报告题目: Theory and Algorithms for Continual Learning
报告人：Bing Liu
时间：5月24日（周三） 上午 9:00—11:00
地点：王选所106会议室

Abstract
Continual learning (CL) learns a sequence of tasks incrementally. A challenging setting of CL is class incremental learning (CIL). While it is well known that catastrophic forgetting (CF) is the major difficulty for CIL, we argue that there is also an equally challenging problem of inter-task class separation (ICS). This talk first presents a theoretical study on (1) the learnability of the CIL problem and (2) how to solve the CIL problem in a principled manner. The key theoretical results are: (1) CIL is learnable and (2) the necessary and sufficient conditions for solving CIL are good within-task prediction and good out-of-distribution (OOD) detection. Based on the theory, several new CIL methods are designed that can deal with both CF and ICS, and significantly outperform existing CIL baselines. At the end of the talk, I will also briefly discuss a recent work on continual pre-training of language models.
Biography
Bing Liu is a distinguished professor at the University of Illinois Chicago. He received his Ph.D. in Artificial Intelligence (AI) from the University of Edinburgh. His current research interests include continual/lifelong learning, lifelong learning dialogue systems, sentiment analysis, machine learning and natural language processing. He has published extensively in prestigious conferences and journals and authored four books: one about lifelong machine learning, two about sentiment analysis, and one about Web mining. Three of his papers have received the Test-of-Time awards, and another one received Test-of-Time honorable mention. Some of his works have also been widely reported in popular and technology press internationally. He served as the Chair of ACM SIGKDD from 2013-2017 and as program chair of many leading data mining conferences. He is the winner of 2018 ACM SIGKDD Innovation Award, and is a Fellow of ACM, AAAI, and IEEE. Additional information about him can be found at https://www.cs.uic.edu/~liub/.