A Framework for Learning Ante-hoc Explainable Models via Concepts

TL;DR

This paper introduces a novel self-explaining deep learning framework that jointly learns concepts and generates explanations, achieving high predictive accuracy and interpretability, especially on large-scale datasets like ImageNet.

Contribution

It proposes a flexible, joint training model for ante-hoc explainability that works with both supervised and unsupervised concepts, outperforming existing methods.

Findings

Achieves high predictive performance with concept supervision.

Effectively generates meaningful concept-based explanations.

Demonstrates scalability to large datasets like ImageNet.

Abstract

Self-explaining deep models are designed to learn the latent concept-based explanations implicitly during training, which eliminates the requirement of any post-hoc explanation generation technique. In this work, we propose one such model that appends an explanation generation module on top of any basic network and jointly trains the whole module that shows high predictive performance and generates meaningful explanations in terms of concepts. Our training strategy is suitable for unsupervised concept learning with much lesser parameter space requirements compared to baseline methods. Our proposed model also has provision for leveraging self-supervision on concepts to extract better explanations. However, with full concept supervision, we achieve the best predictive performance compared to recently proposed concept-based explainable models. We report both qualitative and quantitative results with our method, which shows better performance than recently proposed concept-based explainability methods. We reported exhaustive results with two datasets without ground truth concepts, i.e., CIFAR10, ImageNet, and two datasets with ground truth concepts, i.e., AwA2, CUB-200, to show the effectiveness of our method for both cases. To the best of our knowledge, we are the first ante-hoc explanation generation method to show results with a large-scale dataset such as ImageNet.