DSA Thrust Seminar | Frontier Problems in Weakly Supervised Learning
Due to the unaffordable monetary or time cost of collecting fully labeled data in some real-world scenarios, weakly supervised learning that aims to learn with weak supervision has attracted increasing attention in recent years. In this presentation, I will introduce our studies on some frontier problems in weakly supervised learning, such as partial-label learning, noisy-label learning, and other novel weakly supervised learning problems.
Lei Feng is currently a Professor (PhD supervisor) at the College of Computer Science, Chongqing University, China. He is also a Visiting Scientist at RIKEN Center for Advanced Intelligence Project, Japan. He received his PhD degree in Computer Science from Nanyang Technological University, Singapore, in 2021. He also received NTU SCSE Outstanding PhD Thesis Award Runner-Up, in the situation of early graduation. Besides, he was selected in the list of Forbes 30 under 30 China 2021. His research interests mainly lie in machine learning and data mining, and he has published over 20 machine learning papers on some prestigious conferences and journals. He has served as a senior program committee member for IJCAI 2021 and AAAI 2022, an expert reviewer for ICML 2021, program committee member for other top conferences, and reviewer for many prestigious journals.