TY - GEN
T1 - Baylime: Bayesian local interpretable model-agnostic explanations
AU - Zhao, Xingyu
AU - Huang, Wei
AU - Huang, Xiaowei
AU - Robu, Valentin
AU - Flynn, David
PY - 2021
Y1 - 2021
N2 - 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 Grad- CAM) 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.
AB - 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 Grad- CAM) 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.
UR - https://www.auai.org/uai2021/pdf/uai2021.342.pdf
M3 - Conference contribution
VL - 161
T3 - Proceedings of Machine Learning Research
SP - 887
EP - 896
BT - Uncertainty in Artificial Intelligence, 27-30 July 2021, Online
A2 - de Campos, Cassio
A2 - Maathuis, Marloes H.
T2 - 37th International Conference on Uncertainty in Artificial Intelligence
Y2 - 26 July 2021 through 30 July 2021
ER -