报告题目：标签噪声学习（Learning with Label Noise ）
报 告 人：刘同亮 博士
training data boost the performances of supervised learning but also burdens us
with the laborious and expensive labelling task. Some cheap ways are developed
to label the data. The obtained labels are therefore likely to be erroneous. A
natural question is that can we avoid the adverse effects of the label noise
and get the optimal solutions just as learning from the clean data? Or, how to
mitigate the adverse effects?
talk, the recent advances in both theoretical foundations and algorithm designs
for label noise will be surveyed. We will first introduce the different types
of label noise and the challenges behind them. We will explain the
well-designed algorithms or surrogate losses which can provably learn from the
corrupted labels efficiently. We will finally give some insights of open
questions about label noise.
Liu is currently a Lecturer (Assistant Professor) with the School of
Information Technologies and the Faculty of Engineering and Information
Technologies, and a core member in the UBTECH Sydney AI Centre, at The
University of Sydney. He received the BEng degree in electronic engineering and
information science from the University of Science and Technology of China, and
the PhD degree from the University of Technology Sydney. His research interests
include statistical learning theory, computer vision, and optimisation. He has
authored and co-authored 40+ research papers including IEEE T-PAMI, T-NNLS,
T-IP, ICML, CVPR, and KDD.