Concept-Based Unsupervised Domain Adaptation
This addresses the robustness and generalization of interpretable models for applications in diverse domains, representing an incremental improvement by integrating concept learning into domain adaptation.
The paper tackles the problem of Concept Bottleneck Models (CBMs) degrading under domain shifts by proposing the CUDA framework, which aligns concept representations across domains and infers concepts without labeled data, resulting in significant outperformance over state-of-the-art methods on real-world datasets.
Concept Bottleneck Models (CBMs) enhance interpretability by explaining predictions through human-understandable concepts but typically assume that training and test data share the same distribution. This assumption often fails under domain shifts, leading to degraded performance and poor generalization. To address these limitations and improve the robustness of CBMs, we propose the Concept-based Unsupervised Domain Adaptation (CUDA) framework. CUDA is designed to: (1) align concept representations across domains using adversarial training, (2) introduce a relaxation threshold to allow minor domain-specific differences in concept distributions, thereby preventing performance drop due to over-constraints of these distributions, (3) infer concepts directly in the target domain without requiring labeled concept data, enabling CBMs to adapt to diverse domains, and (4) integrate concept learning into conventional domain adaptation (DA) with theoretical guarantees, improving interpretability and establishing new benchmarks for DA. Experiments demonstrate that our approach significantly outperforms the state-of-the-art CBM and DA methods on real-world datasets.