Image Classification on Tiny-ImageNet (500R/1000R Accuracy & Rounds)
42.26Accuracy (500R)FedACG
Evaluation results
| Method | Links | ||||
|---|---|---|---|---|---|
| FedACGFederated Learning Setting=Moderate-scale, Number of clients=100, Participation rate=5%, Dirichlet parameter=0.32022.01 | 42.26 | 46.31 | 226 | 331 | |
| FedDC‡Federated Learning Setting=Moderate-scale, Number of clients=100, Participation rate=5%, Dirichlet parameter=0.32022.01 | 40.32 | 45.51 | 340 | 403 | |
| FedDynFederated Learning Setting=Moderate-scale, Number of clients=100, Participation rate=5%, Dirichlet parameter=0.32022.01 | 37.35 | 41.18 | 344 | 573 | |
| FedMLBFederated Learning Setting=Moderate-scale, Number of clients=100, Participation rate=5%, Dirichlet parameter=0.32022.01 | 37.2 | 40.16 | 415 | 539 | |
| MOONFederated Learning Setting=Moderate-scale, Number of clients=100, Participation rate=5%, Dirichlet parameter=0.32022.01 | 36.62 | 40.33 | 410 | 627 | |
| FedAvgMFederated Learning Setting=Moderate-scale, Number of clients=100, Participation rate=5%, Dirichlet parameter=0.32022.01 | 36.32 | 38.51 | 416 | 829 | |
| FedLCFederated Learning Setting=Moderate-scale, Number of clients=100, Participation rate=5%, Dirichlet parameter=0.32022.01 | 35.03 | 35.95 | 500 | 1,000 | |
| FedProxFederated Learning Setting=Moderate-scale, Number of clients=100, Participation rate=5%, Dirichlet parameter=0.32022.01 | 34.14 | 35.53 | 613 | 1,000 | |
| FedAvgFederated Learning Setting=Moderate-scale, Number of clients=100, Participation rate=5%, Dirichlet parameter=0.32022.01 | 33.94 | 35.37 | 645 | 1,000 | |
| FedNTDFederated Learning Setting=Moderate-scale, Number of clients=100, Participation rate=5%, Dirichlet parameter=0.32022.01 | 33.91 | 37.33 | 547 | 1,000 | |
| FedDecorrFederated Learning Setting=Moderate-scale, Number of clients=100, Participation rate=5%, Dirichlet parameter=0.32022.01 | 33.4 | 34.86 | 1,000 | 1,000 | |
| FedADAMFederated Learning Setting=Moderate-scale, Number of clients=100, Participation rate=5%, Dirichlet parameter=0.32022.01 | 33.22 | 38.91 | 658 | 945 | |
| FedCM†Federated Learning Setting=Moderate-scale, Number of clients=100, Participation rate=5%, Dirichlet parameter=0.32022.01 | 31.61 | 37.87 | 694 | 1,000 |