Fair feature attribution for multi-output prediction: a Shapley-based perspective

• URL: http://arxiv.org/abs/2602.22882v1
• Date: Thu, 26 Feb 2026 11:22:08 GMT
• Title: Fair feature attribution for multi-output prediction: a Shapley-based perspective
• Authors: Umberto Biccari, Alain Ibáñez de Opakua, José María Mato, Óscar Millet, Roberto Morales, Enrique Zuazua,
• Abstract summary: We provide an axiomatic characterization of feature attribution for multi-output predictors within the Shapley framework.<n>By extending the classical Shapley axioms to vector-valued cooperative games, we establish a rigidity theorem showing that any attribution rule satisfying efficiency, symmetry, dummy player, and additivity must necessarily decompose component-wise across outputs.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this article, we provide an axiomatic characterization of feature attribution for multi-output predictors within the Shapley framework. While SHAP explanations are routinely computed independently for each output coordinate, the theoretical necessity of this practice has remained unclear. By extending the classical Shapley axioms to vector-valued cooperative games, we establish a rigidity theorem showing that any attribution rule satisfying efficiency, symmetry, dummy player, and additivity must necessarily decompose component-wise across outputs. Consequently, any joint-output attribution rule must relax at least one of the classical Shapley axioms. This result identifies a previously unformalized structural constraint in Shapley-based interpretability, clarifying the precise scope of fairness-consistent explanations in multi-output learning. Numerical experiments on a biomedical benchmark illustrate that multi-output models can yield computational savings in training and deployment, while producing SHAP explanations that remain fully consistent with the component-wise structure imposed by the Shapley axioms.

Related papers

• Exact Functional ANOVA Decomposition for Categorical Inputs Models [2.762021507766656]
  ANOVA offers a principled framework for interpretability by decomposing a model's prediction into main effects and higher-order interactions.<n>For independent features, this decomposition is well-defined, strongly linked with SHAP values, and serves as a cornerstone of additive explainability.<n>We completely resolve this limitation for categorical inputs.
  arXiv  Detail & Related papers  (2026-03-03T06:59:56Z)
• A Polynomial-Time Axiomatic Alternative to SHAP for Feature Attribution [0.0]
  We study feature attribution through the lens of cooperative game theory by formulating a class of XAI-TU games.<n>We propose a low-cost attribution rule, ESENSC_rev2, constructed by combining two-time closed-form rules.<n>Experiments show that ESENSC_rev2 closely approximates exact SHAP while substantially improving scalability.
  arXiv  Detail & Related papers  (2026-02-28T06:30:35Z)
• Decoupling the Effect of Chain-of-Thought Reasoning: A Human Label Variation Perspective [60.45433515408158]
  We show that long Chain-of-Thought (CoT) serves as a decisive decision-maker for the top option but fails to function as a granular distribution calibrator for ambiguous tasks.<n>We observe a distinct "decoupled mechanism": while CoT improves distributional alignment, final accuracy is dictated by CoT content.
  arXiv  Detail & Related papers  (2026-01-06T16:26:40Z)
• Loss-Complexity Landscape and Model Structure Functions [53.92822954974537]
  We develop a framework for dualizing the Kolmogorov structure function $h_x(alpha)$.<n>We establish a mathematical analogy between information-theoretic constructs and statistical mechanics.<n>We explicitly prove the Legendre-Fenchel duality between the structure function and free energy.
  arXiv  Detail & Related papers  (2025-07-17T21:31:45Z)
• Beyond Shapley Values: Cooperative Games for the Interpretation of Machine Learning Models [0.3749861135832073]
  We revisit cooperative game theory from an interpretability perspective and argue for a broader and more principled use of its tools.<n>We highlight two general families of efficient allocations, the Weber and Harsanyi sets, that extend beyond Shapley values.<n>We present an accessible overview of these allocation schemes, clarify the distinction between value functions and aggregation rules, and introduce a three-step blueprint for constructing reliable and theoretically-grounded feature attributions.
  arXiv  Detail & Related papers  (2025-06-16T18:22:23Z)
• Explaining a probabilistic prediction on the simplex with Shapley compositions [11.009289275721283]
  We introduce Shapley compositions as a well-founded way to properly explain a multiclass probabilistic prediction.<n>We prove that the Shapley composition is the unique quantity satisfying linearity, symmetry and efficiency on the Aitchison simplex.
  arXiv  Detail & Related papers  (2024-08-02T16:40:58Z)
• On the Tractability of SHAP Explanations under Markovian Distributions [0.1578515540930834]
  The SHAP framework is one of the most widely utilized frameworks for local explainability of ML models. Despite its popularity, its exact computation is known to be very challenging, proven to be NP-Hard in various configurations. Recent works have unveiled positive complexity results regarding the computation of the SHAP score for specific model families.
  arXiv  Detail & Related papers  (2024-05-05T13:56:12Z)
• The vacuum provides quantum advantage to otherwise simulatable architectures [49.1574468325115]
  We consider a computational model composed of ideal Gottesman-Kitaev-Preskill stabilizer states. We provide an algorithm to calculate the probability density function of the measurement outcomes.
  arXiv  Detail & Related papers  (2022-05-19T18:03:17Z)
• Reinforcement Learning from Partial Observation: Linear Function Approximation with Provable Sample Efficiency [111.83670279016599]
  We study reinforcement learning for partially observed decision processes (POMDPs) with infinite observation and state spaces. We make the first attempt at partial observability and function approximation for a class of POMDPs with a linear structure.
  arXiv  Detail & Related papers  (2022-04-20T21:15:38Z)
• Generalization Properties of Optimal Transport GANs with Latent Distribution Learning [52.25145141639159]
  We study how the interplay between the latent distribution and the complexity of the pushforward map affects performance. Motivated by our analysis, we advocate learning the latent distribution as well as the pushforward map within the GAN paradigm.
  arXiv  Detail & Related papers  (2020-07-29T07:31:33Z)
• Generalised Lipschitz Regularisation Equals Distributional Robustness [47.44261811369141]
  We give a very general equality result regarding the relationship between distributional robustness and regularisation. We show a new result explicating the connection between adversarial learning and distributional robustness.
  arXiv  Detail & Related papers  (2020-02-11T04:19:43Z)

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.