Learning under Noisy Supervision
Abstract
Noisy data is ubiquitous and harms the performance of most learning algorithms, and sometimes makes existing algorithms break down. This tutorial summarizes the most recent noisy-supervision-tolerant techniques, from the viewpoint of statistical learning, deep learning and their applications in industry.Biographies
Masashi SugiyamaMasashi Sugiyama is Director of RIKEN Center for Advanced Intelligence Project and Professor at the University of Tokyo. He received the PhD degree in computer science from Tokyo Institute of Technology. His research is designing statistical data analysis algorithms for challenging problems. He (co)-authored machine learning monographs such as Machine Learning in Non-Stationary Environments (MIT Press), Density Ratio Estimation in Machine Learning (Cambridge University Press), Statistical Reinforcement Learning (Chapman and Hall/CRC), Introduction to Statistical Machine Learning (Morgan Kaufmann), and Variational Bayesian Learning Theory (Cambridge University Press). He served as Program Co-chair for the Neural Information Processing Conference, International Conference on Artificial Intelligence and Statistics, and Asian Conference on Machine Learning. He serves as an Associate Editor for the IEEE Transactions on Pattern Analysis and Machine Intelligence and an Action Editor for the Neural Network journal. He received the Japan Academy Medal in 2017.
Tongliang Liu
Tongliang Liu is a Lecturer in Machine Learning with the University of Sydney (USYD). He organized a tutorial on learning with label noise at a main Australian computer vision conference (DICTA) in 2017. Web: http://dicta2017.dictaconference.org/tutorial.html. He has published around 20 papers on learning with Noisy Supervision at top venues.
Bo Han
Bo Han is an Assistant Professor of Computer Science at Hong Kong Baptist University, and a Visiting Scientist at RIKEN Center for Advanced Intelligence Project (RIKEN AIP). He was a Postdoc Fellow at RIKEN AIP (2019-2020). He received his Ph.D. degree in Computer Science from University of Technology Sydney in 2019. He has served as area chairs of NeurIPS and ICLR. He received the RIKEN BAIHO Award (2019) and RGC Early Career Scheme (2020).
Quanming Yao
Gang Niu
Gang Niu is currently a research scientist (indefinite-term) at RIKEN Center for Advanced Intelligence Project. He received the PhD degree in computer science from Tokyo Institute of Technology in 2013. Before joining RIKEN as a research scientist, he was a senior software engineer at Baidu and then an assistant professor at the University of Tokyo. He has published more than 70 journal articles and conference papers, including 14 NeurIPS (1 oral and 3 spotlights), 28 ICML, and 2 ICLR (1 oral) papers. He has served as an area chair 14 times, including ICML 2019–2021, NeurIPS 2019–2021, and ICLR 2021–2022.