Evaluating the Robustness of Interpretability Methods through Explanation Invariance and Equivariance.

Jonathan Crabbé Mihaela van der Schaar

Published in: NeurIPS (2023)

Keyphrases

significant improvement
association rules
benchmark datasets
cross validation
neural network
multiscale
preprocessing
evolutionary algorithm
computational cost
empirical studies
computational efficiency
machine learning methods
search methods