Instances and Labels: Hierarchy-aware Joint Supervised Contrastive Learning for Hierarchical Multi-Label Text Classification

TL;DR

This paper introduces HJCL, a hierarchy-aware joint supervised contrastive learning method that improves hierarchical multi-label text classification by effectively utilizing label hierarchies and contrastive learning techniques.

Contribution

The paper proposes a novel HJCL method that combines instance-wise and label-wise contrastive learning tailored for hierarchical multi-label text classification.

Findings

HJCL outperforms existing methods on four HMTC datasets.

Contrastive learning significantly improves classification accuracy.

Batch construction is crucial for effective contrastive learning in HMTC.

Abstract

Hierarchical multi-label text classification (HMTC) aims at utilizing a label hierarchy in multi-label classification. Recent approaches to HMTC deal with the problem of imposing an over-constrained premise on the output space by using contrastive learning on generated samples in a semi-supervised manner to bring text and label embeddings closer. However, the generation of samples tends to introduce noise as it ignores the correlation between similar samples in the same batch. One solution to this issue is supervised contrastive learning, but it remains an underexplored topic in HMTC due to its complex structured labels. To overcome this challenge, we propose $\textbf{HJCL}$, a $\textbf{H}$ierarchy-aware $\textbf{J}$oint Supervised $\textbf{C}$ontrastive $\textbf{L}$earning method that bridges the gap between supervised contrastive learning and HMTC. Specifically, we employ both instance-wise and label-wise contrastive learning techniques and carefully construct batches to fulfill the contrastive learning objective. Extensive experiments on four multi-path HMTC datasets demonstrate that HJCL achieves promising results and the effectiveness of Contrastive Learning on HMTC.