时 间：2022/10/25 上午10:00
Knowledge graphs are important in a variety of applications such as question answering, online search, recommender systems, and drug discovery. As knowledge graphs are usually incomplete, a fundamental task on knowledge graphs is predicting missing facts by reasoning with existing observed facts, a.k.a. knowledge graph reasoning. In this talk, I will introduce some of our work along this direction including an embedding-based approach (RotatE, ICLR'19), symbolic logic rule based approaches (pLogicNet, NeurIPS'19; RNNLogic, ICLR'21), and a very recent work Neural Bellman-Ford Networks (NBFNet, NeurIPS'21), which combines traditional logic rule-based methods with graph neural networks, enjoys good interpretability, and works in both transductive and inductive settings.
Jian Tang is currently an associate professor at Mila-Quebec AI Institute and also at Computer Science Department and Business School of University of Montreal. He is a Canada CIFAR AI Research Chair. His main research interests are graph representation learning, graph neural networks, geometric deep learning, deep generative models, knowledge graphs and drug discovery. During his PhD, he was awarded with the best paper in ICML2014; in 2016, he was nominated for the best paper award in the top data mining conference World Wide Web (WWW); in 2020, he is awarded with Amazon and Tencent Faculty Research Award. He is one of the most representative researchers in the growing field of graph representation learning and has published a set of representative works in this field such as LINE and RotatE. His work LINE on node representation learning has been widely recognized and is the most cited paper at the WWW conference between 2015 and 2019. He has also done many pionnering work on geometric deep learning for drug discovery and released an open-source machine learning famework for drug discovery, called TorchDrug/TorchProtein. He is an area chair of ICML and NeurIPS.