Image Classification on CIFAR10 (test) (Alpha-Weighted Accuracy)
74.08Accuracy (alpha=0.1)FedProx
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| FedProxModel=VGG 16, Parameters Up /Down=15.1 /15.1 M, FLOPs=20.2 G, Sys. Heter.=×2026.03 | 74.08 | 85.86 | 86.3 | |
| FedAvgModel=VGG 16, Parameters Up /Down=15.1 /15.1 M, FLOPs=40.3 G, Sys. Heter.=×2026.03 | 73.57 | 92.66 | 92.92 | |
| CA-HFPModel=VGG 16, Parameters Up /Down=3.95 /3.95 M, FLOPs=10.2 G, Sys. Heter.=✓2026.03 | 73.12 | 90.15 | 91.5 | |
| FedProxModel=Resnet 32, Parameters Up /Down=466 /466 K, FLOPs=4.45 G, Sys. Heter.=×2026.03 | 58.48 | 79.79 | 80.54 | |
| CA-HFPModel=Resnet 32, Parameters Up /Down=254 /254 K, FLOPs=5.20 G, Sys. Heter.=✓2026.03 | 55.98 | 84.61 | 85.03 | |
| FedAvgModel=Resnet 32, Parameters Up /Down=466 /466 K, FLOPs=9.01 G, Sys. Heter.=×2026.03 | 55.71 | 87.43 | 88.87 | |
| FedMPModel=VGG 16, Parameters Up /Down=3.95 /3.95 M, FLOPs=10.2 G, Sys. Heter.=✓2026.03 | 54.89 | 76.87 | 78.71 | |
| PruneFLModel=VGG 16, Parameters Up /Down=4.30 /4.30 M, FLOPs=20.1 G, Sys. Heter.=×2026.03 | 54.48 | 80.19 | 85.97 | |
| PruneFLModel=Resnet 32, Parameters Up /Down=261 /261 K, FLOPs=5.45 G, Sys. Heter.=×2026.03 | 54.37 | 80.21 | 81.36 | |
| DapperFLModel=Resnet 32, Parameters Up /Down=254 /466 K, FLOPs=5.23 G, Sys. Heter.=✓2026.03 | 53.18 | 80.05 | 81.21 | |
| DapperFLModel=VGG 16, Parameters Up /Down=3.95 /15.1 M, FLOPs=10.3 G, Sys. Heter.=✓2026.03 | 51.6 | 79.63 | 85.62 | |
| FedMPModel=Resnet 32, Parameters Up /Down=254 /254 K, FLOPs=5.20 G, Sys. Heter.=✓2026.03 | 43.55 | 67.47 | 69.53 |