Rate My Professor Jian Tang

Tang's research focuses on graph neural networks, graph representation learning, deep generative models, and artificial intelligence applications in drug discovery, molecular modeling, and computational biology. He has received the Amazon Faculty Research Award in 2020 for his project on deep active learning for graph neural networks, the Prix de recherche Nouveau chercheur 2022 from HEC Montréal, the best paper award at ICML 2014 for “Understanding the limiting factors of topic modeling via posterior contraction analysis,” and best paper nomination at WWW 2016 for “Visualizing Large-scale and High-dimensional Data.” His influential publications include “LINE: Large-scale Information Network Embedding” (WWW 2015, cited over 7,000 times), “RotatE: Knowledge Graph Embedding by Relational Rotation in Complex Space” (ICLR 2019, cited over 3,900 times), “Scientific Discovery in the Age of Artificial Intelligence” (Nature 2023), “InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization” (ICLR 2020), and “GeoDiff: A Geometric Diffusion Model for Molecular Conformation Generation” (ICLR 2022). Tang has developed open-source frameworks such as TorchDrug and GraphVite, served as area chair for NeurIPS 2021 and ICML 2021, and delivered invited talks at institutions including MIT, Yale University, and Tsinghua University.