Learning Transferable Conceptual Prototypes for Interpretable Unsupervised Domain Adaptation
This addresses the need for safe and controllable model decisions in UDA applications, offering a novel approach that is not incremental but introduces a new paradigm for interpretability in this context.
The paper tackles the problem of opaque unsupervised domain adaptation (UDA) models by proposing an inherently interpretable method called Transferable Conceptual Prototype Learning (TCPL), which simultaneously improves performance and provides explanations, achieving state-of-the-art results in experiments.
Despite the great progress of unsupervised domain adaptation (UDA) with the deep neural networks, current UDA models are opaque and cannot provide promising explanations, limiting their applications in the scenarios that require safe and controllable model decisions. At present, a surge of work focuses on designing deep interpretable methods with adequate data annotations and only a few methods consider the distributional shift problem. Most existing interpretable UDA methods are post-hoc ones, which cannot facilitate the model learning process for performance enhancement. In this paper, we propose an inherently interpretable method, named Transferable Conceptual Prototype Learning (TCPL), which could simultaneously interpret and improve the processes of knowledge transfer and decision-making in UDA. To achieve this goal, we design a hierarchically prototypical module that transfers categorical basic concepts from the source domain to the target domain and learns domain-shared prototypes for explaining the underlying reasoning process. With the learned transferable prototypes, a self-predictive consistent pseudo-label strategy that fuses confidence, predictions, and prototype information, is designed for selecting suitable target samples for pseudo annotations and gradually narrowing down the domain gap. Comprehensive experiments show that the proposed method can not only provide effective and intuitive explanations but also outperform previous state-of-the-arts.