Maximum Batch Frobenius Norm for Multi-Domain Text Classification

TL;DR

This paper introduces a novel method called maximum batch Frobenius norm (MBF) to enhance feature discriminability in multi-domain text classification by leveraging the Frobenius norm of batch output matrices, improving state-of-the-art results.

Contribution

It provides a theoretical analysis linking Frobenius norm to feature discriminability and proposes MBF to boost MDTC performance.

Findings

MBF significantly improves classification accuracy on benchmarks.

Theoretical analysis confirms Frobenius norm's role in discriminability.

MBF outperforms existing adversarial learning methods.

Abstract

Multi-domain text classification (MDTC) has obtained remarkable achievements due to the advent of deep learning. Recently, many endeavors are devoted to applying adversarial learning to extract domain-invariant features to yield state-of-the-art results. However, these methods still face one challenge: transforming original features to be domain-invariant distorts the distributions of the original features, degrading the discriminability of the learned features. To address this issue, we first investigate the structure of the batch classification output matrix and theoretically justify that the discriminability of the learned features has a positive correlation with the Frobenius norm of the batch output matrix. Based on this finding, we propose a maximum batch Frobenius norm (MBF) method to boost the feature discriminability for MDTC. Experiments on two MDTC benchmarks show that our MBF approach can effectively advance the performance of the state-of-the-art.