Image Classification on Fashion MNIST Pathological Non-IID
99.07AccuracyOracle
Evaluation results
| Method | Links | |
|---|---|---|
| OracleBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%2025.05 | 99.07 | |
| pFedLIABackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%, Warm-up Rounds=202025.05 | 99.07 | |
| FedFomoBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%2025.05 | 98.63 | |
| FeSEMBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%2025.05 | 97.97 | |
| FedProtoBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%2025.05 | 93.93 | |
| Local-onlyBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%2025.05 | 84.71 | |
| CFLBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%2025.05 | 61 | |
| FedAvgBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Pathological Non-IID, Client Participation Rate=10%2025.05 | 60.99 |