Federated Learning on CIFAR-10 (100 clients, Dirichlet α=0.3)
77.76Accuracy (Round 500)FedDC
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| FedDCParticipation rate=2%, Dirichlet parameter=0.3, Network cost per round=2x2022.01 | 77.76 | 82.86 | 473 | |
| FedACGParticipation rate=2%, Dirichlet parameter=0.3, Network cost per round=1x2022.01 | 76.36 | 84.73 | 543 | |
| FedDynParticipation rate=2%, Dirichlet parameter=0.3, Network cost per round=1x2022.01 | 74.27 | 80.2 | 660 | |
| FedLCParticipation rate=2%, Dirichlet parameter=0.3, Network cost per round=1x2022.01 | 72.9 | 80.9 | 736 | |
| MOONParticipation rate=2%, Dirichlet parameter=0.3, Network cost per round=1x2022.01 | 71.52 | 75.42 | 1,000 | |
| FedDecorrParticipation rate=2%, Dirichlet parameter=0.3, Network cost per round=1x2022.01 | 71.29 | 78.99 | 817 | |
| FedNTDParticipation rate=2%, Dirichlet parameter=0.3, Network cost per round=1x2022.01 | 69.11 | 80.43 | 797 | |
| FedAvgMParticipation rate=2%, Dirichlet parameter=0.3, Network cost per round=1x2022.01 | 68.09 | 79.91 | 748 | |
| FedADAMParticipation rate=2%, Dirichlet parameter=0.3, Network cost per round=1x2022.01 | 68.09 | 78.61 | 978 | |
| FedAvgParticipation rate=2%, Dirichlet parameter=0.3, Network cost per round=1x2022.01 | 65.92 | 78.13 | 977 | |
| FedMLBParticipation rate=2%, Dirichlet parameter=0.3, Network cost per round=1x2022.01 | 65.85 | 79.45 | 899 | |
| FedProxParticipation rate=2%, Dirichlet parameter=0.3, Network cost per round=1x2022.01 | 65.78 | 75.82 | 1,000 | |
| FedCMParticipation rate=2%, Dirichlet parameter=0.3, Network cost per round=1.5x2022.01 | 52.45 | 64.5 | 1,000 |