Evaluations and Methods for Explanation through Robustness AnalysisDownload PDF

Sep 28, 2020 (edited Apr 08, 2021)ICLR 2021 PosterReaders: Everyone
  • Keywords: Interpretability, Explanations, Adversarial Robustness
  • Abstract: Feature based explanations, that provide importance of each feature towards the model prediction, is arguably one of the most intuitive ways to explain a model. In this paper, we establish a novel set of evaluation criteria for such feature based explanations by robustness analysis. In contrast to existing evaluations which require us to specify some way to "remove" features that could inevitably introduces biases and artifacts, we make use of the subtler notion of smaller adversarial perturbations. By optimizing towards our proposed evaluation criteria, we obtain new explanations that are loosely necessary and sufficient for a prediction. We further extend the explanation to extract the set of features that would move the current prediction to a target class by adopting targeted adversarial attack for the robustness analysis. Through experiments across multiple domains and a user study, we validate the usefulness of our evaluation criteria and our derived explanations.
  • One-sentence Summary: We propose a suite of objective measurements for evaluating feature based explanations by the notion of robustness analysis; we further derive new explanation that captures different characteristics of explanation comparing to existing methods.
  • Supplementary Material: zip
  • Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics
18 Replies