Tie-Yan Liu is a Distinguished Scientist at Microsoft, leading the Asia team of Microsoft Research AI4Science. He is a fellow of the IEEE, the ACM and the AAIA. He is also an adjunct/honorary Professor at Tsinghua University, University of Nottingham and Hong Kong University of Science and Technology.
Tie-Yan has served as general chair, program committee chair and (senior) area chair for various top conferences. These include WWW/WebConf, SIGIR, KDD, ICML, NeurIPS, ICLR, IJCAI and AAAI. He has also served as an Associate Editor of ACM Transactions on Information Systems, ACM Transactions on the Web and IEEE Transactions on Pattern Analysis and Machine Intelligence.
As a world-renowned machine learning expert, Tie-Yan has made notable contributions in ranking problems (learning to rank), learning from tabular data (LightGBM) and learning under resource constraints (dual learning, LightLDA, FastSpeech). Recently, he has shown great interest in AI for Science.
Tie-Yan and his team developed Graphormer for molecule representation, which won the KDD Cup 2021 on molecular property prediction and the direct track of Open Catalyst Challenge 2021. They used molecular dynamics simulation to understand SAR-COV-2 and discovered the wedge effect of the NTD of the spike protein, which indicates a potential new drug target for COVID-19.
Furthermore, Tie-Yan and his collaborators applied deep learning to detect new particles from jet data, to effectively solve governing equations of fluid dynamics and to identify non-conservative components in observational data as new physics.