Unlocking Layer-wise Relevance Propagation for Autoencoders
Machine Learning
2023-03-22 v1 Artificial Intelligence
Abstract
Autoencoders are a powerful and versatile tool often used for various problems such as anomaly detection, image processing and machine translation. However, their reconstructions are not always trivial to explain. Therefore, we propose a fast explainability solution by extending the Layer-wise Relevance Propagation method with the help of Deep Taylor Decomposition framework. Furthermore, we introduce a novel validation technique for comparing our explainability approach with baseline methods in the case of missing ground-truth data. Our results highlight computational as well as qualitative advantages of the proposed explainability solution with respect to existing methods.
Cite
@article{arxiv.2303.11734,
title = {Unlocking Layer-wise Relevance Propagation for Autoencoders},
author = {Kenyu Kobayashi and Renata Khasanova and Arno Schneuwly and Felix Schmidt and Matteo Casserini},
journal= {arXiv preprint arXiv:2303.11734},
year = {2023}
}