Image Classification on Tiny ImageNet 70% (test)
83.5Accuracy (Test)FedBCGD
Evaluation results
| Method | Links | ||
|---|---|---|---|
| FedBCGDBackbone=ViT-Base, Heterogeneity (ρ)=0.6, Number of clients (N)=6, Total communication floats budget=100d, Target Accuracy=70%2026.03 | 83.5 | 5.8 | |
| FedBCGD+Backbone=ViT-Base, Heterogeneity (ρ)=0.6, Number of clients (N)=6, Total communication floats budget=100d, Target Accuracy=70%2026.03 | 81.3 | 4.6 | |
| Centralised SGDBackbone=ViT-Base, Heterogeneity (ρ)=0.6, Number of clients (N)=6, Total communication floats budget=100d, Target Accuracy=70%2026.03 | 76.7 | — | |
| FedAvgMBackbone=ViT-Base, Heterogeneity (ρ)=0.6, Number of clients (N)=6, Total communication floats budget=100d, Target Accuracy=70%2026.03 | 76.7 | 10 | |
| FedAvgBackbone=ViT-Base, Heterogeneity (ρ)=0.6, Number of clients (N)=6, Total communication floats budget=100d, Target Accuracy=70%2026.03 | 71.2 | 67 | |
| FedAdamBackbone=ViT-Base, Heterogeneity (ρ)=0.6, Number of clients (N)=6, Total communication floats budget=100d, Target Accuracy=70%2026.03 | 65.5 | — | |
| SCAFFOLDBackbone=ViT-Base, Heterogeneity (ρ)=0.6, Number of clients (N)=6, Total communication floats budget=100d, Target Accuracy=70%2026.03 | 56.8 | — | |
| FedDCBackbone=ViT-Base, Heterogeneity (ρ)=0.6, Number of clients (N)=6, Total communication floats budget=100d, Target Accuracy=70%2026.03 | 55 | — |