Unlocking Layer-wise Relevance Propagation for Autoencoders
This provides an explainability solution for autoencoders used in tasks like anomaly detection, but it is incremental as it builds on existing methods.
The authors tackled the problem of explaining autoencoder reconstructions by extending Layer-wise Relevance Propagation with Deep Taylor Decomposition and introducing a validation technique for cases with missing ground-truth data, resulting in computational and qualitative advantages over existing methods.
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.