Image Classification on CIFAR10 Pathological Non-IID
86.08AccuracyOracle
Evaluation results
| Method | Links | |
|---|---|---|
| OracleBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%2025.05 | 86.08 | |
| pFedLIABackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%, Warm-up Rounds=202025.05 | 86.08 | |
| FedFomoBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%2025.05 | 80.98 | |
| FeSEMBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%2025.05 | 72.9 | |
| Local-onlyBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%2025.05 | 72.83 | |
| FedProtoBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%2025.05 | 67.7 | |
| FedAvgBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%2025.05 | 24.43 | |
| CFLBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%2025.05 | 24.42 |