Leveraged Weighted Loss for Partial Label Learning

Hongwei Wen, Jingyi Cui, Hanyuan Hang, Jiabin Liu*, Yisen Wang*, Zhouchen Lin*

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

45 Citations (Scopus)
25 Downloads (Pure)


As an important branch of weakly supervised learning, partial label learning deals with data where each instance is assigned with a set of candidate labels, whereas only one of them is true. Despite many methodology studies on learning from partial labels, there still lacks theoretical understandings of their risk consistent properties under relatively weak assumptions, especially on the link between theoretical results and the empirical choice of parameters. In this paper, we propose a family of loss functions named \textit{Leveraged Weighted} (LW) loss, which for the first time introduces the leverage parameter 𝛽 to consider the trade-off between losses on partial labels and non-partial ones. From the theoretical side, we derive a generalized result of risk consistency for the LW loss in learning from partial labels, based on which we provide guidance to the choice of the leverage parameter 𝛽. In experiments, we verify the theoretical guidance, and show the high effectiveness of our proposed LW loss on both benchmark and real datasets compared with other state-of-the-art partial label learning algorithms.
Original languageEnglish
Title of host publicationProceedings of the 38th International Conference on Machine Learning, ICML 2021
EditorsMarina Meila, Tong Zhang
Publication statusPublished - Jul 2021
Event38th International Conference on Machine Learning, ICML 2021 - Virtual
Duration: 18 Jul 202124 Jul 2021
Conference number: 38

Publication series

NameProceedings of Machine Learning Research (PMLR)


Conference38th International Conference on Machine Learning, ICML 2021
Abbreviated titleICML


Dive into the research topics of 'Leveraged Weighted Loss for Partial Label Learning'. Together they form a unique fingerprint.

Cite this