mlsanityData to 14 Oct 2026

Is Shapley Value fair? Improving Client Selection for Mavericks in Federated Learning

arXiv 2106.10734 ↗First posted 20 Jun 2021cs.LG cs.AI cs.CYcited by 7

Not on the map. Why?

Abstract (arXiv)

Shapley Value is commonly adopted to measure and incentivize client participation in federated learning. In this paper, we show -- theoretically and through simulations -- that Shapley Value underestimates the contribution of a common type of client: the Maverick. Mavericks are clients that differ both in data distribution and data quantity and can be the sole owners of certain types of data. Selecting the right clients at the right moment is important for federated learning to reduce convergence times and improve accuracy. We propose FedEMD, an adaptive client selection strategy based on the Wasserstein distance between the local and global data distributions. As FedEMD adapts the selection probability such that Mavericks are preferably selected when the model benefits from improvement on rare classes, it consistently ensures the fast convergence in the presence of different types of Mavericks. Compared to existing strategies, including Shapley Value-based ones, FedEMD improves the convergence of neural network classifiers by at least 26.9% for FedAvg aggregation compared with the state of the art.

Key facts. Cited by 7 papers in the map (data through 14 Oct 2026). Builds on 25 of its 42 references that are in the map. First posted on arXiv 20 Jun 2021.

Builds on

25 of 42 references.

References · 25

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2018Federated Learning with Non-IID Datacited by 1,108
  5. 2020Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimizationcited by 906
  6. 2020Personalized Federated Learning with Moreau Envelopescited by 618
  7. 2021Federated Learning on Non-IID Data Silos: An Experimental Studycited by 568
  8. 2020An Efficient Framework for Clustered Federated Learningcited by 511
  9. 2018Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edgecited by 352
  10. 2020Attack of the Tails: Yes, You Really Can Backdoor Federated Learningcited by 309
  11. 2020Data Poisoning Attacks Against Federated Learning Systemscited by 275
  12. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 198
13 more
  1. 2020A Principled Approach to Data Valuation for Federated Learningcited by 127
  2. 2020Lower Bounds and Optimal Algorithms for Personalized Federated Learningcited by 123
  3. 2021Distributionally Robust Federated Averagingcited by 104
  4. 2020Client Selection and Bandwidth Allocation in Wireless Federated Learning Networks: A Long-Term Perspectivecited by 103
  5. 2020Robust Federated Learning: The Case of Affine Distribution Shiftscited by 102
  6. 2020TiFL: A Tier-based Federated Learning Systemcited by 96
  7. 2019Measure Contribution of Participants in Federated Learningcited by 79
  8. 2020Collaborative Machine Learning with Incentive-Aware Model Rewardscited by 71
  9. 2019Active Federated Learningcited by 63
  10. 2020An Efficiency-boosting Client Selection Scheme for Federated Learning with Fairness Guaranteecited by 62
  11. 2020FedCoin: A Peer-to-Peer Payment System for Federated Learningcited by 39
  12. 2020Hierarchically Fair Federated Learningcited by 28
  13. 2019Rewarding High-Quality Data via Influence Functionscited by 11

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 0; 2023: 2; 2024: 2; 2025: 2.

7 papers.

  1. 2021Resource-Efficient Federated Learningcited by 26
  2. 2023Greedy Shapley Client Selection for Communication-Efficient Federated Learningcited by 7
  3. 2024A Comprehensive Study of Shapley Value in Data Analyticscited by 2
  4. 2023Data valuation: The partial ordinal Shapley value for machine learningcited by 1
  5. 2025On the Fragility of Contribution Score Computation in Federated Learningcited by 1
  6. 2024Photon: Federated LLM Pre-Trainingcited by 0
  7. 2025Owen Sampling Accelerates Contribution Estimation in Federated Learningcited by 0