BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations

Xingyu Zhao, Wei Huang, Xiaowei Huang, Valentin Robu, David Flynn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Given the pressing need for assuring algorithmic transparency, Explainable AI (XAI) has emerged as one of the key areas of AI research. In this paper, we develop a novel Bayesian extension to the LIME framework, one of the most widely used approaches in XAI -- which we call BayLIME. Compared to LIME, BayLIME exploits prior knowledge and Bayesian reasoning to improve both the consistency in repeated explanations of a single prediction and the robustness to kernel settings. BayLIME also exhibits better explanation fidelity than the state-of-the-art (LIME, SHAP and GradCAM) by its ability to integrate prior knowledge from, e.g., a variety of other XAI techniques, as well as verification and validation (V&V) methods. We demonstrate the desirable properties of BayLIME through both theoretical analysis and extensive experiments.
Original languageEnglish
Title of host publication37th Conference on Uncertainty in Artificial Intelligence (UAI)
Subtitle of host publicationProceedings of Machine Learning Research (PMLR)
Publication statusAccepted/In press - 12 May 2021
Event37th Conference on Uncertainty in Artificial Intelligence 2021 - virtual, Australia
Duration: 27 Jul 202130 Jul 2021
https://auai.org/uai2021/

Conference

Conference37th Conference on Uncertainty in Artificial Intelligence 2021
Abbreviated titleUAI 2021
Country/TerritoryAustralia
Period27/07/2130/07/21
Internet address

Keywords

  • Explainable AI
  • Bayesian
  • artificial intelligence
  • prediction

Fingerprint

Dive into the research topics of 'BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations'. Together they form a unique fingerprint.

Cite this