Leveraged Weighted Loss for Partial Label Learning

TL;DR

This paper introduces the Leveraged Weighted loss for partial label learning, providing theoretical risk consistency analysis and empirical validation, which improves learning performance from weakly supervised data with ambiguous labels.

Contribution

It proposes a novel LW loss with a leverage parameter, offering theoretical risk consistency results and practical guidance for parameter selection in partial label learning.

Findings

Theoretical risk consistency of LW loss is established.

Empirical results show LW loss outperforms state-of-the-art methods.

Guidance on choosing the leverage parameter $eta$ is provided.

Abstract

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 $\beta$ 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 $\beta$. 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.