TAROT: Towards Essentially Domain-Invariant Robustness with Theoretical Justification

TL;DR

This paper introduces TAROT, a novel algorithm for robust domain adaptation that leverages a new theoretical generalization bound and divergence measure, achieving superior accuracy and robustness across diverse domains.

Contribution

The paper presents a new theoretical generalization bound and a novel divergence measure, along with the TAROT algorithm, to improve robustness and domain invariance in domain adaptation.

Findings

TAROT outperforms state-of-the-art methods on DomainNet.

TAROT enhances domain invariance and robustness.

Theoretical bounds support TAROT's effectiveness.

Abstract

Robust domain adaptation against adversarial attacks is a critical research area that aims to develop models capable of maintaining consistent performance across diverse and challenging domains. In this paper, we derive a new generalization bound for robust risk on the target domain using a novel divergence measure specifically designed for robust domain adaptation. Building upon this, we propose a new algorithm named TAROT, which is designed to enhance both domain adaptability and robustness. Through extensive experiments, TAROT not only surpasses state-of-the-art methods in accuracy and robustness but also significantly enhances domain generalization and scalability by effectively learning domain-invariant features. In particular, TAROT achieves superior performance on the challenging DomainNet dataset, demonstrating its ability to learn domain-invariant representations that generalize well across different domains, including unseen ones. These results highlight the broader applicability of our approach in real-world domain adaptation scenarios.