On Locality of Local Explanation Models

Sahra Ghalebikesabi, Lucile Ter-Minassian, Karla DiazOrdaz, Christopher C. Holmes

Keywords: Shapley values, model interpretability, reference distribution, neighbourhood sampling

Abstract:

Shapley values provide model agnostic feature attributions for model outcome at a particular instance by simulating feature
absence under a global population distribution. The use of a global population can lead to potentially misleading results when local model behaviour is of interest. Hence we consider the formulation of neighbourhood reference distributions that improve the local interpretability of Shapley values. By doing so, we find that the Nadaraya-Watson estimator, a well-studied kernel regressor, can be expressed as a self-normalised importance sampling estimator. Empirically, we observe that Neighbourhood Shapley values identify meaningful sparse feature relevance attributions that provide insight into local model behaviour, complimenting conventional Shapley analysis. They also increase on-manifold explainability and robustness to the construction of adversarial classifiers.

Code Of Conduct: I certify that all co-authors of this work have read and commit to adhering to the NeurIPS Statement on Ethics, Fairness, Inclusivity, and Code of Conduct.

TL;DR: We consider the formulation of neighbourhood reference distributions that improve the local interpretability of Shapley values.

Code: https://medium.com/@lucile.terminassian?p=4c279fb57974