We argue that robustness of explanations---i.e., that similar inputs should give rise to similar explanations---is a key desideratum for interpretability. We introduce metrics to quantify robustness and demonstrate that current methods do not perform well according to these metrics. Finally, we propose ways that robustness can be enforced on existing interpretability approaches.
@article{arxiv.1806.08049,
title = {On the Robustness of Interpretability Methods},
author = {David Alvarez-Melis and Tommi S. Jaakkola},
journal= {arXiv preprint arXiv:1806.08049},
year = {2018}
}
Comments
presented at 2018 ICML Workshop on Human Interpretability in Machine Learning (WHI 2018), Stockholm, Sweden