Explaining black boxes with a SMILE: Statistical Model-agnostic Interpretability with Local Explanations

Koorosh Aslansefat, Mojgan Hashemian, Martin Walker, Mohammed Naveed Akram, Ioannis Sorokos +1 more
11/13/2023
cs.LGcs.AImath.ST

Official code: Dependable-Intelligent-Systems-Lab/xwhy (12 stars, MIT, last commit 2026-02-01).

Abstract

Machine learning is currently undergoing an explosion in capability, popularity, and sophistication. However, one of the major barriers to widespread acceptance of machine learning (ML) is trustworthiness: most ML models operate as black boxes, their inner workings opaque and mysterious, and it can be difficult to trust their conclusions without understanding how those conclusions are reached. Explainability is therefore a key aspect of improving trustworthiness: the ability to better understand, interpret, and anticipate the behaviour of ML models. To this end, we propose SMILE, a new method that builds on previous approaches by making use of statistical distance measures to improve explainability while remaining applicable to a wide range of input data domains.

View on arXivView PDF

Code Implementations(1)

Dependable-Intelligent-Systems-Lab/xwhyOfficial65%
MIT

Explaining black boxes with a SMILE: Statistical Mode-agnostic Interpretability with Local Explanations

123CSS, HTMLAug 23, 20218 months agoMIT
deep-learningexplainabilityinterpretabilityinterpretability-methodslime+3 more

Similar Papers

Sound Explanation for Trustworthy Machine Learning

86% match2023

Explainability for Machine Learning Models: From Data Adaptability to User Perception

84% match2024

Trust Regions for Explanations via Black-Box Probabilistic Certification

84% match1 repo1.8k2024

Investigating the Duality of Interpretability and Explainability in Machine Learning

84% match2025

Distance-Restricted Explanations: Theoretical Underpinnings & Efficient Implementation

83% match2024

Discriminative Feature Attributions: Bridging Post Hoc Explainability and Inherent Interpretability

83% match2026

Cite this paper

@article{aslansefat2023explaining,
  title  = {Explaining black boxes with a SMILE: Statistical Model-agnostic Interpretability with Local Explanations},
  author = {Koorosh Aslansefat and Mojgan Hashemian and Martin Walker and Mohammed Naveed Akram and Ioannis Sorokos and Yiannis Papadopoulos},
  year   = {2023},
  eprint = {2311.07286},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2311.07286v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2311.07286.svg)](https://codeofpaper.com/paper/2311.07286)

Discussion