CISPA
Browse

Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Models.

Download (902.98 kB)
conference contribution
posted on 2024-04-04, 11:13 authored by Siu Lun Chau, Krikamol Muandet, Dino Sejdinovic
We present a novel approach for explaining Gaussian processes (GPs) that can utilize the full analytical covariance structure present in GPs. Our method is based on the popular solution concept of Shapley values extended to stochastic cooperative games, resulting in explanations that are random variables. The GP explanations generated using our approach satisfy similar favorable axioms to standard Shapley values and possess a tractable covariance function across features and data observations. This covariance allows for quantifying explanation uncertainties and studying the statistical dependencies between explanations. We further extend our framework to the problem of predictive explanation, and propose a Shapley prior over the explanation function to predict Shapley values for new data based on previously computed ones. Our extensive illustrations demonstrate the effectiveness of the proposed approach.

History

Editor

Oh A ; Naumann T ; Globerson A ; Saenko K ; Hardt M ; Levine S

Primary Research Area

  • Trustworthy Information Processing

Name of Conference

Conference on Neural Information Processing Systems (NeurIPS)

Journal

NeurIPS

BibTeX

@conference{Chau:Muandet:Sejdinovic:2023, title = "Explaining the Uncertain: Stochastic Shapley Values for Gaussian Process Models.", author = "Chau, Siu Lun" AND "Muandet, Krikamol" AND "Sejdinovic, Dino", editor = "Oh, Alice" AND "Naumann, Tristan" AND "Globerson, Amir" AND "Saenko, Kate" AND "Hardt, Moritz" AND "Levine, Sergey", year = 2023, month = 12, journal = "NeurIPS" }

Usage metrics

    Categories

    No categories selected

    Licence

    Exports

    RefWorks
    BibTeX
    Ref. manager
    Endnote
    DataCite
    NLM
    DC