One Explanation Does Not Fit XIL

Code

• github.com/ml-research/a-typology-for-exploring-the-mitigation-of-shortcut-behavior
  OfficialIn paperpytorch★ 8

Abstract

Current machine learning models produce outstanding results in many areas but, at the same time, suffer from shortcut learning and spurious correlations. To address such flaws, the explanatory interactive machine learning (XIL) framework has been proposed to revise a model by employing user feedback on a model's explanation. This work sheds light on the explanations used within this framework. In particular, we investigate simultaneous model revision through multiple explanation methods. To this end, we identified that one explanation does not fit XIL and propose considering multiple ones when revising models via XIL.

Reproductions