Taxonomy-Structured Domain Adaptation

TL;DR

This paper introduces a novel domain adaptation method that leverages hierarchical taxonomy structures to improve adaptation across nuanced, real-world domain relationships, outperforming existing approaches.

Contribution

It proposes a taxonomy-aware adversarial framework with a new 'taxonomist' component, enabling effective domain adaptation with hierarchical domain structures.

Findings

Achieves state-of-the-art results on synthetic datasets.

Demonstrates successful adaptation on real-world datasets.

Provides a flexible framework for hierarchical domain relationships.

Abstract

Domain adaptation aims to mitigate distribution shifts among different domains. However, traditional formulations are mostly limited to categorical domains, greatly simplifying nuanced domain relationships in the real world. In this work, we tackle a generalization with taxonomy-structured domains, which formalizes domains with nested, hierarchical similarity structures such as animal species and product catalogs. We build on the classic adversarial framework and introduce a novel taxonomist, which competes with the adversarial discriminator to preserve the taxonomy information. The equilibrium recovers the classic adversarial domain adaptation's solution if given a non-informative domain taxonomy (e.g., a flat taxonomy where all leaf nodes connect to the root node) while yielding non-trivial results with other taxonomies. Empirically, our method achieves state-of-the-art performance on both synthetic and real-world datasets with successful adaptation. Code is available at https://github.com/Wang-ML-Lab/TSDA.