mlsanityData to 14 Oct 2026

Joint Shapley values: a measure of joint feature importance

arXiv 2107.11357 ↗First posted 23 Jul 2021stat.ML cs.AI cs.LGcited by 15

Not on the map. Why?

Abstract (arXiv)

The Shapley value is one of the most widely used measures of feature importance partly as it measures a feature's average effect on a model's prediction. We introduce joint Shapley values, which directly extend Shapley's axioms and intuitions: joint Shapley values measure a set of features' average contribution to a model's prediction. We prove the uniqueness of joint Shapley values, for any order of explanation. Results for games show that joint Shapley values present different insights from existing interaction indices, which assess the effect of a feature within a set of features. The joint Shapley values provide intuitive results in ML attribution problems. With binary features, we present a presence-adjusted global value that is more consistent with local intuitions than the usual approach.

Key facts. Cited by 15 papers in the map (data through 14 Oct 2026). Builds on 7 of its 24 references that are in the map. First posted on arXiv 23 Jul 2021.

Builds on

7 of 24 references.

References · 7

  1. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  2. 2019Explainable Machine Learning in Deploymentcited by 211
  3. 2019The Shapley Taylor Interaction Indexcited by 143
  4. 2019Asymmetric Shapley values: incorporating causal knowledge into model-agnostic explainabilitycited by 114
  5. 2021Sampling Permutations for Shapley Value Estimationcited by 102
  6. 2020Efficient nonparametric statistical inference on population feature importance using Shapley valuescited by 61
  7. 2020High Dimensional Model Explanations: an Axiomatic Approachcited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 1; 2022: 2; 2023: 2; 2024: 6; 2025: 3; 2026: 1.

15 papers.

Sort:

  1. 2022Measuring the Effect of Training Data on Deep Learning Predictions via Randomized Experimentscited by 50
  2. 2024shapiq: Shapley Interactions for Machine Learningcited by 43
  3. 2024KernelSHAP-IQ: Weighted Least-Square Optimization for Shapley Interactionscited by 22
  4. 2021Using Shapley Values and Variational Autoencoders to Explain Predictive Models with Dependent Mixed Featurescited by 19
  5. 2022Unifying local and global model explanations by functional decomposition of low dimensional structurescited by 18
  6. 2024Learning to Understand: Identifying Interactions via the M"obius Transformcited by 13
  7. 2024Unifying Feature-Based Explanations with Functional ANOVA and Cooperative Game Theorycited by 10
  8. 2023GeoShapley: A Game Theory Approach to Measuring Spatial Effects in Machine Learning Modelscited by 5
  9. 2023Towards Attributions of Input Variables in a Coalitioncited by 1
  10. 2025Can Moran Eigenvectors Improve Machine Learning of Spatial Data? Insights from Synthetic Data Validationcited by 1
  11. 2024Succinct Interaction-Aware Explanationscited by 0
  12. 2024Saliency Methods are Encoders: Analysing Logical Relations Towards Interpretationcited by 0
3 more
  1. 2025The Geography of Transportation Cybersecurity: Visitor Flows, Industry Clusters, and Spatial Dynamicscited by 0
  2. 2025SX-GeoTree: Self-eXplaining Geospatial Regression Tree Incorporating the Spatial Similarity of Feature Attributionscited by 0
  3. 2026Attribution Upsampling should Redistribute, Not Interpolatecited by 0