Unsupervised Reinforcement Adaptation for Class-Imbalanced Text Classification

TL;DR

This paper introduces a reinforcement learning-based unsupervised domain adaptation method for text classification that effectively handles class imbalance across domains, improving robustness and adaptability.

Contribution

It presents a novel reinforcement learning approach that jointly leverages feature variants and imbalanced labels for unsupervised domain adaptation in text classification.

Findings

Effective learning of domain-invariant representations

Successful adaptation on imbalanced classes across domains

Outperforms five baseline methods

Abstract

Class imbalance naturally exists when train and test models in different domains. Unsupervised domain adaptation (UDA) augments model performance with only accessible annotations from the source domain and unlabeled data from the target domain. However, existing state-of-the-art UDA models learn domain-invariant representations and evaluate primarily on class-balanced data across domains. In this work, we propose an unsupervised domain adaptation approach via reinforcement learning that jointly leverages feature variants and imbalanced labels across domains. We experiment with the text classification task for its easily accessible datasets and compare the proposed method with five baselines. Experiments on three datasets prove that our proposed method can effectively learn robust domain-invariant representations and successfully adapt text classifiers on imbalanced classes over domains. The code is available at https://github.com/woqingdoua/ImbalanceClass.