More about HKUST
Speaker: Dr. Bo Han Hong Kong Baptist University Title" "Exploring Trustworthy Machine Learning under Imperfect Data" Date: Monday; 15 April 2024 Time: 4:00pm - 5;00pm Venue: Lecture Theater F (Leung Yat Sing Lecture Theater), near lift 25/26 HKUST Abstract: Trustworthy machine learning is one of emerging and critical topics in modern machine learning, since most real-world data are easily imperfect, such as online transactions, healthcare, cyber-security, and robotics. Intuitively, trustworthy intelligent system should behave more human-like, which can learn and reason from imperfect data including labels, features, systems and prompts. Therefore, in this talk, I will introduce trustworthy machine learning from several human-inspired views, including reliability, robustness, adaptability and safety. Specifically, reliability will consider uncertain cases, namely reliable learning with noisy labels. Robustness will discuss adversarial conditions, namely robust learning with adversarial features. Adaptability will explore the algorithm interactions, namely adaptive learning with federated systems. Safety will investigate harmful prompts in foundation models, namely safe reasoning with jailbreak attacks. Furthermore, I will introduce the newly established Trustworthy Machine Learning and Reasoning (TMLR) Group at Hong Kong SAR and Greater Bay Area. ********************* Biography: Bo Han is an Assistant Professor in Machine Learning at Hong Kong Baptist University and a BAIHO Visiting Scientist at RIKEN AIP, where his research focuses on machine learning, deep learning, foundation models and their applications. He was a Visiting Faculty Researcher at Microsoft Research and a Postdoc Fellow at RIKEN AIP. He has co-authored two machine learning monographs by MIT Press and Springer Nature. He has served as Area Chairs of NeurIPS, ICML, ICLR, UAI and AISTATS. He has also served as Action Editors and Editorial Board Members of JMLR, MLJ, TMLR, JAIR and IEEE TNNLS. He received Outstanding Paper Award at NeurIPS, Notable Area Chair at NeurIPS, Outstanding Area Chair at ICLR, and Outstanding Associate Editor at IEEE TNNLS.