Reliable Machine Learning from Imperfect Supervision

In recent machine learning applications, it is often challenging to collect a large amount of high-quality labeled data. However, learning from unlabeled data is not necessarily reliable. To overcome this problem, the use of imperfect data is promising. In this talk, I will review our recent research on reliable machine learning from imperfect supervision, including weakly supervised learning, noisy label learning, and transfer learning. Finally, I will discuss how machine learning research should evolve in the era of large foundation models.

About the Speaker

Professor Masashi Sugiyama

Tokyo Institute of Technology, Japan

Professor Masashi Sugiyama received his Ph.D. in Computer Science from Tokyo Institute of Technology, Japan, in 2001. After serving as an assistant and associate professor at the same institute, he became a professor at the University of Tokyo in 2014. Since 2016, he has also served as the director of the RIKEN Center for Advanced Intelligence Project. His research interests include theories and algorithms of machine learning. He was awarded the Japan Academy Medal in 2017 and the Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology of Japan in 2022.