Evaluating Feature Importance Estimates

arXiv preprint arXiv:1806.10758 2019 Sara HookerDumitru ErhanPieter-Jan KindermansBeen Kim

Interpretability methods should be both meaningful to a human and correctly explain model behavior. In this work, we propose a benchmark to evaluate the latter... (read more)

PDF Abstract

Evaluation Results from the Paper


  Submit results from this paper to get state-of-the-art GitHub badges and help community compare results to other papers.