The Inadequacy of Shapley Values for Explainability

• URL: http://arxiv.org/abs/2302.08160v1
• Date: Thu, 16 Feb 2023 09:19:14 GMT
• Title: The Inadequacy of Shapley Values for Explainability
• Authors: Xuanxiang Huang, Joao Marques-Silva
• Abstract summary: 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.
• Score: 0.685316573653194
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper develops a rigorous argument for why the use of Shapley values in explainable AI (XAI) will necessarily yield provably misleading information about the relative importance of features for predictions. Concretely, this paper demonstrates that there exist classifiers, and associated predictions, for which the relative importance of features determined by the Shapley values will incorrectly assign more importance to features that are provably irrelevant for the prediction, and less importance to features that are provably relevant for the prediction. The paper also argues that, given recent complexity results, the existence of efficient algorithms for the computation of rigorous feature attribution values in the case of some restricted classes of classifiers should be deemed unlikely at best.

Related papers

• The Foundations of Tokenization: Statistical and Computational Concerns [51.370165245628975]
  Tokenization is a critical step in the NLP pipeline. Despite its recognized importance as a standard representation method in NLP, the theoretical underpinnings of tokenization are not yet fully understood. The present paper contributes to addressing this theoretical gap by proposing a unified formal framework for representing and analyzing tokenizer models.
  arXiv  Detail & Related papers  (2024-07-16T11:12:28Z)
• From SHAP Scores to Feature Importance Scores [4.8158930873043335]
  This paper shows that there is an essential relationship between feature attribution and a priori voting power. It remains unclear how some of the most widely used power indices might be exploited as feature importance scores (FISs) in XAI.
  arXiv  Detail & Related papers  (2024-05-20T03:52:41Z)
• Identifiable Latent Neural Causal Models [82.14087963690561]
  Causal representation learning seeks to uncover latent, high-level causal representations from low-level observed data. We determine the types of distribution shifts that do contribute to the identifiability of causal representations. We translate our findings into a practical algorithm, allowing for the acquisition of reliable latent causal representations.
  arXiv  Detail & Related papers  (2024-03-23T04:13:55Z)
• Factor Importance Ranking and Selection using Total Indices [0.0]
  A factor importance measure ought to characterize the feature's predictive potential without relying on a specific prediction algorithm. We present the equivalence between predictiveness potential and total Sobol' indices from global sensitivity analysis. We introduce a novel consistent estimator that can be directly estimated from noisy data.
  arXiv  Detail & Related papers  (2024-01-01T16:02:06Z)
• A Refutation of Shapley Values for Explainability [4.483306836710804]
  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.
  arXiv  Detail & Related papers  (2023-09-06T14:34:18Z)
• Explainability is NOT a Game [4.483306836710804]
  XAI aims to help human decision-makers in understanding complex machine learning (ML) models. One of the hallmarks of XAI are measures of relative feature importance, which are theoretically justified through the use of Shapley values. This paper builds on recent work and offers a simple argument for why Shapley values can provide misleading measures of relative feature importance.
  arXiv  Detail & Related papers  (2023-06-27T09:32:49Z)
• Efficient Shapley Values Estimation by Amortization for Text Classification [66.7725354593271]
  We develop an amortized model that directly predicts each input feature's Shapley Value without additional model evaluations. Experimental results on two text classification datasets demonstrate that our amortized model estimates Shapley Values accurately with up to 60 times speedup.
  arXiv  Detail & Related papers  (2023-05-31T16:19:13Z)
• Inferring feature importance with uncertainties in high-dimensional data [0.0]
  We present a Shapley value based framework for inferring the importance of individual features, including uncertainty in the estimator. We build upon the recently published feature importance measure of SAGE and introduce sub-SAGE which can be estimated without resampling for tree-based models.
  arXiv  Detail & Related papers  (2021-09-02T11:57:34Z)
• Don't Just Blame Over-parametrization for Over-confidence: Theoretical Analysis of Calibration in Binary Classification [58.03725169462616]
  We show theoretically that over-parametrization is not the only reason for over-confidence. We prove that logistic regression is inherently over-confident, in the realizable, under-parametrized setting. Perhaps surprisingly, we also show that over-confidence is not always the case.
  arXiv  Detail & Related papers  (2021-02-15T21:38:09Z)
• Generative Counterfactuals for Neural Networks via Attribute-Informed Perturbation [51.29486247405601]
  We design a framework to generate counterfactuals for raw data instances with the proposed Attribute-Informed Perturbation (AIP) By utilizing generative models conditioned with different attributes, counterfactuals with desired labels can be obtained effectively and efficiently. Experimental results on real-world texts and images demonstrate the effectiveness, sample quality as well as efficiency of our designed framework.
  arXiv  Detail & Related papers  (2021-01-18T08:37:13Z)
• Evaluations and Methods for Explanation through Robustness Analysis [117.7235152610957]
  We establish a novel set of evaluation criteria for such feature based explanations by analysis. We obtain new explanations that are loosely necessary and sufficient for a prediction. We extend the explanation to extract the set of features that would move the current prediction to a target class.
  arXiv  Detail & Related papers  (2020-05-31T05:52:05Z)

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.