Tutorial 2: Ivor W Tsang, Bo Han "Towards Noisy Supervision: Problems, Theories, and Algorithms"

Back to list of tutorials

  • Day 1 (Nov.17), 10:00-12:30
  • Room 1102 (11th floor)
  • Speakers: Ivor W Tsang (University of Technology Sydney), Bo Han (RIKEN)

Abstract

As dataset sizes grow bigger, it is laborious and expensive to obtain clean supervision. As a result, the volume of noisy supervision becomes enormous, e.g., crowdsourcing and single-label corruption. Unfortunately, noisy supervision harms the performance of most learning algorithms, and sometimes even makes existing algorithms break down. Recently, there are a brunch of theories and approaches proposed to deal with noisy data. In this tutorial, we summarize the foundations and go through the most recent noisy supervision techniques. By participating the tutorial, the audience will gain a broad knowledge of noisy-supervised learning from the viewpoint of statistical learning theory, and detailed analysis of typical algorithms and frameworks.

Speakers

Ivor W Tsang is an ARC Future Fellow and Professor of Artificial Intelligence, at University of Technology Sydney (UTS). He is also the Research Director of the UTS Flagship Research Centre for Artificial Intelligence (CAI) with more than 30 faculty members and 100 PhD students. His research focuses on transfer learning, feature selection, crowd intelligence, big data analytics for data with extremely high dimensions in features, samples and labels, and their applications to computer vision and pattern recognition. He has more than 180 research papers published in top-tier journal and conference papers. According to Google Scholar, he has more than 12,000 citations and his H-index is 53. In 2009, Prof Tsang was conferred the 2008 Natural Science Award (Class II) by Ministry of Education, China, which recognized his contributions to kernel methods. In 2013, Prof Tsang received his prestigious Australian Research Council Future Fellowship for his research regarding Machine Learning on Big Data. In addition, he had received the prestigious IEEE Transactions on Neural Networks Outstanding 2004 Paper Award in 2007, the 2014 IEEE Transactions on Multimedia Prize Paper Award, and a number of best paper awards and honors from reputable international conferences, including the Best Student Paper Award at CVPR 2010. He serves as an Associate Editor for the IEEE Transactions on Big Data, the IEEE Transactions on Emerging Topics in Computational Intelligence and Neurocomputing. He is serving as a Guest Editor for the special issue of "Structured Multi-output Learning: Modelling, Algorithm, Theory and Applications" in the IEEE Transactions on Neural Networks and Learning Systems.

Bo Han is a Postdoc Fellow at RIKEN Center for Advanced Intelligence Project (RIKEN-AIP), advised by Masashi Sugiyama. He will be a tenured-track Assistant Professor at Hong Kong Baptist University (HKBU). He received his PhD degree in Computer Science from University of Technology Sydney (2015-2019), advised by Ivor W. Tsang and Ling Chen. During 2018-2019, he was a research intern with the AI Residency Program at RIKEN-AIP, advised by Masashi Sugiyama and Gang Niu. His current research interests lie in machine learning, deep learning and their real-world applications. His long-term goal is to develop intelligent systems, which can learn from a massive volume of complex (e.g., weakly-supervised, adversarial, and private) data (e.g, single-/multi-label, ranking, domain, graph and demonstration) automatically. He has published 15 journal articles and conference papers, including MLJ, TNNLS, TKDE articles and NeurIPS, ICML, IJCAI, ECML papers. He has served as program committes for NeurIPS, ICML, ICLR, AISTATS, UAI, AAAI, ACML and ICDM. He received the UTS Research Publication Award (2017 and 2018).