Defining Locality for Surrogates in Post-hoc Interpretablity

Abstract : Local surrogate models, to approximate the local decision boundary of a black-box classifier, constitute one approach to generate explanations for the rationale behind an individual prediction made by the back-box. This paper highlights the importance of defining the right locality, the neighborhood on which a local surrogate is trained, in order to approximate accurately the local black-box decision boundary. Unfortunately, as shown in this paper, this issue is not only a parameter or sampling distribution challenge and has a major impact on the relevance and quality of the approximation of the local black-box decision boundary and thus on the meaning and accuracy of the generated explanation. To overcome the identified problems, quantified with an adapted measure and procedure, we propose to generate surrogate-based explanations for individual predictions based on a sampling centered on particular place of the decision boundary, relevant for the prediction to be explained, rather than on the prediction itself as it is classically done. We evaluate the novel approach compared to state-of-the-art methods and a straightforward improvement thereof on four UCI datasets.
Complete list of metadatas

https://hal.sorbonne-universite.fr/hal-01905924
Contributor : Thibault Laugel <>
Submitted on : Friday, October 26, 2018 - 11:40:59 AM
Last modification on : Thursday, December 12, 2019 - 3:00:31 PM

Links full text

Identifiers

  • HAL Id : hal-01905924, version 1
  • ARXIV : 1806.07498

Citation

Thibault Laugel, Xavier Renard, Marie-Jeanne Lesot, Christophe Marsala, Marcin Detyniecki. Defining Locality for Surrogates in Post-hoc Interpretablity. Workshop on Human Interpretability for Machine Learning (WHI) - International Conference on Machine Learning (ICML), Jul 2018, Stockholm, Sweden. ⟨hal-01905924⟩

Share

Metrics

Record views

74