cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Context

• URL: http://arxiv.org/abs/2602.20396v1
• Date: Mon, 23 Feb 2026 22:21:29 GMT
• Title: cc-Shapley: Measuring Multivariate Feature Importance Needs Causal Context
• Authors: Jörg Martin, Stefan Haufe,
• Abstract summary: cc-Shapley is an interventional modification of conventional observational Shapley values.<n>We show theoretically that cc-Shapley eradicates spurious association induced by collider bias.
• Score: 2.17663651602033
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Explainable artificial intelligence promises to yield insights into relevant features, thereby enabling humans to examine and scrutinize machine learning models or even facilitating scientific discovery. Considering the widespread technique of Shapley values, we find that purely data-driven operationalization of multivariate feature importance is unsuitable for such purposes. Even for simple problems with two features, spurious associations due to collider bias and suppression arise from considering one feature only in the observational context of the other, which can lead to misinterpretations. Causal knowledge about the data-generating process is required to identify and correct such misleading feature attributions. We propose cc-Shapley (causal context Shapley), an interventional modification of conventional observational Shapley values leveraging knowledge of the data's causal structure, thereby analyzing the relevance of a feature in the causal context of the remaining features. We show theoretically that this eradicates spurious association induced by collider bias. We compare the behavior of Shapley and cc-Shapley values on various, synthetic, and real-world datasets. We observe nullification or reversal of associations compared to univariate feature importance when moving from observational to cc-Shapley.

Related papers

• Explainability of Complex AI Models with Correlation Impact Ratio [10.61008729196936]
  Complex AI systems make better predictions but often lack transparency, limiting trustworthiness, interpretability, and safe deployment.<n>We introduce ExCIR (Explainability through Correlation Impact Ratio), a theoretically grounded, simple, and reliable metric for explaining the contribution of input features to model outputs.<n>We demonstrate that ExCIR captures dependencies arising from correlated features through a lightweight single pass formulation.
  arXiv  Detail & Related papers  (2026-01-10T21:56:24Z)
• Causal SHAP: Feature Attribution with Dependency Awareness through Causal Discovery [3.717095609283206]
  Causal SHAP is a novel framework that integrates causal relationships into feature attribution.<n>This study contributes to the field of Explainable AI (XAI) by providing a practical framework for causal-aware model explanations.
  arXiv  Detail & Related papers  (2025-08-31T13:31:34Z)
• A Critical Assessment of Interpretable and Explainable Machine Learning for Intrusion Detection [0.0]
  We study the use of overly complex and opaque ML models, unaccounted data imbalances and correlated features, inconsistent influential features across different explanation methods, and the implausible utility of explanations. Specifically, we advise avoiding complex opaque models such as Deep Neural Networks and instead using interpretable ML models such as Decision Trees. We find that feature-based model explanations are most often inconsistent across different settings.
  arXiv  Detail & Related papers  (2024-07-04T15:35:42Z)
• Causal Feature Selection via Transfer Entropy [59.999594949050596]
  Causal discovery aims to identify causal relationships between features with observational data. We introduce a new causal feature selection approach that relies on the forward and backward feature selection procedures. We provide theoretical guarantees on the regression and classification errors for both the exact and the finite-sample cases.
  arXiv  Detail & Related papers  (2023-10-17T08:04:45Z)
• Explaining Predictive Uncertainty with Information Theoretic Shapley Values [6.49838460559032]
  We adapt the popular Shapley value framework to explain various types of predictive uncertainty. We implement efficient algorithms that perform well in a range of experiments on real and simulated data.
  arXiv  Detail & Related papers  (2023-06-09T07:43:46Z)
• Amortized Inference for Causal Structure Learning [72.84105256353801]
  Learning causal structure poses a search problem that typically involves evaluating structures using a score or independence test. We train a variational inference model to predict the causal structure from observational/interventional data. Our models exhibit robust generalization capabilities under substantial distribution shift.
  arXiv  Detail & Related papers  (2022-05-25T17:37:08Z)
• Unsupervised Features Ranking via Coalitional Game Theory for Categorical Data [0.28675177318965034]
  Unsupervised feature selection aims to reduce the number of features. We show that the deriving features' selection outperforms competing methods in lowering the redundancy rate.
  arXiv  Detail & Related papers  (2022-05-17T14:17:36Z)
• 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)
• Learning Causal Models Online [103.87959747047158]
  Predictive models can rely on spurious correlations in the data for making predictions. One solution for achieving strong generalization is to incorporate causal structures in the models. We propose an online algorithm that continually detects and removes spurious features.
  arXiv  Detail & Related papers  (2020-06-12T20:49:20Z)
• Bayesian Sparse Factor Analysis with Kernelized Observations [67.60224656603823]
  Multi-view problems can be faced with latent variable models. High-dimensionality and non-linear issues are traditionally handled by kernel methods. We propose merging both approaches into single model.
  arXiv  Detail & Related papers  (2020-06-01T14:25:38Z)
• A Critical View of the Structural Causal Model [89.43277111586258]
  We show that one can identify the cause and the effect without considering their interaction at all. We propose a new adversarial training method that mimics the disentangled structure of the causal model. Our multidimensional method outperforms the literature methods on both synthetic and real world datasets.
  arXiv  Detail & Related papers  (2020-02-23T22:52:28Z)

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.