A Rate-Distortion Framework for Explaining Black-box Model Decisions

TL;DR

The paper introduces the Rate-Distortion Explanation (RDE) framework, a mathematically grounded method for explaining black-box model decisions across various data types, including images, audio, and simulations.

Contribution

It proposes a novel, generalizable explanation framework based on rate-distortion theory applicable to any differentiable pre-trained model.

Findings

Demonstrates adaptability to multiple data modalities.

Provides a mathematically well-founded explanation method.

Applicable to neural networks and other differentiable models.

Abstract

We present the Rate-Distortion Explanation (RDE) framework, a mathematically well-founded method for explaining black-box model decisions. The framework is based on perturbations of the target input signal and applies to any differentiable pre-trained model such as neural networks. Our experiments demonstrate the framework's adaptability to diverse data modalities, particularly images, audio, and physical simulations of urban environments.