Robust Unsupervised Domain Adaptation for Neural Networks via Moment Alignment

TL;DR

This paper introduces a new metric-based regularization method for neural networks that enhances unsupervised domain adaptation by aligning higher-order moments of feature distributions, leading to improved accuracy across various tasks.

Contribution

It proposes a moment alignment regularization technique that is less translation-sensitive and theoretically guarantees error minimization under certain conditions.

Findings

Achieves higher classification accuracy than comparable methods.

Demonstrates robustness to parameter changes.

Effective across sentiment, object, and digit recognition tasks.

Abstract

A novel approach for unsupervised domain adaptation for neural networks is proposed. It relies on metric-based regularization of the learning process. The metric-based regularization aims at domain-invariant latent feature representations by means of maximizing the similarity between domain-specific activation distributions. The proposed metric results from modifying an integral probability metric such that it becomes less translation-sensitive on a polynomial function space. The metric has an intuitive interpretation in the dual space as the sum of differences of higher order central moments of the corresponding activation distributions. Under appropriate assumptions on the input distributions, error minimization is proven for the continuous case. As demonstrated by an analysis of standard benchmark experiments for sentiment analysis, object recognition and digit recognition, the outlined approach is robust regarding parameter changes and achieves higher classification accuracies than comparable approaches. The source code is available at https://github.com/wzell/mann.