mlsanityData to 7 Oct 2026

Towards Realistic Mechanisms That Incentivize Federated Participation and Contribution

arXiv 2310.13681 ↗First posted 20 Oct 2023cs.GT cs.CY cs.DCcited by 0

Not on the map. Why?

Abstract (arXiv)

Edge device participation in federating learning (FL) is typically studied through the lens of device-server communication (e.g., device dropout) and assumes an undying desire from edge devices to participate in FL. As a result, current FL frameworks are flawed when implemented in realistic settings, with many encountering the free-rider dilemma. In a step to push FL towards realistic settings, we propose RealFM: the first federated mechanism that (1) realistically models device utility, (2) incentivizes data contribution and device participation, (3) provably removes the free-rider dilemma, and (4) relaxes assumptions on data homogeneity and data sharing. Compared to previous FL mechanisms, RealFM allows for a non-linear relationship between model accuracy and utility, which improves the utility gained by the server and participating devices. On real-world data, RealFM improves device and server utility, as well as data contribution, by over 3 and 4 magnitudes respectively compared to baselines.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 40 references that are in the map. First posted on arXiv 20 Oct 2023.

Builds on

18 of 40 references.

References · 18

  1. 2017Revisiting Unreasonable Effectiveness of Data in Deep Learning Eracited by 916
  2. 2019Federated Learning with Personalization Layerscited by 533
  3. 2019FedMD: Heterogenous Federated Learning via Model Distillationcited by 454
  4. 2020HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clientscited by 334
  5. 2020Differentially Private Learning Needs Better Features (or Much More Data)cited by 233
  6. 2022FedDC: Federated Learning with Non-IID Data via Local Drift Decoupling and Correctioncited by 181
  7. 2020A Principled Approach to Data Valuation for Federated Learningcited by 127
  8. 2020Collaborative Fairness in Federated Learningcited by 95
  9. 2020Collaborative Machine Learning with Incentive-Aware Model Rewardscited by 71
  10. 2020Free-rider Attacks on Model Aggregation in Federated Learningcited by 57
  11. 2019Free-riders in Federated Learning: Attacks and Defensescited by 48
  12. 2021Incentive Mechanisms for Federated Learning: From Economic and Game Theoretic Perspectivecited by 47
6 more
  1. 2020A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learningcited by 38
  2. 2021A Comprehensive Survey of Incentive Mechanism for Federated Learningcited by 38
  3. 2022Mechanisms that Incentivize Data Sharing in Federated Learningcited by 38
  4. 2020Towards Federated Learning in UAV-Enabled Internet of Vehicles: A Multi-Dimensional Contract-Matching Approachcited by 29
  5. 2021A Contract Theory based Incentive Mechanism for Federated Learningcited by 13
  6. 2020Mechanism Design for Multi-Party Machine Learningcited by 6

Built on by

Not cited yet.