Pan Li
Joined department: Fall 2020
Education
Professor Li works on a broad range of problems regarding structured data processing, particularly graph and network data. His research mainly focuses on connecting theory and practice by developing principled algorithms to process structured data, pumping up their computational efficiency and digging out new applications. Specifically, his recent research results included spectral theory and scalable algorithms for higher-order graphs, theory and new applications for graph neural networks and scalable ranking algorithms for large-scale recommender systems.
Selected Publications
Pan Li and Olgica Milenkovic, "Inhomogoenous Hypergraph Clustering with Applications," NeurIPS 2017.
Pan Li and Olgica Milenkovic, "Submodular Hypergraph: p-Laplacian, Cheeger Inequalities and Spectral Clustering," ICML 2018.
Pan Li, Niao He and Olgica Milenkovic, "Quadratic Decomposable Submodular Function Minimization: Theory and Practice", JMLR 2020.
Pan Li, Yanbang Wang, Hongwei Wang, Jure Leskovec, "Distance Encoding -- Design Provably More Powerful Graph Neural Networks for Structural Representation Learning." NeurIPS 2020
Pan Li, Zhen Qin, Xuanhui Wang and Donald Metzler, "Combining Decision Trees and Neural Networks for Learning to Rank in Personal Search," KDD 2019.