Image Classification on CIFAR-10 Dirichlet alpha=0.6 (test)
85.11Test AccuracySpecGradFilter
Evaluation results
| Method | Links | |
|---|---|---|
| SpecGradFilterBackbone=ResNet-20, Number of clients=100, Client participation ratio=0.1, Communication rounds=300, Dirichlet distribution parameter alpha=0.6, spectral filter ratio r=0.052026.07 | 85.11 | |
| FedCMBackbone=ResNet-20, Number of clients=100, Client participation ratio=0.1, Communication rounds=300, Dirichlet distribution parameter alpha=0.62026.07 | 84.03 | |
| FedDynBackbone=ResNet-20, Number of clients=100, Client participation ratio=0.1, Communication rounds=300, Dirichlet distribution parameter alpha=0.62026.07 | 82.18 | |
| SCAFFOLDBackbone=ResNet-20, Number of clients=100, Client participation ratio=0.1, Communication rounds=300, Dirichlet distribution parameter alpha=0.62026.07 | 78.23 | |
| FedAvgBackbone=ResNet-20, Number of clients=100, Client participation ratio=0.1, Communication rounds=300, Dirichlet distribution parameter alpha=0.62026.07 | 77.02 | |
| FedProxBackbone=ResNet-20, Number of clients=100, Client participation ratio=0.1, Communication rounds=300, Dirichlet distribution parameter alpha=0.62026.07 | 77.01 | |
| FedLWSBackbone=ResNet-20, Number of clients=100, Client participation ratio=0.1, Communication rounds=300, Dirichlet distribution parameter alpha=0.62026.07 | 76.77 | |
| FedDiscoBackbone=ResNet-20, Number of clients=100, Client participation ratio=0.1, Communication rounds=300, Dirichlet distribution parameter alpha=0.62026.07 | 76.71 | |
| FedAWABackbone=ResNet-20, Number of clients=100, Client participation ratio=0.1, Communication rounds=300, Dirichlet distribution parameter alpha=0.62026.07 | 76.49 | |
| FedSAMBackbone=ResNet-20, Number of clients=100, Client participation ratio=0.1, Communication rounds=300, Dirichlet distribution parameter alpha=0.62026.07 | 75.88 |