mlsanityData to 14 Oct 2026

Incentive Mechanism Design for Unbiased Federated Learning with Randomized Client Participation

arXiv 2304.07981 ↗First posted 17 Apr 2023cs.GT cs.AI cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Incentive mechanism is crucial for federated learning (FL) when rational clients do not have the same interests in the global model as the server. However, due to system heterogeneity and limited budget, it is generally impractical for the server to incentivize all clients to participate in all training rounds (known as full participation). The existing FL incentive mechanisms are typically designed by stimulating a fixed subset of clients based on their data quantity or system resources. Hence, FL is performed only using this subset of clients throughout the entire training process, leading to a biased model because of data heterogeneity. This paper proposes a game theoretic incentive mechanism for FL with randomized client participation, where the server adopts a customized pricing strategy that motivates different clients to join with different participation levels (probabilities) for obtaining an unbiased and high performance model. Each client responds to the server's monetary incentive by choosing its best participation level, to maximize its profit based on not only the incurred local cost but also its intrinsic value for the global model. To effectively evaluate clients' contribution to the model performance, we derive a new convergence bound which analytically predicts how clients' arbitrary participation levels and their heterogeneous data affect the model performance. By solving a non-convex optimization problem, our analysis reveals that the intrinsic value leads to the interesting possibility of bidirectional payment between the server and clients. Experimental results using real datasets on a hardware prototype demonstrate the superiority of our mechanism in achieving higher model performance for the server as well as higher profits for the clients.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 26 of its 46 references that are in the map. First posted on arXiv 17 Apr 2023.

Builds on

26 of 46 references.

References · 26

  1. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  2. 2019Advances and Open Problems in Federated Learningcited by 3,046
  3. 2018Federated Optimization in Heterogeneous Networkscited by 2,987
  4. 2021Convex optimizationcited by 2,515
  5. 2019On the Convergence of FedAvg on Non-IID Datacited by 1,229
  6. 2018Local SGD Converges Fast and Communicates Littlecited by 605
  7. 2018Adaptive Federated Learning in Resource Constrained Edge Computing Systemscited by 409
  8. 2020Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategiescited by 198
  9. 2021Achieving Linear Speedup with Partial Worker Participation in Non-IID Federated Learningcited by 193
  10. 2020Optimal Client Sampling for Federated Learningcited by 124
  11. 2019Federated Learning for Edge Networks: Resource Optimization and Incentive Mechanismcited by 75
  12. 2021Tackling System and Statistical Heterogeneity for Federated Learning with Adaptive Client Samplingcited by 66
14 more
  1. 2020Cost-Effective Federated Learning Designcited by 62
  2. 2020FMore: An Incentive Scheme of Multi-dimensional Auction for Federated Learning in MECcited by 48
  3. 2021Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspectivecited by 47
  4. 2019Device Scheduling with Fast Convergence for Wireless Federated Learningcited by 46
  5. 2019Motivating Workers in Federated Learning: A Stackelberg Game Perspectivecited by 45
  6. 2020An Incentive Mechanism for Federated Learning in Wireless Cellular network: An Auction Approachcited by 39
  7. 2019Toward an Automated Auction Framework for Wireless Federated Learning Services Marketcited by 38
  8. 2021A Comprehensive Survey of Incentive Mechanism for Federated Learningcited by 38
  9. 2022Communication-Efficient Device Scheduling for Federated Learning Using Stochastic Optimizationcited by 28
  10. 2020Federated Learning under Importance Samplingcited by 26
  11. 2021Cost-Effective Federated Learning in Mobile Edge Networkscited by 25
  12. 2021Optimal Rate Adaption in Federated Learning with Compressed Communicationscited by 15
  13. 2020Joint Auction-Coalition Formation Framework for Communication-Efficient Federated Learning in UAV-Enabled Internet of Vehiclescited by 14
  14. 2021Faithful Edge Federated Learning: Scalability and Privacycited by 13

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 1; 2025: 4; 2026: 3.

8 papers.

  1. 2025Ten Challenging Problems in Federated Foundation Modelscited by 20
  2. 2025Incentivizing Multi-Tenant Split Federated Learning for Foundation Models at the Network Edgecited by 1
  3. 2024Beyond Right to be Forgotten: Managing Heterogeneity Side Effects Through Strategic Incentivescited by 0
  4. 2025Cooperative SGD with Dynamic Mixing Matricescited by 0
  5. 2025Gaming and Cooperation in Federated Learning: What Can Happen and How to Monitor Itcited by 0
  6. 2026Mechanism Design for Federated Learning with Non-Monotonic Network Effectscited by 0
  7. 2026Incentive-Aware Federated Averaging with Performance Guarantees under Strategic Participationcited by 0
  8. 2026Federated Learning by Utility-Constrained Stochastic Aggregation for Improving Rational Participationcited by 0