Assessing the Fidelity of Explanations with Global Sensitivity Analysis
Files
Date
2023-01-03
Contributor
Advisor
Department
Instructor
Depositor
Speaker
Researcher
Consultant
Interviewer
Narrator
Transcriber
Annotator
Journal Title
Journal ISSN
Volume Title
Publisher
Volume
Number/Issue
Starting Page
1085
Ending Page
Alternative Title
Abstract
Many explainability methods have been proposed as a means of understanding how a learned machine learning model makes decisions and as an important factor in responsible and ethical artificial intelligence. However, explainability methods often do not fully and accurately describe a model's decision process. We leverage the mathematical framework of global sensitivity analysis techniques to reveal deficiencies of explanation methods. We find that current explainaiblity methods fail to capture prediction uncertainty and make several simplifying assumptions that have significant ramifications on the accuracy of the resulting explanations. We show that the simplifying assumptions result in explanations that: (1) fail to model nonlinear interactions in the model and (2) misrepresent the importance of correlated features. Experiments suggest that failing to capture nonlinear feature interaction has a larger impact on the accuracy of the explanations. Thus, as most state-of-the-art ML models have non-linear interactions and operate on correlated data, explanations should only be used with caution.
Description
Keywords
Explainable Artificial Intelligence (XAI), artificial intelligence, explainability, fidelity, machine learning, sensitivity analysis
Citation
Extent
10
Format
Geographic Location
Time Period
Related To
Proceedings of the 56th Hawaii International Conference on System Sciences
Related To (URI)
Table of Contents
Rights
Attribution-NonCommercial-NoDerivatives 4.0 International
Rights Holder
Local Contexts
Collections
Email libraryada-l@lists.hawaii.edu if you need this content in ADA-compliant format.