Learning by Self-Explaining

TL;DR

This paper introduces Learning by Self-Explaining (LSX), a novel approach where models improve by generating explanations that are internally validated, leading to better generalization and more faithful explanations in image classification.

Contribution

The paper proposes LSX, integrating self-explanation and internal critique to enhance model learning and explanation quality, a novel approach in explainable AI.

Findings

Improved model generalization and robustness.

Reduced influence of confounding factors.

Generated explanations are more task-relevant and faithful.

Abstract

Much of explainable AI research treats explanations as a means for model inspection. Yet, this neglects findings from human psychology that describe the benefit of self-explanations in an agent's learning process. Motivated by this, we introduce a novel workflow in the context of image classification, termed Learning by Self-Explaining (LSX). LSX utilizes aspects of self-refining AI and human-guided explanatory machine learning. The underlying idea is that a learner model, in addition to optimizing for the original predictive task, is further optimized based on explanatory feedback from an internal critic model. Intuitively, a learner's explanations are considered "useful" if the internal critic can perform the same task given these explanations. We provide an overview of important components of LSX and, based on this, perform extensive experimental evaluations via three different example instantiations. Our results indicate improvements via Learning by Self-Explaining on several levels: in terms of model generalization, reducing the influence of confounding factors, and providing more task-relevant and faithful model explanations. Overall, our work provides evidence for the potential of self-explaining within the learning phase of an AI model.