Generative Example-Based Explanations: Bridging the Gap between Generative Modeling and Explainability
This work addresses a conceptual gap for researchers in generative modeling and explainability, though it is incremental as it builds on existing methods without introducing a new paradigm.
The paper tackles the disconnect between generative modeling methods for example-based explanations and classical explainability literature by proposing a probabilistic framework that formally defines such explanations, aiming to improve rigor and communication in this research area.
Recently, several methods have leveraged deep generative modeling to produce example-based explanations of image classifiers. Despite producing visually stunning results, these methods are largely disconnected from classical explainability literature. This conceptual and communication gap leads to misunderstandings and misalignments in goals and expectations. In this paper, we bridge this gap by proposing a probabilistic framework for example-based explanations, formally defining the example-based explanations in a probabilistic manner amenable for modeling via deep generative models while coherent with the critical characteristics and desiderata widely accepted in the explainability community. Our aim is on one hand to provide a constructive framework for the development of well-grounded generative algorithms for example-based explanations and, on the other, to facilitate communication between the generative and explainability research communities, foster rigor and transparency, and improve the quality of peer discussion and research progress in this promising direction.