Fine-Grained Neural Network Explanation by Identifying Input Features With Predictive Information
MCML Authors
Ashkan Khakzar
Dr.
Azade Farshad
Dr.
Nassir Navab
Prof. Dr.
Core PI
Abstract
Ashkan Khakzar
Dr.
Azade Farshad
Dr.
Nassir Navab
Prof. Dr.
Core PI
Abstract
One principal approach for illuminating a black-box neural network is feature attribution, i.e. identifying the importance of input features for the network’s prediction. The predictive information of features is recently proposed as a proxy for the measure of their importance. So far, the predictive information is only identified for latent features by placing an information bottleneck within the network. We propose a method to identify features with predictive information in the input domain. The method results in fine-grained identification of input features' information and is agnostic to network architecture. The core idea of our method is leveraging a bottleneck on the input that only lets input features associated with predictive latent features pass through. We compare our method with several feature attribution methods using mainstream feature attribution evaluation experiments. The code is publicly available.
inproceedings ZKL+21
NeurIPS 2021
Track on Datasets and Benchmarks at the 35th Conference on Neural Information Processing Systems. Virtual, Dec 06-14, 2021.
Authors
Y. Zhang • A. Khakzar • Y. Li • A. Farshad • S. T. Kim • N. NavabLinks
URLResearch Areas
BibTeXKey: ZKL+21