A Simple Graph Contrastive Learning Framework for Short Text Classification

TL;DR

This paper introduces SimSTC, a simple graph contrastive learning framework for short text classification that avoids data augmentation, leverages multi-view embeddings, and outperforms large language models on multiple datasets.

Contribution

It proposes a novel, straightforward graph contrastive learning method that eliminates data augmentation and effectively utilizes multi-view embeddings for short text classification.

Findings

Outperforms large language models on various datasets

Eliminates the need for data augmentation in contrastive learning

Achieves superior accuracy with a simple framework

Abstract

Short text classification has gained significant attention in the information age due to its prevalence and real-world applications. Recent advancements in graph learning combined with contrastive learning have shown promising results in addressing the challenges of semantic sparsity and limited labeled data in short text classification. However, existing models have certain limitations. They rely on explicit data augmentation techniques to generate contrastive views, resulting in semantic corruption and noise. Additionally, these models only focus on learning the intrinsic consistency between the generated views, neglecting valuable discriminative information from other potential views. To address these issues, we propose a Simple graph contrastive learning framework for Short Text Classification (SimSTC). Our approach involves performing graph learning on multiple text-related component graphs to obtain multi-view text embeddings. Subsequently, we directly apply contrastive learning on these embeddings. Notably, our method eliminates the need for data augmentation operations to generate contrastive views while still leveraging the benefits of multi-view contrastive learning. Despite its simplicity, our model achieves outstanding performance, surpassing large language models on various datasets.