Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings
| Main Authors: | MacDonald, Jan, Besançon, Pokutta, Sebastian |
|---|---|
| Format: | info software Journal |
| Terbitan: |
, 2021
|
| Subjects: | |
| Online Access: |
https://zenodo.org/record/5718781 |
Daftar Isi:
- This repository provides the official implementation of the paper Interpretable Neural Networks with Frank-Wolfe: Sparse Relevance Maps and Relevance Orderings by J. Macdonald, M. Besançon and S. Pokutta (2021). We use a constrained optimization formulation of the Rate-Distortion Explanations (RDE) (Macdonald et al., 2019) method for relevance attribution and Frank-Wolfe algorithms for obtaining interpretable neural network predictions. The corresponding github repo is at https://github.com/ZIB-IOL/fw-rde