Class-Aware Contrastive Optimization for Imbalanced Text Classification

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Khvatskii, Grigorii, Moniz, Nuno, Doan, Khoa, Chawla, Nitesh V
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912093512400896
author Khvatskii, Grigorii
Moniz, Nuno
Doan, Khoa
Chawla, Nitesh V
author_facet Khvatskii, Grigorii
Moniz, Nuno
Doan, Khoa
Chawla, Nitesh V
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2410_22197
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Class-Aware Contrastive Optimization for Imbalanced Text Classification
Khvatskii, Grigorii
Moniz, Nuno
Doan, Khoa
Chawla, Nitesh V
Computation and Language
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.
title Class-Aware Contrastive Optimization for Imbalanced Text Classification
topic Computation and Language
url https://arxiv.org/abs/2410.22197