Leveraged Weighted Loss for Partial Label Learning
Hongwei Wen,u00a0Jingyi Cui,u00a0Hanyuan Hang,u00a0Jiabin Liu,u00a0Yisen Wang,u00a0Zhouchen Lin
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 extit{Leveraged Weighted} (LW) loss, which for the first time introduces the leverage parameter $eta$ 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 $eta$. 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.
