ComCo: Complementary supervised contrastive learning for complementary label learning

doi:10.1016/j.neunet.2023.10.013

ComCo: Complementary supervised contrastive learning for complementary label learning

2024-01-01

3

OA

AI

DOI：10.1016/j.neunet.2023.10.013

Original

Save

View PDF

Abstract

En 中文

Complementary label learning (CLL) is an important problem that aims to reduce the cost of obtaining largescale accurate datasets by only allowing each training sample to be equipped with labels the sample does not belong. Despite its promise, CLL remains a challenging task. Previous methods have proposed new loss functions or introduced deep learning-based models to CLL, but they mostly overlook the semantic information that may be implicit in the complementary labels. In this work, we propose a novel method, ComCo, which leverages a contrastive learning framework to assist CLL. Our method includes two key strategies: a positive selection strategy that identifies reliable positive samples and a negative selection strategy that skillfully integrates and leverages the information in the complementary labels to construct a negative set. These strategies bring ComCo closer to supervised contrastive learning. Empirically, ComCo significantly achieves better representation learning and outperforms the baseline models and the current state-of-the-art by up to 14.61% in CLL.

Keywords:

Complementary label learning

Weakly supervised learning

Contrastive learning

Machine learning

Representation learning

ComCo: Complementary supervised contrastive learning for complementary label learning

Abstract

AI Summary

Journal

Organization