Dean's Associate Professor of Information Systems
2118C Hamburg Hall
I am the Heinz College Dean's Associate Professor at Carnegie Mellon University's Heinz College of Information Systems and Public Policy. I also hold courtesy appointments at the Machine Learning Department (MLD) and the Computer Science Department (CSD) of School of Computer Science (SCS).
At Heinz, I
direct the Data Analytics Techniques Algorithms (DATA) Lab.
My research interests are broadly in
data mining, graph mining, machine learning, and knowledge discovery, with specific
focus on anOmaLiEs---identifying and characterizing 'what stands out' in large-scale, time-varying, multi-modal data sources
through scalable computational methods. Prospective students with similar interests, please see here.
A short bio can be found here
- Dec, 2020 Joint work with Neil Shah @Snap on fairness-aware outlier detection is now on arXiv!
- Dec, 2020 Keynote speaker at the 9th International Conference on Complex Networks 2020 (Virtual), December 1-3. Slides are here. A similar version of the talk is on Youtube.
- Nov, 2020 OddBall (authored w/ Mary and Christos) received The Most Influential Paper Award at PAKDD 2020!
- Sep, 2020 Joint work with U Michigan on learning with graph neural networks under heterophily to appear at NeurIPS 2020!
- May, 2020 Our work on spotting emerging rare classes continually is to appear at ACM TKDD Journal!
- Apr, 2020 Couple of talks, Human-in-the-loop Anomaly Mining and Tackling Structure And Oversmoothing for Graph-based SSL, at the INFORMS Annual Meeting 2020.
- Apr, 2020 I am co-organizing the 3rd ACM SIGKDD 2020 Workshop on Machine Learning in Finance with Nitesh Chawla,
Tanveer Faruquie, Senthil Kumar, Saurabh Nagrecha, and Jose A. Rodriguez-Serrano. Submissions here, due May 20th!
- Mar, 2020 I will attend the Amazon Scholar & Faculty Summit Fall 2020.
- Dec, 2019 Our work on tackling oversmoothing in graph neural networks via a novel normalization scheme to appear at ICLR 2020!
- Sep, 2019 Awarded an Adobe University Marketing Research Grant for our project titled
Entity Resolution and User De-duplication of Recurring Fraudsters and Free-loaders. Thanks Adobe!
- Sep, 2019 Our work investigating nearest neighbor methods for anomaly detection to appear at NeurIPS 2019!
- Sep, 2019 I am giving an invited talk (highlighting the applications of my research on anomaly mining to fraud detection) at the AI in Finance Summit in NYC. See the agenda here.
- July, 2019 I am officially promoted to Associate Professor! Thanks to all the students, post-docs, collaborators, letter writers, and role models who helped make this happen :-)
- June, 2019 Our work on continual rare class classification to appear at ECML PKDD 2019!
- May, 2019 I am visiting and giving talks at Amazon Inc. at Palo Alto and the Stanford RAIN Seminar.
- Apr, 2019 I am honored to receive the prestigious title "Heinz College Dean's Professorship" for the next 3 years!
- Apr, 2019 Our work on human-in-the-loop interactive anomaly detection received the Best Research Paper Award at SIAM SDM'19!!!
- Mar, 2019 I am co-organizing the 2nd Workshop on Anomaly Detection in Finance at ACM SIGKDD 2019. Submit your related work by May 12!
- Feb, 2019 I am one of the Gilbreth Lecturers at the upcoming National Academy of Engineering's National Meeting! I will give a talk titled "Anomaly Mining: Detection and Beyond" to 100-200 middle and high school students in addition to the 40-50 NAE members in attendance. Here is a photo :-)
- Jan, 2019 Our work on contrastive and visual topic modeling to appear at TheWebConf'19 as a full paper!
- Dec, 2018 Our work on human-in-the-loop interactive anomaly detection to appear at SIAM SDM'19!
- Nov-Dec, 2018 I am visiting Singapore Management University for a collaborative project on early event detection using large-scale mobility data (bus, metro, autoparks, and social media).
- September, 2018 Our paper is awarded the Best Student Machine Learning Paper Runner-up at ECML PKDD 2018! The main scope of the work is to show why and how one could leverage privileged information for anomaly detection.
- August, 2018 2 conference papers on graph learning for semi-supervised classification and change point detection and localization on a graph accepted to appear at ACM CIKM'18!
- July, 2018 Our work on analyzing employee peer-reviews to appear at ACM/IEEE ASONAM'18 Industry Track!
- June, 2018 3 conference papers on anomaly detection and explanation accepted to appear at ECML PKDD'18!
- June, 2018 Our work on explaining anomalous patterns to appear at ECML PKDD'18 Journal Track!
- June, 2018 Upcoming talks and travel:
- May, 2018 Our work on outlier detection in feature-evolving data streams to appear in ACM SIGKDD'18!
- Mar, 2018 I am co-organizing the 5th ACM SIGKDD 2018 Workshop ODD v5.0: Outlier Detection De-constructed,
with Evgeny Burnaev (Skolkovo IST), Charu Aggarwal (IBM), Christos Faloutsos (CMU).
Submit your ODD work by May 15th!
- Feb, 2018 Our work on graph-based semi-supervised learning in noisy multi-graphs to appear in PAKDD'18.
- Feb 9, 2018 Two talks at ACM WSDM: "Mining Rich Graphs: Ranking, Classification, and Anomaly Detection" at International Workshop on Heterogeneous Networks Analysis, and "Opinion Spam Detection: A Story of Networks, Meta-data and an Oracle" at MIS2: Workshop on Misinformation and Misbehavior Mining on the Web.
- Jan, 2018 Our work on attributed graphs: discovering communities and anomalies, interactive visual exploration and summarization appeared in Transactions on Knowledge Discovery from Data (TKDD) Journal, Volume 12, Issue 2.
- Nov, 2017 Talk at IEEE ICDM Workshop on High Performance Graph Data Mining and Machine Learning; Online Detection of Anomalous Heterogeneous Graphs with Streaming Edges
- Oct, 2017 Talk at UT Southwestern Medical Center CSB (Computational and Systems Biology) Seminar; autOmated Data Description (ODD): Explaining Anomalies for Human Interpretation
- Oct, 2017 Talk at UT Austin McCombs School of Business Information Management Seminar; Temporal Prediction of Customer Purchases and Using Forecasts in Coupon Design
- Sep, 2017 Talk at University of Pittsburgh Big Data Science Colloquium; Discovering Communities and Anomalies in Attributed Graphs: Interactive Visual Exploration and Summarization
- Aug, 2017 Talk at the ACM KDD Interactive Data Exploration and Analytics (IDEA) Workshop
- May, 2017 Our paper on promoting targeted time-limited digital coupons via purchase forecasts will appear at the Applied Data Science Track at ACM SIGKDD'17.
- Mar, 2017 Awarded an Adobe University Marketing Research Grant for our project titled
Real-time Detection of Online Click and Display Ad Exchange Fraud. Thanks Adobe!
- Talk at the Women in Data Science (WinDS) Workshop at SIAM SDM, April 2017
- Jan, 2017 Our paper on spam URL detection to appear at PAKDD'17 and another work on explaining class differences via attributes to appear at WWW'17 Web Science Track.
- Dec, 2016 Our work on Ranking in Heterogeneous Networks with Geo-Location Information will appear at SIAM SDM'17.
- Sep, 2016 We are building ODDS (Outlier Detection Data Sets) -- an online data repository! Stay tuned for updates!
- Sep, 2016 1 (short) paper Sequential Ensemble Learning for Outlier Detection: A Bias-Variance Perspective is accepted to ICDM'16.
- Sep, 2016 Our DAMI article on a general framework for optimizing network robustness by edge rewiring is published in Volume 30, Issue 5.
- Aug, 2016 I moved to CMU's
Heinz College, where I will focus on data mining for societal
problems through big data and computational methods. I am looking for students (PhD and MS)!
- July, 2016 Talk on anomaly mining at the US Army Research Labs.
- June, 2016 Talk on anomaly mining at the 2016 ICML Workshop on Anomaly Detection.
- June, 2016 Talk on opinion spam detection at Flipkart Inc. and Amazon India.
- May, 2016 1 paper Fast Memory-Efficient Anomaly Detection in Streaming Heterogeneous Graphs at ACM SIGKDD'16.
- May, 2016 Won SIAM SDM 2016 Best Paper Runner-up award for joint work with Bryan Perozzi on scalable ranking of anomalies in attributed graphs!
- Apr, 2016 Keynote speaker at the 12th International Workshop on Mining and Learning with Graphs (MLG) (co-located with KDD) on Aug 14th in San Francisco.
- Apr, 2016 Invited to serve as Workshops Co-Chair of ACM SIGKDD 2017.
- Apr, 2016 Invited speaker at the ICML 2016 Anomaly Detection Workshop on June 24th in NYC.
- Mar, 2016 Keynote speaker at the 2016 SDM Workshop on Mining Networks and Graphs: "Fraud Detection with Networks and Beyond" on May 7th in Miami.
- Mar, 2016 ACM SIGKDD 2016 Workshop ODD 4.0: Outlier Definition, Detection, and Description On-Demand, with F. Bell (Uber), E. Muller (HPI Germany), T. Senator (IARPA)
- Mar, 2016 1 short paper Temporal Opinion Spam Detection by Multivariate Indicative Signals to appear at ICWSM'16)
- Feb, 2016 Invited to serve as Workshops Co-Chair of SIAM SDM 2017.
- Feb, 2016 Our work on social security fraud detection with V. Van Vlasselaer, T. Eliassi-Rad, M. Snoeck, and B. Baesens is to appear in the Management Science Journal.
- Jan, 2016 Invited Associate Editorship for the IEEE Transactions on Knowledge and Data Engineering (TKDE) Journal.
- Jan, 2016 Invited to the Editorial Board of the Data Mining and Knowledge Discovery (DMKD) Journal.
- Jan, 2016 Our work on building anomaly ensembles is to appear in the Transactions on Knowledge Discovery from Data (TKDD) Journal.
- Dec, 2015 3 papers on attributed graph anomalies and opinion spam at SIAM SDM'16.
- Nov, 2015 1 paper Optimizing Network Robustness by Edge Rewiring: A General Framework at Data Mining and Knowledge Discovery (DAMI) (To appear at ECML PKDD'16)
- Nov, 2015 SIGKDD 2016 Student Travel Awards Co-chair
- Nov, 2015 ECML PKDD 2016 PhD Forum Co-chair
- Nov, 2015 Talk on "3D's of Anomaly Mining" at University of Illinois at Chicago
- Nov, 2015 Talk on "Semi-supervised Learning with Multi-Graphs" at Tepper School of Business at CMU
- Oct, 2015 Talk on "3D's of Anomaly Mining" at KU Leuven
- Oct, 2015 Attending Workshop on Information Networks (WIN) at NYU Business School (1 paper and 1 poster presentation).
- Sep, 2015 Invited speaker at the NII Shonan Meeting on "Analytics on Complex Networks: Scalable Solutions for Empirical Questions" Japan, Feb 2016.
- July, 2015 DARPA grant joint with IBM, Northwestern, UIC, and Stony Brook. Thanks DARPA!
- July, 2015 Offering a new course: Data Science Fundamentals this Fall.
- June, 2015 1 paper Discovering Opinion Spammer Groups by Network Footprints at ECML/PKDD'15.
- May, 2015 Received a Facebook Faculty Gift. Thanks Facebook!
- May, 2015 1 paper Collective Opinion Spam Detection: Bridging Review Networks and Metadata at ACM SIGKDD'15.
- Apr, 2015 Best Research Paper at SIAM SDM 2015. Congrats Hau and Shuchu!
- Apr, 2015 KDD 2015 tutorial "Graph-Based User Behavior Modeling: From Prediction to Fraud Detection" with Alex
Beutel and Christos Faloutsos.
- Apr, 2015 Co-chairing KDD 2015 Workshop on Outlier Definition, Detection, and Description (ODDx3). Submit your work!
- Mar, 2015 NSF CAREER award (2015-2020). Thanks NSF!
- Feb, 2015 1 paper Correlation of Node Importance Measures: An Empirical Study through Graph Robustness at WWW'15 (Web Science Track).
- Jan, 2015 Invited talk at Workshop on Statistical and Computational Challenges in Networks, Web Mining, and Cybersecurity, Montreal, Canada (May 4-8).
- Dec, 2014 2 papers Less is More: Building Selective Anomaly Ensembles and Where Graph Topology Matters: The Robust Subgraph Problem at SIAM SDM'15.
- Nov, 2014 Invited talk at Huawei Technologies R and D, Santa Clara, CA.
- June, 2014 1 paper Guilt-by-Constellation: Fraud Detection by Suspicious Clique Memberships at HICSS'15.
- Sep, 2014 Slides and Software for our SIGKDD 2014 paper is now online.
- Sep, 2014 New course Data Mining meets Graph Mining this Fall.
- July, 2014 Invited talk at NICTA Sydney, AU
- July, 2014 Best paper award at ADC'14.
- June, 2014 1 paper Fast Nearest Neighbor Search on Large Time-Evolving Graphs at ECML/PKDD'14.
- June, 2014 2 papers Watch Your Tags: Analysis of Question Response Time in StackOverflow and Joint Voting Prediction for Questions and Answers in CQA at IEEE/ACM ASONAM'14.
- May, 2014 1 paper Focused Clustering and Outlier Detection in Large Attributed Graphs at ACM SIGKDD'14.
- April, 2014 DAMI Survey on Graph-based Anomaly Detection
- April, 2014 ODD^2 @ KDD2014: Workshop on Outlier Detection and Description under Data Diversity
- Mar 20, 2014 Attend Facebook Machine Learning Open House, Menlo Park, CA
- Mar 19, 2014 Invited talk at Twitter Inc., San Francisco, CA
- Mar 17, 2014 Invited talk at University of California, Santa Barbara
- Mar, 2014 1 (full) paper Quantifying Political Polarity based on Bipartite Opinion Networks is accepted to ICWSM'14.
- Mar, 2014 1 (full) paper ConnotationWordNet: Learning Connotation of the
Word+Sense Network at ACL'14 for presentation.
- Feb, 2014 SDM Early Career Travel Grant, thanks SIAM!
- Jan, 2014 1 paper User Churn in Focused Q&A Sites: Characterizations and Prediction is accepted to WWW'14 WebSci for presentation.
- 1 (full) paper Make It or Break It: Manipulating Robustness in Large Networks is accepted to SIAM SDM'14.
- Apr 7, 2014 Full-day Workshop BGM @ WWW 2014 on Big Graph Mining
- 1 (short) paper on External Evaluation of Topic Models: A Graph Mining Approach
is accepted to ICDM'13.
- Teaching Machine Learning this Spring!
- 1 paper on Sex Differences in the Human Connectome is accepted to BHI'13.
- Tutorial on Big Graph Mining at this year's ASONAM. Slides right here
- Check out my new course Networks and Data Mining Techniques
- Anomaly, Event, and Fraud detection
- Large-scale Graph mining
- Deep learning and Graph Neural Networks
- Statistical data analysis and Applied machine learning
- Social and Information Network analysis
Selected Honors and Awards
- The Most Influential Paper Award, PAKDD 2020
- Heinz College Dean's Professor for Feb 2019-2022
- Best Research Paper Award, SIAM SDM 2019
- Best Student Machine Learning Paper Runner-up Award, ECML PKDD 2018
- NSF CAREER Award, 2015-2020
- Best Research Paper Runner-up Award, SIAM SDM 2016
- Best Research Paper Award, SIAM SDM 2015
- Army Research Office Young Investigator Award, 2013
- Best Paper Award, PAKDD 2010
- Best Knowledge Discovery Paper Award, ECML PKDD 2009