Learning to Generalize Unseen Domains via Multi-Source Meta Learning for Text Classification

TL;DR

This paper introduces a multi-source meta-learning framework with a memory and jury mechanism to improve text classification models' ability to generalize to unseen domains, outperforming existing methods.

Contribution

It proposes a novel multi-source meta-learning domain generalization framework with memory and jury mechanisms for better unseen domain adaptation in text classification.

Findings

Enhanced generalization to unseen domains.

Outperforms state-of-the-art methods on multiple datasets.

Effective use of memory and jury mechanisms.

Abstract

With the rapid development of deep learning methods, there have been many breakthroughs in the field of text classification. Models developed for this task have been shown to achieve high accuracy. However, most of these models are trained using labeled data from seen domains. It is difficult for these models to maintain high accuracy in a new challenging unseen domain, which is directly related to the generalization of the model. In this paper, we study the multi-source Domain Generalization of text classification and propose a framework to use multiple seen domains to train a model that can achieve high accuracy in an unseen domain. Specifically, we propose a multi-source meta-learning Domain Generalization framework to simulate the process of model generalization to an unseen domain, so as to extract sufficient domain-related features. We introduced a memory mechanism to store domain-specific features, which coordinate with the meta-learning framework. Besides, we adopt the novel "jury" mechanism that enables the model to learn sufficient domain-invariant features. Experiments demonstrate that our meta-learning framework can effectively enhance the ability of the model to generalize to an unseen domain and can outperform the state-of-the-art methods on multi-source text classification datasets.