BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations

Zhao, Xingyu ORCID: 0000-0002-3474-349X, Huang, Wei, Huang, Xiaowei ORCID: 0000-0001-6267-0366, Robu, Valentin and Flynn, David (2020) BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations. In: 37th Conference on Uncertainty in Artificial Intelligence (UAI'21), 2021-7-27 - 2021-7-29, Virtual.

This is the latest version of this item.

Text
zhao_342-supp.pdf - Author Accepted Manuscript
Download (3MB) | Preview

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.

Item Type:	Conference or Workshop Item (Unspecified)
Additional Information:	Preprint accepted by UAI2021. The final version to appear in the UAI2021 volume of Proceedings of Machine Learning Research
Uncontrolled Keywords:	cs.AI, cs.AI
Divisions:	Faculty of Science and Engineering > School of Electrical Engineering, Electronics and Computer Science
Depositing User:	Symplectic Admin
Date Deposited:	20 May 2021 09:22
Last Modified:	18 Jan 2023 22:46
Related URLs:	Author
URI:	https://livrepository.liverpool.ac.uk/id/eprint/3123325