Bibliographic Details
| Title: |
Unlocking Layer-wise Relevance Propagation for Autoencoders |
| Authors: |
Kobayashi, Kenyu, Khasanova, Renata, Schneuwly, Arno, Schmidt, Felix, Casserini, Matteo |
| Publication Year: |
2023 |
| Collection: |
Computer Science |
| Subject Terms: |
Computer Science - Machine Learning, Computer Science - Artificial Intelligence |
| More Details: |
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. |
| Document Type: |
Working Paper |
| Access URL: |
http://arxiv.org/abs/2303.11734 |
| Accession Number: |
edsarx.2303.11734 |
| Database: |
arXiv |
