On the Robustness of Interpretability Methods
On the Robustness of Interpretability Methods
David Alvarez-Melis,T. Jaakkola
2018 · ArXiv: 1806.08049
arXiv.org · 573 Citations
TLDR
It is argued that robustness of explanations---i.e., that similar inputs should give rise to similar explanations---is a key desideratum for interpretability, and metrics to quantify robustness are introduced.
Abstract
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.