Explainer Divergence Scores (EDS): Some Post-Hoc Explanations May be Effective for Detecting Unknown Spurious Correlations. (arXiv:2211.07650v1 [cs.LG])

Recent work has suggested post-hoc explainers might be ineffective for
detecting spurious correlations in Deep Neural Networks (DNNs). However, we
show there are serious weaknesses with the existing evaluation frameworks for
this setting. Previously proposed metrics are extremely difficult to interpret
and are not directly comparable between explainer methods. To alleviate these
constraints, we propose a new evaluation methodology, Explainer Divergence
Scores (EDS), grounded in an information theory approach to evaluate
explainers. EDS is easy to interpret and naturally comparable …

arxiv divergence explainer