Simple-Sampling and Hard-Mixup with Prototypes to Rebalance Contrastive Learning for Text Classification

TL;DR

This paper introduces SharpReCL, a novel approach that uses class prototypes and balanced sampling to improve supervised contrastive learning for imbalanced text classification, outperforming large language models.

Contribution

The paper proposes a prototype-based balanced sampling method to enhance contrastive learning in imbalanced text classification tasks.

Findings

SharpReCL outperforms existing models on multiple datasets.

The method effectively handles data imbalance in contrastive learning.

Results surpass those of popular large language models.

Abstract

Text classification is a crucial and fundamental task in web content mining. Compared with the previous learning paradigm of pre-training and fine-tuning by cross entropy loss, the recently proposed supervised contrastive learning approach has received tremendous attention due to its powerful feature learning capability and robustness. Although several studies have incorporated this technique for text classification, some limitations remain. First, many text datasets are imbalanced, and the learning mechanism of supervised contrastive learning is sensitive to data imbalance, which may harm the model's performance. Moreover, these models leverage separate classification branches with cross entropy and supervised contrastive learning branches without explicit mutual guidance. To this end, we propose a novel model named SharpReCL for imbalanced text classification tasks. First, we obtain the prototype vector of each class in the balanced classification branch to act as a representation of each class. Then, by further explicitly leveraging the prototype vectors, we construct a proper and sufficient target sample set with the same size for each class to perform the supervised contrastive learning procedure. The empirical results show the effectiveness of our model, which even outperforms popular large language models across several datasets. Our code is available here.