Abstract: A fundamental problem in modern vector databases is to process approximate similarity queries in high dimensional space. Vector databases become a central research topic with the increasing popularity of large language models. Troubled by the “curse of dimensionality” issue, it has long been questioned whether it is possible to index high-dimensional data effectively and whether the nearest neighbor queries are meaningful in high-dimensional spaces. Another critical issue is how such queries can be processed efficiently. In this talk, I will provide an overview of research progress in this field and share our recent research results in managing and processing high-dimensional data in the era of generative AI.
Bio: Professor Xiaofang Zhou is Otto Poon Professor of Engineering and Chair Professor of Computer Science and Engineering at The Hong Kong University of Science and Technology (HKUST). He is Head of the Department of Computer Science and Engineering at HKUST. He has been working in database systems, data quality management, big data analytics, machine learning and AI. He was Program Committee Chair of the IEEE International Conference on Data Engineering (ICDE 2013), the ACM International Conference on Information and Knowledge Management (CIKM 2016), and the International Conference on Very Large Databases (PVLDB 2020). He was the General Chair of ICDE 2025 and ACM Multimedia Conference (MM 2015). Before joining HKUST, He was a Professor of Computer Science at The University of Queensland, leading its Data Science discipline. Professor Zhou is a Global STEM Scholar of Hong Kong and a Fellow of IEEE.