Papers › Federated Optimization for Heterogeneous Networks

Federated Optimization for Heterogeneous Networks

16 May 2019ICML Workshop AMTL 2019 6archive 2025-07-28

Anonymous

Federated learning involves training and effectively combining machine learning models from distributed partitions of data (i.e., tasks) on edge devices, and be naturally viewed as a multi- task learning problem. While Federated Averaging (FedAvg) is the leading optimization method for training non-convex models in this setting, its behavior is not well understood in realistic federated settings when the devices/tasks are statistically heterogeneous, i.e., where each device collects data in a non-identical fashion. In this work, we introduce a framework, called FedProx, to tackle statistical heterogeneity. FedProx encompasses FedAvg as a special case. We provide convergence guarantees for FedProx through a device dissimilarity assumption. Our empirical evaluation validates our theoretical analysis and demonstrates the improved robustness and stability of FedProx for learning in heterogeneous networks.

PaperPDFCode

Code

litian96/FedProx officialmentioned in papertfMIT report
KarhouTam/FL-bench pytorchGPL-3.0 report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Federated LearningMulti-Task Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections