Overview

Shapley value attribution uses cooperative game theory to distribute an outcome among participants according to their average marginal contribution across possible coalitions. It is used to explain model predictions and interactions, value training data, and assign credit in settings such as multimodal models and multi-agent systems. Common approaches include exact computation for structured models, Monte Carlo and regression-based estimators, and hierarchical variants such as Owen values; causal and conditional methods aim to make coalition comparisons more realistic when inputs are dependent. A central challenge is balancing computational cost with reliable explanations, while choices about the value function, missing-feature treatment, and data distribution can substantially change what an attribution means—and whether it helps people make better decisions.

Latest papers

CardsList

111 papers9 papers in the last four weeks, down 10% on the four weeks before. 0.1% of all new papers.

  1. DynSurvX: Time-Resolved Explanations for Dynamic Survival Predictions

    Nov 16, 2026Van Tuan Nguyen, Agathe GuillouxFeature AttributionSurvival Analysis

  2. Leverage-Enhanced Sampling Owen Method for Explainable Artificial Intelligence

    Nov 16, 2026Jing Liu, Elena Parilina, Chi ZhaoShapley Value Attribution

  3. ReShap: Interpretable Reinforcement Learning for High-Dimensional Multi-Action Settings

    Nov 11, 2026Yiyu Qian, Pengfei Guo, Liyuan ZhaoInterpretability in RLReinforcement Learning

  4. MotionBench-XAI: Benchmarking What Shapes Shapley Explanations in Spatiotemporal Machine Learning

    Nov 5, 2026Mathilde Papillon, Louisa Cornelis, Nina MiolaneFeature AttributionShapley Value Attribution

  5. ShapleyOG: Fast Adaptive Shapley Value Estimation with Odd Gaussian Processes

    Nov 4, 2026David Rundel, R. Teal Witter, Santo M. A. R. Thies +3Shapley Value AttributionAdaptive Sampling

  6. A Comparative Study of Importance Attribution to Columns in Deep Learning over Relational Databases

    Nov 4, 2026Hila Levi-Yosefi, Shunit Agmon, Ester Livshits +2Feature AttributionExplainability Evaluation

  7. An Axiomatic Framework for Reinforcement Learning in Open Multi-Agent Systems

    Nov 2, 2026Jianhong Wang, Yang Li, Samuel Kaski +1Multi-Agent Reinforcement LearningCooperative MARL

  8. Top-kk Retrieval Leaves Memory Value Undetermined

    Nov 2, 2026Arman BehnamMemory Management for LLM AgentsMemory-Augmented Agents

  9. Seeing Through Distractions: Context-Stable Attribution via the Least Core

    Oct 26, 2026Sai Ganesh Nagarajan, Toshinori Yamauchi, Hiroshi KeraFeature AttributionShapley Value Attribution

  10. TempShap: When and How Much a Feature Matters in Time-Series Forecasting

    Oct 23, 2026Chi Zhao, Anastasiia Chelnokova, Jing Liu +1Explainable Time Series ForecastingFeature Attribution

  11. Spectral-Spatial Interpretation

    Oct 15, 2026Haotian Ma, Ruqi Yang, Philip TownsendFeature AttributionShapley Value Attribution

  12. Exact power indices for plurality-voting ensembles

    Oct 13, 2026Ilie Sarpe, Theofanis Georgakopoulos, Aristides GionisShapley Value AttributionEnsemble Learning

  13. Measuring Variable Importance Using Proportional Inclusive Marginal Effects

    Oct 12, 2026Youngseo Cho, V. Roshan JosephFeature AttributionShapley Value Attribution

  14. Interval-valued SHAP in Tree-Based Models

    Oct 8, 2026Chenrui Zhu, Vu-Linh Nguyen, Marie-Hélène Masson +1Shapley Value AttributionFeature Attribution

  15. A Hierarchy of Entropy-Shapley Games for Multivariate Predictive Uncertainty

    Sep 28, 2026Niklas Koenen, Claudia Battistin, Jeriek Van den Abeele +1Probabilistic ForecastingShapley Value Attribution

  16. Shapley Value Estimation for Multi-Site Data with Blockwise-Missing Features

    Sep 14, 2026Siqi Li, Wangxuan Fan, Yiming Li +2Feature AttributionLearning with Missing Data

  17. qshap: Fast Shapley Decomposition of R2R^2 for Gradient-Boosted Trees

    Aug 25, 2026Zhongli Jiang, Min Zhang, Dabao ZhangFeature AttributionShapley Value Attribution

  18. SkillShapley: Boundary-Adaptive Shapley Valuation for Skill Step Attribution in LLM Agents

    Aug 13, 2026Chang Liu, Yuqi Zhang, Yiman Zhong +3LLM Agent Skill LearningShapley Value Attribution

  19. RelShap: Relationally Consistent Shapley Explanations

    Aug 11, 2026Seungeun Lee, Joao Fonseca, Julia StoyanovichFeature AttributionShapley Value Attribution

  20. What Is a Skill Worth? Structure-Aware Shapley Valuation of Agent Skills

    Aug 5, 2026Tao Li, Junfeng Liu, Qinghua Zhao +5Agent EvaluationShapley Value Attribution

  21. Shapley-Value-Based Feature Attribution for Data Masking

    Jul 31, 2026Xinxue, Qu, Francis Bilson Darku +1Shapley Value AttributionPrivacy-Utility Tradeoff

  22. Explaining BiomedCLIP with Weighted Banzhaf Interactions Supported by Tree-Gram Parsing

    Jul 25, 2026Jakub Rymarski, Adam Rempała, Bartłomiej Sobieski +1VLM InterpretabilityShapley Value Attribution

  23. A Polynomial Architecture-Attribution Co-Design Framework for Exact Aumann-Shapley Attribution in GNNs

    Jul 23, 2026Bizu Feng, Zhimu Yang, Shuming Wang +4Gradient-Based AttributionPolynomial Neural Networks

  24. Fishing Out Free Riders: Shapley-Based Reward Attribution for Parallel Reasoning via Reinforcement Learning

    Jul 21, 2026Wentao Zhang, Haoyu Zhang, Xinke Jiang +7RL for Language Model ReasoningShapley Value Attribution