Mind the Class Weight Bias: Weighted Maximum Mean Discrepancy for Unsupervised Domain Adaptation

TL;DR

This paper introduces a weighted maximum mean discrepancy (MMD) method that accounts for class prior distribution differences in unsupervised domain adaptation, improving performance over traditional MMD.

Contribution

The paper proposes a novel weighted MMD model that incorporates class-specific auxiliary weights to handle class weight bias in domain adaptation.

Findings

Weighted MMD outperforms conventional MMD in experiments.

The method effectively addresses class prior distribution shifts.

The approach improves domain adaptation performance across multiple datasets.

Abstract

In domain adaptation, maximum mean discrepancy (MMD) has been widely adopted as a discrepancy metric between the distributions of source and target domains. However, existing MMD-based domain adaptation methods generally ignore the changes of class prior distributions, i.e., class weight bias across domains. This remains an open problem but ubiquitous for domain adaptation, which can be caused by changes in sample selection criteria and application scenarios. We show that MMD cannot account for class weight bias and results in degraded domain adaptation performance. To address this issue, a weighted MMD model is proposed in this paper. Specifically, we introduce class-specific auxiliary weights into the original MMD for exploiting the class prior probability on source and target domains, whose challenge lies in the fact that the class label in target domain is unavailable. To account for it, our proposed weighted MMD model is defined by introducing an auxiliary weight for each class in the source domain, and a classification EM algorithm is suggested by alternating between assigning the pseudo-labels, estimating auxiliary weights and updating model parameters. Extensive experiments demonstrate the superiority of our weighted MMD over conventional MMD for domain adaptation.