My name is Chunpai Wang (王春派). I am a PhD candidate in Computer Science at State University of New York at Albany, where I work on user modeling and sequential recommendation. My thesis advisor is Dr. Sherry Sahebi. During my PhD, I am also fortunate to be advised by Dr. Feng Chen from UT-Dallas and Dr. Daniel B. Neill from NYU on anomaly pattern detection on large-scale graphs. I received a B.S. degree in Computer Science and a B.A. degree in Statistics from the University of Rochester and I was fortunate to be advised by Dr. Jiebo Luo on graph mining research during my undergraduate studies.

Email | Google Scholar | Linkedin

profile photo


Currently, I am mainly working on user modeling and sequential recommendation with applications where users' inherent states are not observable from partially observed data. The title of my working thesis is "Sequential User Modeling and Recommendation Under Partially Obeservable Environment". I am also working on counterfactual evaluation and model-based reinforcement learning that are related to offline evaluation of long-term and delayed rewards of sequential recommendation policies. Besides, I am also interested in and have been working on anomaly pattern detection in images and graphs. Overall, I have 6 years hand-on experience on doing research independently and collaboratively, including identifing the nature of a problem, conducting literurature reviews, statistical modeling, rigorous experimental design and result analysis. Following is a list of my publications.

Calibrated Nonparametric Scan Statistics for Anomalous Pattern Detection on Graphs
Chunpai Wang, Daniel B. Neill, and Feng Chen
36th AAAI Conference on Artificial Intelligence (AAAI), 2022
Acceptance Rate: 15%, and Selected for Oral Presentation.
paper / appendix / slides / code

STRETCH: Stress and Behavior Modeling with Tensor Decomposition of Heterogeneous Data
Chunpai Wang, Shaghayegh Sahebi, and Helma Torkamaan
30th IEEE/WIC/ACM International Joint Conference on Web Intelligence and Intelligent Agent Technology (WI-IAT), 2021

MOCHI: an Offline Evaluation Framework for Educational Recommendations
Chunpai Wang, Shaghayegh Sahebi, and Peter Brusilovsky
Perspectives at 15th ACM Conference on Recommender Systems (RecSys), 2021
paper / code

Learning from Non-Assessed Resources: Deep Multi-Type Knowledge Tracing
Chunpai Wang, Siqian Zhao, and Shaghayegh Sahebi
14th International Conference on Educational Data Mining (EDM), 2021
Acceptance Rate: 20%
paper / video / code

Knowledge Tracing for Complex Problem Solving: Granular Rank-based Tensor Factorization
Chunpai Wang, Shaghayegh Sahebi, Siqian Zhao, Peter Brusilovsky, and Laura O. Moraes
29th ACM Conference on User Modeling, Adaptation and Personalization (UMAP), 2021
Acceptance Rate: 23%
paper / video / code

A Framework for Subgraph Detection in Interdependent Networks via Graph Block-Structured Optimization
Fei Jie, Chunpai Wang, Feng Chen, Lei Li, and Xindong Wu,
IEEE Access, 2020

Modeling Knowledge Acquisition from Multiple Learning Resource Types
Siqian Zhao*, Chunpai Wang*, and Shaghayegh Sahebi
13th International Conference on Educational Data Mining (EDM), 2020
(* Equal Contribution)
paper / code

Block-Structured Optimization for Anomalous Pattern Detection in Interdependent Networks
Fei Jie*, Chunpai Wang*, Feng Chen, Lei Li, and Xindong Wu,
IEEE International Conference on Data Mining (ICDM), 2019
(* Equal Contribution, Acceptance Rate: 18.5%)

Collective Subjective Logic: Scalable Uncertainty-based Opinion Inference
Feng Chen, Chunpai Wang, and Jin-Hee Cho
IEEE International Conference on Big Data (BigData), 2017
Acceptance Rate: 18%