Image Classification on Tiny ImageNet (Test Acc, Train Loss)
85.23Test AccuracyFedAdamW
Evaluation results
| Method | Links | ||
|---|---|---|---|
| FedAdamWBackbone=Swin Transformer, Data Distribution (Dirichlet)=Dir-0.1, Communication Rounds=100, Number of Clients=100, Participation Rate=5%, Batch Size=16, K=50, Evaluation Protocol=Fine-tuning2025.10 | 85.23 | 0.446 | |
| FedCMBackbone=Swin Transformer, Data Distribution (Dirichlet)=Dir-0.1, Communication Rounds=100, Number of Clients=100, Participation Rate=5%, Batch Size=16, K=50, Evaluation Protocol=Fine-tuning2025.10 | 83.18 | 0.522 | |
| SCAFFOLDBackbone=Swin Transformer, Data Distribution (Dirichlet)=Dir-0.1, Communication Rounds=100, Number of Clients=100, Participation Rate=5%, Batch Size=16, K=50, Evaluation Protocol=Fine-tuning2025.10 | 82.41 | 0.65 | |
| FedAvgBackbone=Swin Transformer, Data Distribution (Dirichlet)=Dir-0.1, Communication Rounds=100, Number of Clients=100, Participation Rate=5%, Batch Size=16, K=50, Evaluation Protocol=Fine-tuning2025.10 | 80.38 | 0.826 | |
| Local AdamWBackbone=Swin Transformer, Data Distribution (Dirichlet)=Dir-0.1, Communication Rounds=100, Number of Clients=100, Participation Rate=5%, Batch Size=16, K=50, Evaluation Protocol=Fine-tuning2025.10 | 80.26 | 0.686 | |
| FedAdamBackbone=Swin Transformer, Data Distribution (Dirichlet)=Dir-0.1, Communication Rounds=100, Number of Clients=100, Participation Rate=5%, Batch Size=16, K=50, Evaluation Protocol=Fine-tuning2025.10 | 78.2 | 0.834 | |
| Local AdamBackbone=Swin Transformer, Data Distribution (Dirichlet)=Dir-0.1, Communication Rounds=100, Number of Clients=100, Participation Rate=5%, Batch Size=16, K=50, Evaluation Protocol=Fine-tuning2025.10 | 73.63 | 1.045 | |
| FedLADABackbone=Swin Transformer, Data Distribution (Dirichlet)=Dir-0.1, Communication Rounds=100, Number of Clients=100, Participation Rate=5%, Batch Size=16, K=50, Evaluation Protocol=Fine-tuning2025.10 | 70.95 | 0.944 |