Local Shapley: Model-Induced Locality and Optimal Reuse in Data Valuation

• URL: http://arxiv.org/abs/2603.03672v1
• Date: Wed, 04 Mar 2026 02:59:23 GMT
• Title: Local Shapley: Model-Induced Locality and Optimal Reuse in Data Valuation
• Abstract summary: Shapley is a principled foundation for data valuation, but exact computation is #P-hard due to the exponential coalition space.<n>We formalize this model-induced locality through support sets defined by the model's computational pathway.<n>We propose LSMR, an optimal subset-centric algorithm that trains each influential subset exactly once.
• Score: 32.861851772914996
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The Shapley value provides a principled foundation for data valuation, but exact computation is #P-hard due to the exponential coalition space. Existing accelerations remain global and ignore a structural property of modern predictors: for a given test instance, only a small subset of training points influences the prediction. We formalize this model-induced locality through support sets defined by the model's computational pathway (e.g., neighbors in KNN, leaves in trees, receptive fields in GNNs), showing that Shapley computation can be projected onto these supports without loss when locality is exact. This reframes Shapley evaluation as a structured data processing problem over overlapping support-induced subset families rather than exhaustive coalition enumeration. We prove that the intrinsic complexity of Local Shapley is governed by the number of distinct influential subsets, establishing an information-theoretic lower bound on retraining operations. Guided by this result, we propose LSMR (Local Shapley via Model Reuse), an optimal subset-centric algorithm that trains each influential subset exactly once via support mapping and pivot scheduling. For larger supports, we develop LSMR-A, a reuse-aware Monte Carlo estimator that remains unbiased with exponential concentration, with runtime determined by the number of distinct sampled subsets rather than total draws. Experiments across multiple model families demonstrate substantial retraining reductions and speedups while preserving high valuation fidelity.

Related papers

• RelShap: Relationally Consistent Shapley Explanations [16.81821907834537]
  We propose RelShap, a framework that incorporates relational constraints and data provenance into Shapley value.<n>The framework is estimator-agnostic and composes with Kernel SHAP, Monte Carlo, and SHAP without altering their sampling or weighting properties.
  arXiv  Detail & Related papers  (2026-08-11T23:45:00Z)
• An Odd Estimator for Shapley Values [19.262788739385012]
  The Shapley value is a framework for attribution in machine learning, encompassing feature importance, data valuation, and causal inference.<n>We prove that the Shapley value depends exclusively on the odd component of the set function, and that paired samplingizes the objective regression to filter out the irrelevant even component.<n>We propose OddSHAP, a consistent estimator that performs regression solely on the odd subspace.
  arXiv  Detail & Related papers  (2026-02-01T19:07:16Z)
• Truncating Trajectories in Monte Carlo Policy Evaluation: an Adaptive Approach [51.76826149868971]
  Policy evaluation via Monte Carlo simulation is at the core of many MC Reinforcement Learning (RL) algorithms. We propose as a quality index a surrogate of the mean squared error of a return estimator that uses trajectories of different lengths. We present an adaptive algorithm called Robust and Iterative Data collection strategy Optimization (RIDO)
  arXiv  Detail & Related papers  (2024-10-17T11:47:56Z)
• Improving the Weighting Strategy in KernelSHAP [0.8057006406834466]
  In Explainable AI (XAI) Shapley values are a popular framework for explaining predictions made by complex machine learning models.<n>We propose a novel modification of KernelSHAP which replaces the deterministic weights with ones to reduce the variance of the resulting Shapley value approximations.<n>Our methods can reduce the required number of contribution function evaluations by $5%$ to $50%$ while preserving the same accuracy of the approximated Shapley values.
  arXiv  Detail & Related papers  (2024-10-07T10:02:31Z)
• Robust Second-order LiDAR Bundle Adjustment Algorithm Using Mean Squared Group Metric [5.153195958837083]
  We propose a novel mean square group metric (MSGM) to build the optimization objective in the LiDAR BA algorithm. By integrating a robust kernel function, the metrics involved in the BA algorithm are reweighted, and thus enhancing the robustness of the solution process.
  arXiv  Detail & Related papers  (2024-09-03T12:53:39Z)
• Fast Shapley Value Estimation: A Unified Approach [71.92014859992263]
  We propose a straightforward and efficient Shapley estimator, SimSHAP, by eliminating redundant techniques. In our analysis of existing approaches, we observe that estimators can be unified as a linear transformation of randomly summed values from feature subsets. Our experiments validate the effectiveness of our SimSHAP, which significantly accelerates the computation of accurate Shapley values.
  arXiv  Detail & Related papers  (2023-11-02T06:09:24Z)
• Consensus-Adaptive RANSAC [104.87576373187426]
  We propose a new RANSAC framework that learns to explore the parameter space by considering the residuals seen so far via a novel attention layer. The attention mechanism operates on a batch of point-to-model residuals, and updates a per-point estimation state to take into account the consensus found through a lightweight one-step transformer.
  arXiv  Detail & Related papers  (2023-07-26T08:25:46Z)
• DU-Shapley: A Shapley Value Proxy for Efficient Dataset Valuation [23.646508094051768]
  We consider the dataset valuation problem, that is, the problem of quantifying the incremental gain. The Shapley value is a natural tool to perform dataset valuation due to its formal axiomatic justification. We propose a novel approximation, referred to as discrete uniform Shapley, which is expressed as an expectation under a discrete uniform distribution.
  arXiv  Detail & Related papers  (2023-06-03T10:22:50Z)
• 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)
• On Locality of Local Explanation Models [0.43012765978447565]
  We consider the formulation of neighbourhood reference distributions that improve the local interpretability of Shapley values. We observe that Neighbourhood Shapley values identify meaningful sparse feature relevance attributions that provide insight into local model behaviour.
  arXiv  Detail & Related papers  (2021-06-24T16:20:38Z)
• Clustered Federated Learning via Generalized Total Variation Minimization [83.26141667853057]
  We study optimization methods to train local (or personalized) models for local datasets with a decentralized network structure. Our main conceptual contribution is to formulate federated learning as total variation minimization (GTV) Our main algorithmic contribution is a fully decentralized federated learning algorithm.
  arXiv  Detail & Related papers  (2021-05-26T18:07:19Z)
• Spatially Adaptive Inference with Stochastic Feature Sampling and Interpolation [72.40827239394565]
  We propose to compute features only at sparsely sampled locations. We then densely reconstruct the feature map with an efficient procedure. The presented network is experimentally shown to save substantial computation while maintaining accuracy over a variety of computer vision tasks.
  arXiv  Detail & Related papers  (2020-03-19T15:36:31Z)

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.