Skip to Main content Skip to Navigation
New interface
Conference papers

The Explanation Game: Explaining Machine Learning Models Using Shapley Values

Abstract : A number of techniques have been proposed to explain a machine learning model’s prediction by attributing it to the corresponding input features. Popular among these are techniques that apply the Shapley value method from cooperative game theory. While existing papers focus on the axiomatic motivation of Shapley values, and efficient techniques for computing them, they offer little justification for the game formulations used, and do not address the uncertainty implicit in their methods’ outputs. For instance, the popular SHAP algorithm’s formulation may give substantial attributions to features that play no role in the model. In this work, we illustrate how subtle differences in the underlying game formulations of existing methods can cause large differences in the attributions for a prediction. We then present a general game formulation that unifies existing methods, and enables straightforward confidence intervals on their attributions. Furthermore, it allows us to interpret the attributions as contrastive explanations of an input relative to a distribution of reference inputs. We tie this idea to classic research in cognitive psychology on contrastive explanations, and propose a conceptual framework for generating and interpreting explanations for ML models, called formulate, approximate, explain (FAE). We apply this framework to explain black-box models trained on two UCI datasets and a Lending Club dataset.
Complete list of metadata

https://hal.inria.fr/hal-03414754
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Thursday, November 4, 2021 - 3:58:45 PM
Last modification on : Friday, November 5, 2021 - 3:57:57 AM
Long-term archiving on: : Saturday, February 5, 2022 - 7:11:28 PM

File

 Restricted access
To satisfy the distribution rights of the publisher, the document is embargoed until : 2023-01-01

Please log in to resquest access to the document

Licence


Distributed under a Creative Commons Attribution 4.0 International License

Identifiers

Citation

Luke Merrick, Ankur Taly. The Explanation Game: Explaining Machine Learning Models Using Shapley Values. 4th International Cross-Domain Conference for Machine Learning and Knowledge Extraction (CD-MAKE), Aug 2020, Dublin, Ireland. pp.17-38, ⟨10.1007/978-3-030-57321-8_2⟩. ⟨hal-03414754⟩

Share

Metrics

Record views

36