Image Classification on CIFAR100 (test) (Alpha-Weighted Accuracy)
58.32Accuracy (alpha=0.1)DapperFL
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| DapperFLModel=VGG 16, Parameters Up /Down=3.95 /15.1 M, FLOPs=10.3 G, Sys. Heter.=✓2026.03 | 58.32 | 46.25 | 44.7 | |
| CA-HFPModel=VGG 16, Parameters Up /Down=3.95 /3.95 M, FLOPs=10.2 G, Sys. Heter.=✓2026.03 | 56.27 | 61.3 | 61.71 | |
| FedProxModel=VGG 16, Parameters Up /Down=15.1 /15.1 M, FLOPs=20.2 G, Sys. Heter.=×2026.03 | 50.01 | 53.21 | 53.9 | |
| FedAvgModel=VGG 16, Parameters Up /Down=15.1 /15.1 M, FLOPs=40.3 G, Sys. Heter.=×2026.03 | 49.21 | 59.79 | 61.46 | |
| CA-HFPModel=Resnet 32, Parameters Up /Down=254 /254 K, FLOPs=5.20 G, Sys. Heter.=✓2026.03 | 38.41 | 46.25 | 44.7 | |
| PruneFLModel=Resnet 32, Parameters Up /Down=261 /261 K, FLOPs=5.45 G, Sys. Heter.=×2026.03 | 38.12 | 45.51 | 41.49 | |
| DapperFLModel=Resnet 32, Parameters Up /Down=254 /466 K, FLOPs=5.23 G, Sys. Heter.=✓2026.03 | 37.77 | 45.36 | 43.35 | |
| PruneFLModel=VGG 16, Parameters Up /Down=4.30 /4.30 M, FLOPs=20.1 G, Sys. Heter.=×2026.03 | 36.8 | 39.57 | 40.29 | |
| FedAvgModel=Resnet 32, Parameters Up /Down=466 /466 K, FLOPs=9.01 G, Sys. Heter.=×2026.03 | 36.37 | 39.02 | 39.58 | |
| FedMPModel=VGG 16, Parameters Up /Down=3.95 /3.95 M, FLOPs=10.2 G, Sys. Heter.=✓2026.03 | 35.97 | 41.33 | 39.14 | |
| FedProxModel=Resnet 32, Parameters Up /Down=466 /466 K, FLOPs=4.45 G, Sys. Heter.=×2026.03 | 35.9 | 38.96 | 39.92 | |
| FedMPModel=Resnet 32, Parameters Up /Down=254 /254 K, FLOPs=5.20 G, Sys. Heter.=✓2026.03 | 26.55 | 34.46 | 32.93 |