Counterfactual Explanation of Shapley Value in Data Coalitions
Summary: Defines counterfactual explanations for Shapley value: the minimal subset transfer from owner A to B that reverses their Shapley ranking; proves existence and NP-hardness. Proposes SV-Exp—heuristics using differential Shapley, per-entry power, and greedy shifting—to cheaply approximate counterfactuals with empirical speedups. (summarized by gpt-5-mini on Feb 09 2026)
Incoming Non-self Citations Over Time
Authors
- 1. Michelle Si (Duke University)
- 2. Jian Pei (Duke University)
BibTeX Citation
@article{si_vldb24,
title = {{Counterfactual Explanation of Shapley Value in Data Coalitions}},
author = {Si, Michelle and Pei, Jian},
journal = {PVLDB},
series = {{VLDB} '24},
volume = {17},
number = {11},
pages = {3332--3345},
doi = {10.14778/3681954.3682004},
url = {https://doi.org/10.14778/3681954.3682004},
year = {2024}
}Incoming Citations (Sorted by Pagerank)
Showing 3 of 3 citing papers.
| Rank | Citing Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 10,214 | CoShap: A Scalable Coalition Growth Approach to Shapley Value Approximation | 2026 | SIGMOD | 5.093636e-05 |
| 10,796 | Understanding the Black Box: A Deep Empirical Dive into Shapley Value Approximations for Tabular Data | 2025 | SIGMOD | 5.093636e-05 |
| 10,906 | A Comprehensive Study of Shapley Value in Data Analytics | 2025 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Outgoing Citations (Sorted by Pagerank)
Showing 8 of 8 cited papers.
Citations counted here include only citations to other VLDB/SIGMOD/CIDR/PODS papers in this database.
| Rank | Cited Paper | Year | Venue | Pagerank |
|---|---|---|---|---|
| 1,488 | Towards Model-based Pricing for Machine Learning in a Data Marketplace | 2019 | SIGMOD | 0.00010612416 |
| 1,576 | Data Markets in the Cloud: An Opportunity for the Database Community | 2011 | VLDB | 0.00010317008 |
| 2,025 | Data Market Platforms: Trading Data Assets to Solve Data Problems | 2020 | VLDB | 9.2903125e-05 |
| 2,424 | Computing the Shapley Value of Facts in Query Answering | 2022 | SIGMOD | 8.6009068e-05 |
| 5,441 | Fast Shapley Value Computation in Data Assemblage Tasks as Cooperative Simple Games | 2024 | SIGMOD | 6.2184806e-05 |
| 6,272 | On Shapley Value in Data Assemblage Under Independent Utility | 2022 | VLDB | 5.9319813e-05 |
| 7,107 | A Demonstration of Sterling: A Privacy-Preserving Data Marketplace | 2018 | VLDB | 5.700522e-05 |
| 11,698 | Comprehensible Counterfactual Explanation on Kolmogorov-Smirnov Test | 2021 | VLDB | 5.093636e-05 |
Previous
Page 1 / 1
Next
Semantically Similar Papers
| # | Overall Rank | Paper | Year | Venue |
|---|---|---|---|---|
| 1 | 2,670 | The Impact of Negation on the Complexity of the Shapley Value in Conjunctive Queries | 2020 | PODS |
| 2 | 6,145 | Equitable Data Valuation Meets the Right to Be Forgotten in Model Markets | 2023 | VLDB |
| 3 | 2,424 | Computing the Shapley Value of Facts in Query Answering | 2022 | SIGMOD |
| 4 | 1,066 | Efficient Task-Specific Data Valuation for Nearest Neighbor Algorithms | 2019 | VLDB |
| 5 | 10,214 | CoShap: A Scalable Coalition Growth Approach to Shapley Value Approximation | 2026 | SIGMOD |
| 6 | 6,551 | Efficient Sampling Approaches to Shapley Value Approximation | 2023 | SIGMOD |
| 7 | 9,541 | Shapley Value Estimation Based on Differential Matrix | 2025 | SIGMOD |
| 8 | 5,441 | Fast Shapley Value Computation in Data Assemblage Tasks as Cooperative Simple Games | 2024 | SIGMOD |
| 9 | 6,272 | On Shapley Value in Data Assemblage Under Independent Utility | 2022 | VLDB |
| 10 | 10,906 | A Comprehensive Study of Shapley Value in Data Analytics | 2025 | VLDB |