Label Information Bottleneck for Label Enhancement

TL;DR

This paper introduces a novel Label Information Bottleneck method for Label Enhancement, which effectively extracts essential label relevant information to improve the accuracy of recovering label distributions from logical labels.

Contribution

The proposed LIB method uniquely excavates both label assignment and gap information using a bottleneck approach, enhancing label distribution recovery performance.

Findings

LIB outperforms existing methods on benchmark datasets.

The method effectively isolates label relevant information.

Experimental results verify the method's competitiveness.

Abstract

In this work, we focus on the challenging problem of Label Enhancement (LE), which aims to exactly recover label distributions from logical labels, and present a novel Label Information Bottleneck (LIB) method for LE. For the recovery process of label distributions, the label irrelevant information contained in the dataset may lead to unsatisfactory recovery performance. To address this limitation, we make efforts to excavate the essential label relevant information to improve the recovery performance. Our method formulates the LE problem as the following two joint processes: 1) learning the representation with the essential label relevant information, 2) recovering label distributions based on the learned representation. The label relevant information can be excavated based on the "bottleneck" formed by the learned representation. Significantly, both the label relevant information about the label assignments and the label relevant information about the label gaps can be explored in our method. Evaluation experiments conducted on several benchmark label distribution learning datasets verify the effectiveness and competitiveness of LIB. Our source codes are available https://github.com/qinghai-zheng/LIBLE