A Framework for Learning Ante-hoc Explainable Models via Concepts
This work addresses the need for interpretable AI models by providing an ante-hoc explanation framework, which is incremental as it builds on existing concept-based methods but extends to large-scale datasets like ImageNet.
The paper tackles the problem of learning self-explaining deep models that generate concept-based explanations during training, eliminating the need for post-hoc methods, and reports better predictive performance and meaningful explanations compared to recent concept-based explainable models on datasets like CIFAR10, ImageNet, AwA2, and CUB-200.
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.