Conditional Support Alignment for Domain Adaptation with Label Shift

2023-05-29

arXiv.org

AI Summary

Unsupervised domain adaptation (UDA) under label distribution shift suffers from performance degradation, as conventional methods rely on the covariate shift assumption and fail to guarantee discriminative domain-invariant features. Method: This paper proposes Conditional Adversarial Support Alignment (CASUAL), a theoretically grounded framework that jointly optimizes support alignment of conditional feature distributions and classification discriminability via conditional adversarial training. Contribution/Results: CASUAL introduces the first theoretical analysis of conditional support alignment and derives a tighter upper bound on the target risk—rigorously proving its superiority over classical marginal alignment. Extensive experiments across multiple UDA benchmarks with label shift demonstrate that CASUAL consistently outperforms state-of-the-art methods, validating both the effectiveness and generalizability of theory-driven alignment strategies.

Abstract

Unsupervised domain adaptation (UDA) refers to a domain adaptation framework in which a learning model is trained based on the labeled samples on the source domain and unlabeled ones in the target domain. The dominant existing methods in the field that rely on the classical covariate shift assumption to learn domain-invariant feature representation have yielded suboptimal performance under label distribution shift. In this paper, we propose a novel Conditional Adversarial SUpport ALignment (CASUAL) whose aim is to minimize the conditional symmetric support divergence between the source's and target domain's feature representation distributions, aiming at a more discriminative representation for the classification task. We also introduce a novel theoretical target risk bound, which justifies the merits of aligning the supports of conditional feature distributions compared to the existing marginal support alignment approach in the UDA settings. We then provide a complete training process for learning in which the objective optimization functions are precisely based on the proposed target risk bound. Our empirical results demonstrate that CASUAL outperforms other state-of-the-art methods on different UDA benchmark tasks under different label shift conditions.

Problem

• Addresses label distribution shift in unsupervised domain adaptation
• Minimizes conditional support divergence between source and target domains
• Improves discriminative representation for classification under label shift

Innovation

• Conditional adversarial support alignment method
• Minimizes conditional symmetric support divergence
• Novel theoretical target risk bound optimization