Data Science and Analytics Thrust Seminar | Knowledge Graph Reasoning with Graph Neural Network
Supporting the below United Nations Sustainable Development Goals:支持以下聯合國可持續發展目標：支持以下联合国可持续发展目标：
Knowledge graph (KG), as a special kind of graph-structured data, has benefited many downstream tasks in data mining and machine learning such as search engine, recommendation system and dialogue robot. Recently, with the development of graph neural network (GNN), various GNN-based methods have been proposed for KG reasoning, achieving significant reasoning results. In this talk, representative methods using GNN for KG from perspective of message aggregation and subgraph learning are introduced and discussed, including the future research trends in this area.
Dr. Yongqi Zhang is a research scientist in 4Paradigm Inc. He received the bachelor's degree from Shanghai Jiao Tong University in 2015, and PhD degree from HKUST in 2020, advised by Prof. Lei Chen. His research interests include knowledge graph reasoning, graph neural network and automated machine learning. His research project AutoBLM won the first place on the leaderboard of biomedical link prediction task in open graph benchmark. He has published several top-tier journal/conference papers, including TPAMI, VLDB-Journal, NeurIPS, ACL, WWW, etc., as the first author.