An Introduction to Machine Learning with Noisy Labels

 

An Introduction to Machine Learning with Noisy Labels

Speaker: Associate Professor Tongliang Liu, The University of Sydney

Abstract:
With the rise of large AI models, data assets have gained increasing importance. Understanding how to identify and correct label errors in our datasets is crucial. This is because label errors are pervasive in the era of big data and rectifying them can significantly enhance our knowledge. Moreover, large AI models are prone to overfitting label errors, which hinders their ability to generalize. In this talk, we will present typical approaches to handle label noise, such as extracting confident examples and modelling the label noise. By illustrating the intuitions behind state-of-the-art techniques, we would equip researchers and practitioners with valuable insights into effectively managing label noise.

Short bio:
Tongliang Liu is an Associate Professor in machine learning at The University of Sydney, Australia. He is broadly interested in the fields of trustworthy machine learning and its interdisciplinary applications, with a particular emphasis on learning with noisy labels, adversarial learning, causal representation learning, 3D computer vision, and AI for science. He is/was a senior meta reviewer for many conferences, such as ICML, ICLR, NeurIPS, AAAI, and IJCAI. He is a co-Editor-in-Chief for Neural Networks, an Associate Editor of IEEE TPAMI, IEEE TIP, JAIR, MLJ, TMLR, and ACM Computing Surveys. He received the Young Distinguished Scientist Award from the International Association of Engineers (IAENG) in 2025; the Outstanding Research Contribution Award from CORE in 2024;  the IEEE AI's 10 to Watch Award from the IEEE Computer Society in 2022.