FedAvg + SWA

Reported on 2 benchmarks across 1 task · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Methodology2 results

Federated LearningonCityscapes heterogeneous
mIoU· 2022-03-22
42.48
best: 49.75 (SiloBN + ASAM)
Improving Generalization in Federated Learning by Seeking Flat Minima arXiv:2203.11834
Federated LearningonLandmarks-User-160k
Acc@1-1262Clients· 2022-03-22
67.52
best: 68.32 (FedASAM + SWA)
Improving Generalization in Federated Learning by Seeking Flat Minima arXiv:2203.11834