SHAP scores fail pervasively even when Lipschitz succeeds

• URL: http://arxiv.org/abs/2412.13866v1
• Date: Wed, 18 Dec 2024 14:02:15 GMT
• Title: SHAP scores fail pervasively even when Lipschitz succeeds
• Authors: Olivier Letoffe, Xuanxiang Huang, Joao Marques-Silva,
• Abstract summary: Recent work devised examples of machine learning (ML) classifiers for which the computed SHAP scores are thoroughly unsatisfactory. It was unclear how general were the issues identified with SHAP scores. This paper shows that for Boolean classifiers there are arbitrarily many examples for which the SHAP scores must be deemed unsatisfactory.
• Score: 3.3766484312332303
• License:
• Abstract: The ubiquitous use of Shapley values in eXplainable AI (XAI) has been triggered by the tool SHAP, and as a result are commonly referred to as SHAP scores. Recent work devised examples of machine learning (ML) classifiers for which the computed SHAP scores are thoroughly unsatisfactory, by allowing human decision-makers to be misled. Nevertheless, such examples could be perceived as somewhat artificial, since the selected classes must be interpreted as numeric. Furthermore, it was unclear how general were the issues identified with SHAP scores. This paper answers these criticisms. First, the paper shows that for Boolean classifiers there are arbitrarily many examples for which the SHAP scores must be deemed unsatisfactory. Second, the paper shows that the issues with SHAP scores are also observed in the case of regression models. In addition, the paper studies the class of regression models that respect Lipschitz continuity, a measure of a function's rate of change that finds important recent uses in ML, including model robustness. Concretely, the paper shows that the issues with SHAP scores occur even for regression models that respect Lipschitz continuity. Finally, the paper shows that the same issues are guaranteed to exist for arbitrarily differentiable regression models.

Related papers

• Analysis of Zero Day Attack Detection Using MLP and XAI [0.0]
  This paper analyzes Machine Learning (ML) and Deep Learning (DL) based approaches to create Intrusion Detection Systems (IDS) The focus is on using the KDD99 dataset, which has the most research done among all the datasets for detecting zero-day attacks. We evaluate the performance of four multilayer perceptron (MLP) trained on the KDD99 dataset, including baseline ML models, weighted ML models, truncated ML models, and weighted truncated ML models.
  arXiv  Detail & Related papers  (2025-01-28T02:20:34Z)
• The Explanation Game -- Rekindled (Extended Version) [3.3766484312332303]
  Recent work demonstrated the existence of critical flaws in the current use of Shapley values in explainable AI (XAI) This paper proposes a novel definition of SHAP scores that overcomes existing flaws.
  arXiv  Detail & Related papers  (2025-01-20T12:00:36Z)
• Towards trustable SHAP scores [3.3766484312332303]
  This paper investigates how SHAP scores can be modified so as to extend axiomatic aggregations to the case of Shapley values in XAI. The proposed new definition of SHAP scores avoids all the known cases where unsatisfactory results have been identified.
  arXiv  Detail & Related papers  (2024-04-30T10:39:20Z)
• Value-Distributional Model-Based Reinforcement Learning [59.758009422067]
  Quantifying uncertainty about a policy's long-term performance is important to solve sequential decision-making tasks. We study the problem from a model-based Bayesian reinforcement learning perspective. We propose Epistemic Quantile-Regression (EQR), a model-based algorithm that learns a value distribution function.
  arXiv  Detail & Related papers  (2023-08-12T14:59:19Z)
• 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)
• Benign-Overfitting in Conditional Average Treatment Effect Prediction with Linear Regression [14.493176427999028]
  We study the benign overfitting theory in the prediction of the conditional average treatment effect (CATE) with linear regression models. We show that the T-learner fails to achieve the consistency except the random assignment, while the IPW-learner converges the risk to zero if the propensity score is known.
  arXiv  Detail & Related papers  (2022-02-10T18:51:52Z)
• Smoothed Embeddings for Certified Few-Shot Learning [63.68667303948808]
  We extend randomized smoothing to few-shot learning models that map inputs to normalized embeddings. Our results are confirmed by experiments on different datasets.
  arXiv  Detail & Related papers  (2022-02-02T18:19:04Z)
• Robust Implicit Networks via Non-Euclidean Contractions [63.91638306025768]
  Implicit neural networks show improved accuracy and significant reduction in memory consumption. They can suffer from ill-posedness and convergence instability. This paper provides a new framework to design well-posed and robust implicit neural networks.
  arXiv  Detail & Related papers  (2021-06-06T18:05:02Z)
• Positive-Congruent Training: Towards Regression-Free Model Updates [87.25247195148187]
  In image classification, sample-wise inconsistencies appear as "negative flips" A new model incorrectly predicts the output for a test sample that was correctly classified by the old (reference) model. We propose a simple approach for PC training, Focal Distillation, which enforces congruence with the reference model.
  arXiv  Detail & Related papers  (2020-11-18T09:00:44Z)
• Censored Quantile Regression Forest [81.9098291337097]
  We develop a new estimating equation that adapts to censoring and leads to quantile score whenever the data do not exhibit censoring. The proposed procedure named it censored quantile regression forest, allows us to estimate quantiles of time-to-event without any parametric modeling assumption.
  arXiv  Detail & Related papers  (2020-01-08T23:20:23Z)

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.