson},
   title={Role-Dynamics: Fast Mining of Large Dynamic Networks},
   booktitle={Proceedings of the 21st International Conference Companion on World Wide Web (WWW)},
   year={2012},
   pages={997-1006},
}
Conference

, .

PAKDD, Pages 1-13, .

Relational networks often evolve over time by the addition, deletion, and changing of links, nodes, and attributes. However, accurately incorporating the full range of temporal dependencies into relational learning algorithms remains a challenge. We propose a novel framework for discovering temporal-relational representations for classi- fication. The framework considers transformations over all the evolving relational components (More...)
@inproceedings{rossi2012dynamic-srl,
   author={Ryan A. Rossi and Jennifer Neville},
   title={Time-evolving Relational Classification and Ensemble Methods},
   booktitle={PAKDD},
   year={2012},
   pages={1-13},
   publisher={Springer},
}
Workshop/symposia

, .

SIGKDD SOMA, Pages 89-97, .

Textual analysis is one means by which to assess communication type and moderate the influence of network structure in predictive models of individual behavior. However, there are few methods available to incorporate textual content into time-evolving network models. In particular, modeling both the evolution of network topology and textual (More...)
@inproceedings{rossi2010modeling,
   author={Ryan A. Rossi and Jennifer Neville},
   title={Modeling the Evolution of Discussion Topics and Communication to Improve Relational Classification},
   booktitle={SIGKDD SOMA},
   year={2010},
   pages={89-97},
}
Conference

, , Axel E. Bernal.

AINAW, Volume 1, Pages 745-751, .

Presented in the US, Russia, Japan, Thailand and Canada at various conferences and keynotes.

In 1957 Crick hypothesized that the genetic code was a comma free code. This property would imply the existence of a universal coding frame and make the set of coding sequences a locally testable language. As the link between nucleotides and amino acids became better understood, it appeared clearly (More...)
@inproceedings{rossi2007crick,
   author={Jean-Louis Lassez and Ryan A. Rossi and Axel E. Bernal},
   title={Cricks Hypothesis Revisited: The Existence of a Universal Coding Frame},
   booktitle={AINAW},
   volume={1},
   year={2007},
   pages={745-751},
}
Conference

, , Kumar Jeev.

New Frontiers in Applied Artificial Intelligence (IEA/AIE), Pages 199-208, .

The main algorithms at the heart of search engines have focused on ranking and classifying sites. This is appropriate when we know what we are looking for and want it directly. Alternatively, we surf, in which case ranking and classifying links becomes the focus. We address this problem using (More...)
@article{lassez2008ranking,
   author={Jean-Louis Lassez and Ryan A. Rossi and Kumar Jeev},
   title={Ranking Links on the Web: Search and Surf Engines},
   journal={New Frontiers in Applied Artificial Intelligence (IEA/AIE)},
   year={2008},
   pages={199-208},
   publisher={Springer},
}
Conference

, , Stephen Sheel, Srinivas Mukkamala.

Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN), Pages 1068-1074, .

We address the problem of selecting and extracting key features by using singular value decomposition and latent semantic analysis. As a consequence, we are able to discover latent information which allows us to design signatures for forensics and in a dual approach for real-time intrusion detection systems. The validity (More...)
@inproceedings{lassez2008signature,
   author={Jean-Louis Lassez and Ryan A. Rossi and Stephen Sheel and Srinivas Mukkamala},
   title={Signature based Intrusion Detection using Latent Semantic Analysis},
   booktitle={Proceedings of the IEEE International Joint Conference on Neural Networks (IJCNN)},
   year={2008},
   pages={1068-1074},
}
Conference

John Stamey, , Daniel Boorn, .

Proceedings of the 25th annual ACM International Conference on Design of Communication (SIGDOC), Pages 155-161, .

@inproceedings{stamey2007dynamic,
   author={John Stamey and Jean-Louis Lassez and Daniel Boorn and Ryan A. Rossi},
   title={Client-side Dynamic Metadata in Web 2.0},
   booktitle={Proceedings of the 25th annual ACM International Conference on Design of Communication (SIGDOC)},
   year={2007},
   pages={155-161},
}
Conference

.

Computational Intelligence and Intelligent Systems, Pages 128-137, .

We use Latent Semantic Analysis as a basis to study the languages of life. Using this approach we derive techniques to discover latent relationships between organisms such as significant motifs and evolutionary features. Doubly Singular Value Decomposition is defined and the significance of this adaptation is demonstrated by finding (More...)
@article{rossi2009latent,
   author={Ryan A. Rossi},
   title={Latent Semantic Analysis of the Languages of Life},
   journal={Computational Intelligence and Intelligent Systems},
   year={2009},
   pages={128-137},
   publisher={Springer},
}
Conference

, , Khawaja S. Shams.

IEEE Aerospace, Pages 1-11, .

The Mars Reconnaissance Orbiter's HiRISE (High Resolution Imaging Science Experiment) camera takes the largest images of the Martian surface. The image size is typically around 2.52 gigapixels. There is only a handful of software capable of doing a task as simple as reducing the size of the image by (More...)
@inproceedings{powell2010scalable,
   author={Mark W. Powell and Ryan A. Rossi and Khawaja S. Shams},
   title={A Scalable Image Processing Framework for Gigapixel Mars and Other Celestial Body Images},
   booktitle={IEEE Aerospace},
   year={2010},
   pages={1-11},
}
Conference

Khawaja S. Shams, , Tom M. Crockett, Jeffrey S. Norris, , Tom Soderstrom.

10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing (CCGrid), Pages 606-611, .

Amazon AWS Case Study: NASA JPL’s Desert Research and Training

Cloud Computing has delivered unprecedented compute capacity to NASA missions at affordable rates. Missions like the Mars Exploration Rovers (MER) and Mars Science Lab (MSL) are enjoying the elasticity that enables them to leverage hundreds, if not thousands, or machines for short durations without making any hardware procurements. In (More...)
@inproceedings{shams2010polyphony,
   author={Khawaja S. Shams and Mark W. Powell and Tom M. Crockett and Jeffrey S. Norris and Ryan A. Rossi and Tom Soderstrom},
   title={Polyphony: A Workflow Orchestration Framework for Cloud Computing},
   booktitle={10th IEEE/ACM International Conference on Cluster, Cloud and Grid Computing (CCGrid)},
   year={2010},
   pages={606-611},
}
Conference

John W. Stamey, .

Proceedings of the 27th ACM International Conference on Design of Communication, Pages 233-238, .

@inproceedings{stamey2009automatically,
   author={John W. Stamey and Ryan A. Rossi},
   title={Automatically Identifying Relations in Privacy Policies},
   booktitle={Proceedings of the 27th ACM International Conference on Design of Communication},
   year={2009},
   pages={233-238},
}
Technical report

, , .

Tech. Report Purdue CS, Pages 1-10, .

The topology of a network (connectivity of autonomous systems (ASes) or routers) has significant implications on the design of protocols and applications, and on the placement of services and data centers. Researchers and practitioners alike are in constant need of realistic topologies for their simulation, emulation, and testbed experiments. In this work, we propose a (More...)
@inproceedings{rossi2013modeling-evol,
   author={Ryan A. Rossi and Sonia Fahmy and Nilothpal Talukder},
   title={Modeling the Evolution of the Internet Topology: A Multi-Level Evaluation Framework},
   booktitle={Tech. Report Purdue CS},
   year={2013},
   pages={1-10},
}
Technical report

, , , Mostofa A. Patwary.

arXiv preprint arXiv:1302.6256, Pages 1-9, .

We propose a fast, parallel, maximum clique algorithm for large, sparse graphs that is designed to exploit characteristics of social and information networks. We observe roughly linear runtime scaling over graphs between 1000 vertices and 100M vertices. In a test with a 1.8 billion-edge social network, the algorithm finds the largest clique in about (More...)
@article{rossi2013parallel-cliques,
   author={Ryan A. Rossi and David F. Gleich and Assefaw H. Gebremedhin and Mostofa A. Patwary},
   title={A Fast Parallel Maximum Clique Algorithm for Large Sparse Graphs and Temporal Strong Components},
   journal={arXiv preprint arXiv:1302.6256},
   year={2013},
   pages={1-9},
}
Technical report

, , , Mostofa A. Patwary.

arXiv preprint arXiv:1210.5802, Pages 1-11, .

Exact maximum clique finders have progressed to the point where we can investigate cliques in million-node social and information networks, as well as find strongly connected components in temporal networks. We use one such finder to study a large collection of modern networks emanating from biological, social, and technological domains. We show inter-relationships between maximum (More...)
@article{rossi2012fastclique,
   author={Ryan A. Rossi and David F. Gleich and Assefaw H. Gebremedhin and Mostofa A. Patwary},
   title={What if CLIQUE were fast? Maximum Cliques in Information Networks and Strong Components in Temporal Networks},
   journal={arXiv preprint arXiv:1210.5802},
   year={2012},
   pages={1-11},
}
Technical report

, , , Keith Henderson.

DOE Scientific and Technical Information, LLNL-TR-514271, Pages 1-10, .

Given a large time-evolving network, how can we model and characterize the temporal behaviors of individual nodes (and network states)? How can we model the behavioral transition patterns of nodes? We propose a temporal behavior model that captures the 'roles' of nodes in the graph and how they evolve (More...)
@inproceedings{rossi2011modeling,
   author={Ryan A. Rossi and Brian Gallagher and Jennifer Neville and Keith Henderson},
   title={Modeling Temporal Behavior in Large Networks: A Dynamic Mixed-Membership Model},
   booktitle={DOE Scientific and Technical Information, LLNL-TR-514271},
   year={2011},
   pages={1-10},
   publisher={DOE},
}
Technical report

.

JPL Tech. Report, Pages 1-9, .

This paper proposes a new direction in Adversarial Information Retrieval through automatically ranking links. We use techniques based on Latent Semantic Analysis to define a novel algorithm to eliminate spam sites. Our model automatically creates, suppresses, and reinforces links. Using an appropriately weighted graph spam links are assigned substantially (More...)
@inproceedings{rossi2009discovering,
   author={Ryan A. Rossi},
   title={Discovering Latent Graphs with Positive and Negative Links to Eliminate Spam},
   booktitle={JPL Tech. Report},
   year={2009},
   pages={1-9},
}

.

Purdue University, Pages 163, .

Ph.D. Dissertation, Purdue University

Networks encode dependencies between entities (people, computers, proteins) and allow us to study phenomena across social, technological, and biological domains. These networks naturally evolve over time by the addition, deletion, and changing of links, nodes, and attributes. Existing work in Relational Machine Learning (RML) has ignored relational time series (More...)
@phdthesis{rossi2015purdue,
   author={Ryan A. Rossi},
   title={Improving Relational Machine Learning by Modeling Temporal Dependencies},
   school={Purdue University},
   year={2015},
   pages={163},
   publisher={ProQuest},
}
Patent

One-class Similarity Machines for Anomaly Detection

, Ajay Raghavan, Jungho Park.

Patent, .

Patent application filed

One-class similarity machines is a family of unsupervised novelty/anomaly detection methods. We have used it for detecting anomalies in multi-variate time series data. Performance is comparable and sometimes better than one-class SVM. The method also has many advantages over one-class SVM, e.g., the target function is approximated locally and (More...)
@misc{rossi18oneClassSim,
   author={Ryan A. Rossi and Ajay Raghavan and Jungho Park},
   title={One-class Similarity Machines for Anomaly Detection},
   booktitle={Patent},
   year={2017},
   yearfiled={2018},
}
Patent

Higher-Order Network Embedding

, , .

Patent, .

Patent application filed, USPTO App. #16/204,616

In implementations of higher-order network embedding, a computing device maintains interconnected data in the form of a graph that represents a network, the graph including nodes that each represent entities in the network and node associations that each represent edges between the nodes in the graph. The computing device includes a network embedding (More...)
@misc{rossi18hone-patent,
   author={Ryan A. Rossi and Sungchul Kim and Eunyee Koh},
   title={Higher-Order Network Embedding},
   booktitle={Patent},
   year={2018},
   yearfiled={2018},
}
Patent

Latent Network Summarization

, , , , .

Patent, .

Patent application filed, USPTO App. #16/252,169

An important reason behind the prevalence of node representation learning is their superiority in downstream machine learning tasks on graphs. However, storing the vector-based node representation of massive real-world graphs often requires space that is orders of magnitude larger. To alleviate this issue, we introduce the problem of latent (More...)
@misc{latent-network-summ-patent,
   author={Di Jin and Ryan A. Rossi and Eunyee Koh and Sungchul Kim and Anup Rao},
   title={Latent Network Summarization},
   booktitle={Patent},
   year={2018},
   yearfiled={2019},
}
Patent

Time-Dependent Network Embedding

, , .

Patent, .

Patent application filed, USPTO App. #16/192,313

In implementations of time-dependent network embedding, a computing device maintains time-dependent interconnected data in the form of a time-based graph that includes nodes and node associations that each represent an edge between two of the nodes in the time-based graph based at least in part on a temporal value that indicates when the (More...)
@misc{rossi18time-dependent-network-embedding,
   author={Ryan A. Rossi and Sungchul Kim and Eunyee Koh},
   title={Time-Dependent Network Embedding},
   booktitle={Patent},
   year={2018},
   yearfiled={2018},
}
Patent

System and Method for Anomaly Characterization Based on Joint Historical and Time-series Analysis

Jungho Park, Ajay Raghavan, , Yosuke Tajika, Akira Minegishi, Tetsuyoshi Ogura.

Patent, .

Patent application filed, USPTO App. #16/170,815

One embodiment provides a system for facilitating anomaly detection and characterization. During operation, the system determines, by a computing device, a first set of testing data which includes a plurality of data points, wherein the first set includes a data series for a first variable and one or more second variables. The system (More...)
@misc{park18JointAnomaly,
   author={Jungho Park and Ajay Raghavan and Ryan A. Rossi and Yosuke Tajika and Akira Minegishi and Tetsuyoshi Ogura},
   title={System and Method for Anomaly Characterization Based on Joint Historical and Time-series Analysis},
   booktitle={Patent},
   year={2017},
   yearfiled={2018},
}
Patent

Binned IQR for Anomaly Detection in Multivariate Time Series

Ajay Raghavan, , Jungho Park.

Patent, .

Patent application filed

This invention presents a new method to detect anomalies in multivariate time series data using "binned" IQR (Inter-Quartile Range). The IQR method is commonly used to detect anomaly in one-dimensional data. However, the IQR method does not perform well if the data instances have different behaviors according to other (More...)
@misc{ajay18binnedIQR,
   author={Ajay Raghavan and Ryan A. Rossi and Jungho Park},
   title={Binned IQR for Anomaly Detection in Multivariate Time Series},
   booktitle={Patent},
   year={2017},
   yearfiled={2018},
}
Patent

Method and System for Similarity-based Multi-label Learning

, .

Patent, .

Patent application filed, USPTO App. #16/237,439

A system is provided for facilitating multi-label classification. During operation, the system maintains a set of training vectors. A respective vector represents an object and is associated with one or more labels that belong to a label set. After receiving an input vector, the system determines a (More...)
@misc{rossi17multilabel,
   author={Ryan A. Rossi and Hoda Eldardiry},
   title={Method and System for Similarity-based Multi-label Learning},
   booktitle={Patent},
   year={2017},
   yearfiled={2017},
}
Patent

Deep Graph Representation Learning

, .

Patent, .

US Patent No. 10482375

@misc{rossi17deepRML,
   author={Ryan A. Rossi and Rong Zhou},
   title={Deep Graph Representation Learning},
   booktitle={Patent},
   year={2019},
   yearfiled={2016},
}
Patent

A Graph Search Engine

, .

Patent, .

Patent pending

@misc{rossi17graphSearchEngine,
   author={Ryan A. Rossi and Rong Zhou},
   title={A Graph Search Engine},
   booktitle={Patent},
   year={2017},
   yearfiled={2016},
}
Patent

Deep Relational Learning

, .

Patent, .

Patent application filed

@misc{rossi16deep-relational-learning,
   author={Ryan A. Rossi and Rong Zhou},
   title={Deep Relational Learning},
   booktitle={Patent},
   year={2016},
   yearfiled={2015},
}
Patent

Fast and Accurate Unbiased Graphlet Estimation

, .

Patent, .

Patent application filed, USPTO App. #15/179724

@misc{rossi16patent-graphlet-estimation,
   author={Ryan A. Rossi and Rong Zhou},
   title={Fast and Accurate Unbiased Graphlet Estimation},
   booktitle={Patent},
   year={2016},
   yearfiled={2015},
}
Patent

Efficient Parallel Hybrid CPU-GPU Graph Mining and Learning via Induced Subgraph Features

, .

Patent, .

Patent application filed

@misc{rossi15patent-hybrid-cpu-gpu-graphlets,
   author={Ryan A. Rossi and Rong Zhou},
   title={Efficient Parallel Hybrid CPU-GPU Graph Mining and Learning via Induced Subgraph Features},
   booktitle={Patent},
   year={2016},
   yearfiled={2016},
}
Patent

System And Method For Compressing Graphs Via Cliques

, .

Patent, .

Patent application filed, USPTO App. #15/183561

@misc{rossi15patent-clique-compression,
   author={Ryan A. Rossi and Rong Zhou},
   title={System And Method For Compressing Graphs Via Cliques},
   booktitle={Patent},
   year={2016},
   yearfiled={2015},
}
Patent

Localized Visual Graph Filters for Complex Graph Queries

, .

Patent, .

Patent application filed, USPTO App. #15/175751

@misc{rossi16patent-localized-visual,
   author={Ryan A. Rossi and Rong Zhou},
   title={Localized Visual Graph Filters for Complex Graph Queries},
   booktitle={Patent},
   year={2016},
   yearfiled={2015},
}
Patent

Computer-implemented System And Method For Relational Time Series Learning

, .

US Patent No. 10438130, .

Patent application filed, USPTO App. #14/955965

@misc{rossi16patent-rel-time-series,
   author={Ryan A. Rossi and Rong Zhou},
   title={Computer-implemented System And Method For Relational Time Series Learning},
   booktitle={US Patent No. 10438130},
   year={2016},
   yearfiled={2014},
}
Patent

, .

Patent, .

US Patent No. 10235403

A system and a method perform matrix factorization. According to the system and the method, at least one matrix is received. The at least one matrix is to be factorized into a plurality of lower-dimension matrices defining a latent feature model. After receipt of the at least one matrix, (More...)
@misc{rossi16patent-pcmf,
   author={Ryan A. Rossi and Rong Zhou},
   title={Parallel Collective Matrix Factorization Framework for Big Data},
   booktitle={Patent},
   year={2015},
   yearfiled={2014},
}

, , , .

arXiv:1810.02959, Pages 15, .

Higher-order connectivity patterns such as small induced sub-graphs called graphlets (network motifs) are vital to understand the important components (modules/functional units) governing the configuration and behavior of complex networks. Existing work in higher-order clustering has focused on simple homogeneous graphs with a single node/edge type. However, heterogeneous graphs consisting (More...)
@inproceedings{higher-order-clustering-heter-arxiv,
   author={Aldo G. Carranza and Ryan A. Rossi and Anup Rao and Eunyee Koh},
   title={Higher-Order Clustering for Heterogeneous Networks via Typed Motifs},
   booktitle={arXiv:1810.02959},
   year={2018},
   pages={15},
}
Book

, , Stephen Sheel.

Book ISBN 1329925912, .

Bioinformatics is the application of computational techniques and tools to analyze and manage biological data. This book provides an introduction to bioinformatics through the use of Action Labs. These labs allow students to get experience using real data and tools to solve difficult problems. The book comes with supplementary (More...)
@article{introBINF,
   author={Jean-Louis Lassez and Ryan A. Rossi and Stephen Sheel},
   title={Introduction to Bioinformatics Using Action Labs},
   journal={Book ISBN 1329925912},
   year={2009},
}

Research Experience

Senior Research Scientist, Adobe Research
Member of Research Staff, Palo Alto Research Center
Visiting Researcher, Palo Alto Research Center (Xerox PARC)
Research Fellow, Purdue University (2009-2012)

Research Assistant, Lawrence Livermore National Laboratory (ISCR)
LLNL Scholar: Cyber Defenders Program (2011-2012)

Research Assistant, Naval Research Laboratory, AI Research Center
Advisor: David Aha, Co-advisor: Luke McDowell, ONR NREIP
Relational Representation Discovery in Statistical Relational Learning, (Summer 2010)

Research Assistant, Coastal Carolina University (2005-2009)
Advisor: Jean-Louis Lassez, Retired IBM T.J. Watson Research Center
(Mathematics Genealogy Project)

Research Assistant, NASA Jet Propulsion Laboratory, (Summer 2009)
California Institute of Technology, Space Grant/USRP Fellowship
(Returned to continue my research).

Research Assistant, NASA Jet Propulsion Laboratory, (Spring 2009)
California Institute of Technology, USRP NASA Fellowship
Advisor: Mark Powell(Scalable Image Processing) and Khawaja Shams(Cloud Computing)

Research Assistant, University of Massachusetts at Amherst, KDL, (Summer 2008)
Advisor: David Jensen, Graduate Advisor: Brian Taylor, REU NSF Fellowship

Research Assistant, New Mexico Tech, Institute for Complex Additive Systems
Advisor: Srinivas Mukkamala, Senior Research Scientist, ICASA (Summer 2007)


Teaching Experience

Search Engine Theory, Instructor, Spring 2008
This course was taught from a machine learning perspective using a variety of resources and recent papers along with a series of homeworks and projects implementing the significant parts of a search engine.

Algorithms in Bioinformatics, Teaching Assistant, Fall 2007
Numerical Methods, Teaching Assistant, Spring 2007
Introduction to Bioinformatics, Teaching Assistant, Fa 2008, Fa/Spr 2007, Spr 2006
Introduction to Algorithm Design II, Teaching Assistant, Spring 2006
Introduction to Algorithm Design I, Teaching Assistant, Spring 2006

As a teaching assistant I gave lectures and review sessions; developed homeworks, labs, and programs, held office hours, and maintained course website.


Books / Lecture Notes

Bioinformatics is the application of computational techniques and tools to analyze and manage biological data. This book provides an Introduction to Bioinformatics through the use of Action Labs. These labs allow students to get experience using real data and tools to solve difficult problems. The book comes with supplementary slides, papers, and tools. The labs use data from Breast Cancer, Liver Disease, Diabetes, SARS, HIV, Extinct Organisms, and many others. The book has been written for first or second year computer science, mathematics, and biology students. The book is published by the Digital University Press. [pdf version] (6.2 MB)

KAIS SIGKDD TKDE Internet Mathematics WSDM WAW JAIR WWW AI

Research Positions

  • Present 2015

    Member of Research Staff

    Palo Alto Research Center

  • 2015 2009

    Ph.D. Fellow

    Purdue University, Computer Science

  • 2015 2013

    Visiting Researcher

    Palo Alto Research Center

Education

  • Ph.D. 2015

    Ph.D. in Computer Science

    Purdue University

  • M.S.2013

    Master of Science in Computer Science

    Purdue University

  • B.S.2009

    Bachelor of Science in Computer Science

    CCU

Honors and Awards

  • 2015
    Purdue Bilsland Dissertation Fellowship
    Purdue Bilsland Dissertation Fellowship
  • 2012
    DoD NDSEG Fellow
    DoD NDSEG Fellow
  • 2009
    National Science Foundation GRFP Award
    National Science Foundation GRFP Award

Research Positions

  • 2017-Present
    Adobe Research
    Senior Research Scientist, Adobe Research
  • 2015-2017
    PARC
    Member of Research Staff, Palo Alto Research Center (Xerox PARC)
  • 2009-2015
    Purdue
    Research Fellow, Department of Computer Science, Purdue University
  • 2013-2015
    PARC
    Visiting Researcher, Palo Alto Research Center (PARC)
  • 2011-2012
    image
    Research Assistant, Lawrence Livermore National Laboratory (ISCR)
  • Summer 2010
    Naval Research Laboratory (NRL)
    Research Assistant, Naval Research Laboratory (Artificial Intelligence Center)
  • 2009
    NASA JPL
    Research Assistant, NASA Jet Propulsion Laboratory/California Institute of Technology
  • Summer 2008
    UMass CS
    Research Assistant, University of Massachusetts at Amherst (UMass Amherst)