A Refutation of Shapley Values for Explainability

• URL: http://arxiv.org/abs/2309.03041v2
• Date: Tue, 13 Feb 2024 07:35:25 GMT
• Title: A Refutation of Shapley Values for Explainability
• Authors: Xuanxiang Huang, Joao Marques-Silva
• Abstract summary: Recent work demonstrated the existence of Boolean functions for which Shapley values provide misleading information. This paper proves that, for any number of features, there exist Boolean functions that exhibit one or more inadequacy-revealing issues.
• Score: 4.483306836710804
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent work demonstrated the existence of Boolean functions for which Shapley values provide misleading information about the relative importance of features in rule-based explanations. Such misleading information was broadly categorized into a number of possible issues. Each of those issues relates with features being relevant or irrelevant for a prediction, and all are significant regarding the inadequacy of Shapley values for rule-based explainability. This earlier work devised a brute-force approach to identify Boolean functions, defined on small numbers of features, and also associated instances, which displayed such inadequacy-revealing issues, and so served as evidence to the inadequacy of Shapley values for rule-based explainability. However, an outstanding question is how frequently such inadequacy-revealing issues can occur for Boolean functions with arbitrary large numbers of features. It is plain that a brute-force approach would be unlikely to provide insights on how to tackle this question. This paper answers the above question by proving that, for any number of features, there exist Boolean functions that exhibit one or more inadequacy-revealing issues, thereby contributing decisive arguments against the use of Shapley values as the theoretical underpinning of feature-attribution methods in explainability.

Related papers

• Refutation of Shapley Values for XAI -- Additional Evidence [4.483306836710804]
  Recent work demonstrated the inadequacy of Shapley values for explainable artificial intelligence (XAI) This paper demonstrates the inadequacy of Shapley values for families of classifiers where features are not Boolean, but also for families of classifiers for which multiple classes can be picked.
  arXiv  Detail & Related papers  (2023-09-30T15:44:06Z)
• The Inadequacy of Shapley Values for Explainability [0.685316573653194]
  The paper argues that the use of Shapley values in explainable AI (XAI) will necessarily yield provably misleading information about the relative importance of features for predictions.
  arXiv  Detail & Related papers  (2023-02-16T09:19:14Z)
• Inference on Strongly Identified Functionals of Weakly Identified Functions [71.42652863687117]
  We study a novel condition for the functional to be strongly identified even when the nuisance function is not. We propose penalized minimax estimators for both the primary and debiasing nuisance functions.
  arXiv  Detail & Related papers  (2022-08-17T13:38:31Z)
• Don't Explain Noise: Robust Counterfactuals for Randomized Ensembles [50.81061839052459]
  We formalize the generation of robust counterfactual explanations as a probabilistic problem. We show the link between the robustness of ensemble models and the robustness of base learners. Our method achieves high robustness with only a small increase in the distance from counterfactual explanations to their initial observations.
  arXiv  Detail & Related papers  (2022-05-27T17:28:54Z)
• groupShapley: Efficient prediction explanation with Shapley values for feature groups [2.320417845168326]
  Shapley values has established itself as one of the most appropriate and theoretically sound frameworks for explaining predictions from machine learning models. The main drawback with Shapley values is that its computational complexity grows exponentially in the number of input features. The present paper introduces groupShapley: a conceptually simple approach for dealing with the aforementioned bottlenecks.
  arXiv  Detail & Related papers  (2021-06-23T08:16:14Z)
• Fundamental Limits and Tradeoffs in Invariant Representation Learning [99.2368462915979]
  Many machine learning applications involve learning representations that achieve two competing goals. Minimax game-theoretic formulation represents a fundamental tradeoff between accuracy and invariance. We provide an information-theoretic analysis of this general and important problem under both classification and regression settings.
  arXiv  Detail & Related papers  (2020-12-19T15:24:04Z)
• The Struggles of Feature-Based Explanations: Shapley Values vs. Minimal Sufficient Subsets [61.66584140190247]
  We show that feature-based explanations pose problems even for explaining trivial models. We show that two popular classes of explainers, Shapley explainers and minimal sufficient subsets explainers, target fundamentally different types of ground-truth explanations.
  arXiv  Detail & Related papers  (2020-09-23T09:45:23Z)
• Structural Causal Models Are (Solvable by) Credal Networks [70.45873402967297]
  Causal inferences can be obtained by standard algorithms for the updating of credal nets. This contribution should be regarded as a systematic approach to represent structural causal models by credal networks. Experiments show that approximate algorithms for credal networks can immediately be used to do causal inference in real-size problems.
  arXiv  Detail & Related papers  (2020-08-02T11:19:36Z)
• Shapley explainability on the data manifold [10.439136407307048]
  General implementations of Shapley explainability make an untenable assumption: that the model's features are uncorrelated. One solution, based on generative modelling, provides flexible access to data imputations. The other directly learns the Shapley value-function, providing performance and stability at the cost of flexibility.
  arXiv  Detail & Related papers  (2020-06-01T21:20:04Z)
• Problems with Shapley-value-based explanations as feature importance measures [12.08945475767566]
  Game-theoretic formulations of feature importance have become popular as a way to "explain" machine learning models. We show that mathematical problems arise when Shapley values are used for feature importance. We argue that Shapley values do not provide explanations which suit human-centric goals of explainability.
  arXiv  Detail & Related papers  (2020-02-25T18:51:14Z)
• Contextual Linear Bandits under Noisy Features: Towards Bayesian Oracles [65.9694455739978]
  We study contextual linear bandit problems under feature uncertainty, where the features are noisy and have missing entries. Our analysis reveals that the optimal hypothesis can significantly deviate from the underlying realizability function, depending on the noise characteristics. This implies that classical approaches cannot guarantee a non-trivial regret bound.
  arXiv  Detail & Related papers  (2017-03-03T21:39:56Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.