mlsanityData to 7 Oct 2026

GTG-Shapley: Efficient and Accurate Participant Contribution Evaluation in Federated Learning

arXiv 2109.02053 ↗First posted 5 Sep 2021cs.AIcited by 73

Not on the map. Why?

Abstract (arXiv)

Federated Learning (FL) bridges the gap between collaborative machine learning and preserving data privacy. To sustain the long-term operation of an FL ecosystem, it is important to attract high quality data owners with appropriate incentive schemes. As an important building block of such incentive schemes, it is essential to fairly evaluate participants' contribution to the performance of the final FL model without exposing their private data. Shapley Value (SV)-based techniques have been widely adopted to provide fair evaluation of FL participant contributions. However, existing approaches incur significant computation costs, making them difficult to apply in practice. In this paper, we propose the Guided Truncation Gradient Shapley (GTG-Shapley) approach to address this challenge. It reconstructs FL models from gradient updates for SV calculation instead of repeatedly training with different combinations of FL participants. In addition, we design a guided Monte Carlo sampling approach combined with within-round and between-round truncation to further reduce the number of model reconstructions and evaluations required, through extensive experiments under diverse realistic data distribution settings. The results demonstrate that GTG-Shapley can closely approximate actual Shapley values, while significantly increasing computational efficiency compared to the state of the art, especially under non-i.i.d. settings.

Key facts. Cited by 73 papers in the map (data through 7 Oct 2026). Builds on 16 of its 42 references that are in the map. First posted on arXiv 5 Sep 2021.

Builds on

16 of 42 references.

References · 16

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,592
  2. 2019Data Shapley: Equitable Valuation of Data for Machine Learningcited by 617
  3. 2021Towards Personalized Federated Learningcited by 462
  4. 2019Towards Efficient Data Valuation Based on the Shapley Valuecited by 279
  5. 2020A Principled Approach to Data Valuation for Federated Learningcited by 127
  6. 2020Collaborative Fairness in Federated Learningcited by 95
  7. 2019Measure Contribution of Participants in Federated Learningcited by 78
  8. 2013Bounding the Estimation Error of Sampling-based Shapley Value Approximationcited by 56
  9. 2020FMore: An Incentive Scheme of Multi-dimensional Auction for Federated Learning in MECcited by 48
  10. 2020FOCUS: Dealing with Label Quality Disparity in Federated Learningcited by 36
  11. 2019A Crowdsourcing Framework for On-Device Federated Learningcited by 32
  12. 2020Hierarchically Fair Federated Learningcited by 28
4 more
  1. 2018Joint Service Pricing and Cooperative Relay Communication for Federated Learningcited by 22
  2. 2020Estimation of Individual Device Contributions for Incentivizing Federated Learningcited by 14
  3. 2019Rewarding High-Quality Data via Influence Functionscited by 11
  4. 2021When Crowdsensing Meets Federated Learning: Privacy-Preserving Mobile Crowdsensing Systemcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 9; 2023: 17; 2024: 22; 2025: 15; 2026: 9.

73 papers.

Sort:

By area:

  1. 2022Vertical Federated Learning: Concepts, Advances and Challengescited by 104
  2. 2022The Shapley Value in Machine Learningcited by 97
  3. 2023Federated Learning for Generalization, Robustness, Fairness: A Survey and Benchmarkcited by 97
  4. 2021Towards Fairness-Aware Federated Learningcited by 57
  5. 2023FedGH: Heterogeneous Federated Learning with Generalized Global Headercited by 56
  6. 2023Fair Federated Medical Image Segmentation via Client Contribution Estimationcited by 50
  7. 2022WeightedSHAP: analyzing and improving Shapley based feature attributionscited by 36
  8. 2024Advances and Open Challenges in Federated Foundation Modelscited by 33
  9. 2022Fair and efficient contribution valuation for vertical federated learningcited by 18
  10. 2023Data Valuation and Detections in Federated Learningcited by 17
  11. 2024Redefining Contributions: Shapley-Driven Federated Learningcited by 16
  12. 2023Fairness-Aware Client Selection for Federated Learningcited by 15
38 more
  1. 2024FedImpro: Measuring and Improving Client Update in Federated Learningcited by 15
  2. 2022Towards Verifiable Federated Learningcited by 11
  3. 2023Towards Interpretable Federated Learningcited by 11
  4. 2025Stochastic Self-Organization in Multi-Agent Systemscited by 9
  5. 2022Differentially Private Shapley Values for Data Evaluationcited by 8
  6. 2024Statistical Significance of Feature Importance Rankingscited by 7
  7. 2022Reward Systems for Trustworthy Medical Federated Learningcited by 6
  8. 2022Towards More Efficient Data Valuation in Healthcare Federated Learning using Ensemblingcited by 6
  9. 2023Greedy Shapley Client Selection for Communication-Efficient Federated Learningcited by 6
  10. 2025Aequa: Fair Model Rewards in Collaborative Learning via Slimmable Networkscited by 6
  11. 2022Auction-Based Ex-Post-Payment Incentive Mechanism Design for Horizontal Federated Learning with Reputation and Contribution Measurementcited by 5
  12. 2023Proof-of-Contribution-Based Design for Collaborative Machine Learning on Blockchaincited by 5
  13. 2024A Survey on Contribution Evaluation in Vertical Federated Learningcited by 5
  14. 2024ACE: A Model Poisoning Attack on Contribution Evaluation Methods in Federated Learningcited by 5
  15. 2023Trustworthy Federated Learning: A Surveycited by 4
  16. 2024Intelligent Agents for Auction-based Federated Learning: A Surveycited by 4
  17. 2023Exploring Data Redundancy in Real-world Image Classification through Data Selectioncited by 3
  18. 2023Multi-Session Budget Optimization for Forward Auction-based Federated Learningcited by 3
  19. 2024Contribution Evaluation of Heterogeneous Participants in Federated Learning via Prototypical Representationscited by 3
  20. 2024Benchmarking Data Heterogeneity Evaluation Approaches for Personalized Federated Learningcited by 3
  21. 2023Incentive Allocation in Vertical Federated Learning Based on Bankruptcy Problemcited by 2
  22. 2024Towards Fair, Robust and Efficient Client Contribution Evaluation in Federated Learningcited by 2
  23. 2024On the Volatility of Shapley-Based Contribution Metrics in Federated Learningcited by 2
  24. 2024Maverick-Aware Shapley Valuation for Client Selection in Federated Learningcited by 2
  25. 2024A Comprehensive Study of Shapley Value in Data Analyticscited by 2
  26. 2025Efficient Data Valuation Approximation in Federated Learning: A Sampling-based Approachcited by 2
  27. 2025Faithful Group Shapley Valuecited by 2
  28. 2025Analyzing the Impact of Participant Failures in Cross-Silo Federated Learningcited by 2
  29. 2023Welfare and Fairness Dynamics in Federated Learning: A Client Selection Perspectivecited by 1
  30. 2023Cross-Silo Federated Learning Across Divergent Domains with Iterative Parameter Alignmentcited by 1
  31. 2024Emulating Full Participation: An Effective and Fair Client Selection Strategy for Federated Learningcited by 1
  32. 2024WeShap: Weak Supervision Source Evaluation with Shapley Valuescited by 1
  33. 2024Federated Learning for Data Market: Shapley-UCB for Seller Selection and Incentivescited by 1
  34. 2024ROSS: RObust decentralized Stochastic learning based on Shapley valuescited by 1
  35. 2025VFL-RPS: Relevant Participant Selection in Vertical Federated Learningcited by 1
  36. 2025The Impact Analysis of Delays in Asynchronous Federated Learning with Data Heterogeneity for Edge Intelligencecited by 1
  37. 2025On the Fragility of Contribution Score Computation in Federated Learningcited by 1
  38. 2026Private and Robust Contribution Evaluation in Federated Learningcited by 1

50 most cited of 73 All 73 (JSON)