Research map / Federated learning and privacy / Communication-efficient FL
Incentives in Federated Learning: Equilibria, Dynamics, and Mechanisms for Welfare Maximization
Aniket Murhekar, Zhuowen Yuan, Bhaskar Ray Chaudhury, Bo Li, Ruta Mehta
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add budget-balancing payments (FedBR-BG vs FedBR) | FedBR · MNIST p=0.2 | p-mean welfare: 53395.21 -> 54589.31 | Improved |
| add budget-balancing payments (FedBR-BG vs FedBR) | FedBR · MNIST p=1.0 | p-mean welfare: 5.340 -> 5.459 | Improved |
| add budget-balancing payments (FedBR-BG vs FedBR) | FedBR · CIFAR-10 p=0.2 | p-mean welfare: 58297.23 -> 60385.32 | Improved |
| add budget-balancing payments (FedBR-BG vs FedBR) | FedBR · CIFAR-10 p=1.0 | p-mean welfare: 5.681 -> 5.891 | Improved |
| let agents choose contributions via best response instead of contributing all data (FedBR vs FedAvg) | FedAvg · MNIST p=0.2 | p-mean welfare: 48985.23 -> 53395.21 | Improved |
| let agents choose contributions via best response instead of contributing all data (FedBR vs FedAvg) | FedAvg · CIFAR-10 p=0.2 | p-mean welfare: 42386.21 -> 58297.23 | Improved |
| replace MWFed with FedBR-BG | MWFed · CIFAR-10 p=1.0 | p-mean welfare: 4.891 -> 5.891 | Improved |
| compare MWFed to FedAvg | FedAvg · MNIST p=0.6 | p-mean welfare: 22.763 -> 21.648 | Hurt |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FedBR — FedBR: Improving Federated Learning on Heterogeneous Data via Local Learning Bias Reduction (ICML 2023) · better on 10 of 10 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- You Get What You Give: Reciprocally Fair Federated Learning (ICML 2025 · similarity 0.93)
- Towards Fair Graph Federated Learning via Incentive Mechanisms (AAAI 2024 · similarity 0.89)
- Multiplayer Federated Learning: Reaching Equilibrium with Less Communication (NeurIPS 2025 · similarity 0.88)
- Pursuing Overall Welfare in Federated Learning through Sequential Decision Making (ICML 2024 · similarity 0.88)
- Multi-Session Budget Optimization for Forward Auction-based Federated Learning (ICML 2025 · similarity 0.88)
- FedCross: Intertemporal Federated Learning Under Evolutionary Games (AAAI 2025 · similarity 0.88)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
