Generative Example-Based Explanations: Bridging the Gap between Generative Modeling and Explainability

TL;DR

This paper introduces a probabilistic framework for example-based explanations using deep generative models, aiming to unify generative modeling with explainability principles to improve clarity and research progress.

Contribution

It proposes a formal probabilistic framework for example-based explanations, bridging generative modeling and explainability literature for clearer communication and development.

Findings

Framework formalizes explanation generation process

Enhances communication between research communities

Supports development of more grounded generative algorithms

Abstract

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.