A Self-explaining Neural Architecture for Generalizable Concept Learning

TL;DR

This paper introduces a self-explaining neural architecture that enhances concept learning by improving interpretability, domain generalization, and concept fidelity through novel modules and regularization techniques, validated on multiple datasets.

Contribution

The paper proposes a new architecture with a concept saliency network, contrastive learning, and prototype-based regularization to address fidelity and interoperability issues in concept learning.

Findings

Improves concept overlap and fidelity.

Enhances domain adaptation performance.

Outperforms state-of-the-art methods on real-world datasets.

Abstract

With the wide proliferation of Deep Neural Networks in high-stake applications, there is a growing demand for explainability behind their decision-making process. Concept learning models attempt to learn high-level 'concepts' - abstract entities that align with human understanding, and thus provide interpretability to DNN architectures. However, in this paper, we demonstrate that present SOTA concept learning approaches suffer from two major problems - lack of concept fidelity wherein the models fail to learn consistent concepts among similar classes and limited concept interoperability wherein the models fail to generalize learned concepts to new domains for the same task. Keeping these in mind, we propose a novel self-explaining architecture for concept learning across domains which - i) incorporates a new concept saliency network for representative concept selection, ii) utilizes contrastive learning to capture representative domain invariant concepts, and iii) uses a novel prototype-based concept grounding regularization to improve concept alignment across domains. We demonstrate the efficacy of our proposed approach over current SOTA concept learning approaches on four widely used real-world datasets. Empirical results show that our method improves both concept fidelity measured through concept overlap and concept interoperability measured through domain adaptation performance.