Unifying Continual Learning and OOD Detection
[CFAR Distinguished Professor Lecture Series]
Unifying Continual Learning and OOD Detection (Hybrid event) by Prof Liu Bing
Continual learning (CL) learns a sequence of tasks incrementally. One of its main setting, class incremental learning (CIL) remains a challenging scenario. While it is well known that catastrophic forgetting (CF) is a major difficulty for CIL, inter-task class separation (ICS) is equally challenging. In this talk, Prof Liu Bing will first present a theoretical investigation on ways to solve the CIL problem and the key results achieved: (1) The necessary and sufficient conditions for good CIL are good within-task prediction and task-id prediction; and (2) the task-id prediction is correlated with out-of-distribution (OOD) detection. The theory unifies OOD detection and continual learning and proves that a good CIL method could also perform OOD detection well. Prof Liu will also discuss how some new CIL methods (designed based on the theory) could outperform existing CIL baselines by a large margin and also perform OOD detection well.
OOD (or novelty) detection and incremental learning of the identified novel items are two key functions to enable artificial intelligence (AI) agents to function and learn independently in the open world with unknowns. Prof Liu will conclude the talk by exploring ways to enable learning on the fly in the open world to achieve open-world continual learning.
Unifying Continual Learning and OOD Detection (Hybrid event) by Prof Liu Bing
21 Feb 2023 | 11.00am (Singapore Time)
Continual learning (CL) learns a sequence of tasks incrementally. One of its main setting, class incremental learning (CIL) remains a challenging scenario. While it is well known that catastrophic forgetting (CF) is a major difficulty for CIL, inter-task class separation (ICS) is equally challenging. In this talk, Prof Liu Bing will first present a theoretical investigation on ways to solve the CIL problem and the key results achieved: (1) The necessary and sufficient conditions for good CIL are good within-task prediction and task-id prediction; and (2) the task-id prediction is correlated with out-of-distribution (OOD) detection. The theory unifies OOD detection and continual learning and proves that a good CIL method could also perform OOD detection well. Prof Liu will also discuss how some new CIL methods (designed based on the theory) could outperform existing CIL baselines by a large margin and also perform OOD detection well.
OOD (or novelty) detection and incremental learning of the identified novel items are two key functions to enable artificial intelligence (AI) agents to function and learn independently in the open world with unknowns. Prof Liu will conclude the talk by exploring ways to enable learning on the fly in the open world to achieve open-world continual learning.
SPEAKER
Prof Liu Bing
Distinguished Professor
Department of Computer Science
University of Illinois Chicago (UIC)
Distinguished Professor
Department of Computer Science
University of Illinois Chicago (UIC)
Prof Liu Bing is a distinguished professor at the University of Illinois Chicago (UIC). 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 is also the author to four books: one on lifelong machine learning, two on sentiment analysis, and one about web mining. Prof Liu has received the Test-of-Time awards for three of his papers and also recognised with the Test-of-Time honorable mention for another paper. Some of his works have also been widely reported in popular and technology press internationally. He had served as the Chair of ACM SIGKDD from 2013 – 2017 and program chair of many leading data mining conferences. He was also the winner of the 2018 ACM SIGKDD Innovation Award, and is a Fellow of ACM, AAAI, and IEEE.
A*STAR celebrates International Women's Day
From groundbreaking discoveries to cutting-edge research, our researchers are empowering the next generation of female science, technology, engineering and mathematics (STEM) leaders.
Get inspired by our #WomeninSTEM