Class-Aware Contrastive Optimization for Imbalanced Text Classification
It addresses a common real-world problem of imbalanced text classification, which is incremental as it builds on existing autoencoder and contrastive learning approaches.
The paper tackled imbalanced text classification by combining class-aware contrastive optimization with denoising autoencoders, achieving better performance than state-of-the-art methods across various datasets.
The unique characteristics of text data make classification tasks a complex problem. Advances in unsupervised and semi-supervised learning and autoencoder architectures addressed several challenges. However, they still struggle with imbalanced text classification tasks, a common scenario in real-world applications, demonstrating a tendency to produce embeddings with unfavorable properties, such as class overlap. In this paper, we show that leveraging class-aware contrastive optimization combined with denoising autoencoders can successfully tackle imbalanced text classification tasks, achieving better performance than the current state-of-the-art. Concretely, our proposal combines reconstruction loss with contrastive class separation in the embedding space, allowing a better balance between the truthfulness of the generated embeddings and the model's ability to separate different classes. Compared with an extensive set of traditional and state-of-the-art competing methods, our proposal demonstrates a notable increase in performance across a wide variety of text datasets.