A Self-Paced Regularization Framework for Multi-Label Learning

TL;DR

This paper introduces MLSPL, a multi-label learning framework that employs a self-paced strategy to gradually incorporate easier labels and instances, improving learning efficiency and effectiveness.

Contribution

It proposes a novel self-paced regularization method for multi-label learning, adaptable to different scenarios, and demonstrates state-of-the-art results on benchmark datasets.

Findings

Achieves state-of-the-art performance on three benchmark datasets.

Effectively ranks label and instance importance during training.

Flexible framework adaptable to various multi-label scenarios.

Abstract

In this paper, we propose a novel multi-label learning framework, called Multi-Label Self-Paced Learning (MLSPL), in an attempt to incorporate the self-paced learning strategy into multi-label learning regime. In light of the benefits of adopting the easy-to-hard strategy proposed by self-paced learning, the devised MLSPL aims to learn multiple labels jointly by gradually including label learning tasks and instances into model training from the easy to the hard. We first introduce a self-paced function as a regularizer in the multi-label learning formulation, so as to simultaneously rank priorities of the label learning tasks and the instances in each learning iteration. Considering that different multi-label learning scenarios often need different self-paced schemes during optimization, we thus propose a general way to find the desired self-paced functions. Experimental results on three benchmark datasets suggest the state-of-the-art performance of our approach.