A Rate-Distortion Framework for Explaining Black-box Model Decisions
Machine Learning
2021-10-19 v1 Artificial Intelligence
Information Theory
math.IT
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.
Keywords
Cite
@article{arxiv.2110.08252,
title = {A Rate-Distortion Framework for Explaining Black-box Model Decisions},
author = {Stefan Kolek and Duc Anh Nguyen and Ron Levie and Joan Bruna and Gitta Kutyniok},
journal= {arXiv preprint arXiv:2110.08252},
year = {2021}
}