AIDec 5, 2020

BayLIME: Bayesian Local Interpretable Model-Agnostic Explanations

arXiv:2012.03058v5131 citations
Originality Incremental advance
AI Analysis

This work addresses the problem of improving the reliability and fidelity of local interpretable explanations for users of AI systems, particularly in critical applications where transparency is crucial.

This paper introduces BayLIME, a Bayesian extension to the LIME framework for Explainable AI. BayLIME improves explanation consistency and robustness to kernel settings by incorporating prior knowledge and Bayesian reasoning, and achieves better explanation fidelity compared to LIME, SHAP, and GradCAM.

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.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes