Image Classification on Fashion MNIST Noisy Non-IID
87.39AccuracyFedProto
Evaluation results
| Method | Links | |
|---|---|---|
| FedProtoBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Noisy Non-IID, Client Participation Rate=10%2025.05 | 87.39 | |
| FedFomoBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Noisy Non-IID, Client Participation Rate=10%2025.05 | 85.11 | |
| Local-onlyBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Noisy Non-IID, Client Participation Rate=10%2025.05 | 84.71 | |
| pFedLIABackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Noisy Non-IID, Client Participation Rate=10%, Warm-up Rounds=202025.05 | 82.1 | |
| FeSEMBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Noisy Non-IID, Client Participation Rate=10%2025.05 | 81.75 | |
| CFLBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Noisy Non-IID, Client Participation Rate=10%2025.05 | 67.1 | |
| FedAvgBackbone=ResNet-18, Pre-trained=true, Data Heterogeneity Setting=Noisy Non-IID, Client Participation Rate=10%2025.05 | 65.95 |