Image Classification on CIFAR-100 Practical Heterogeneity (Accuracy)
59.89AccuracyFedKT-CSD
Evaluation Results
| Method | Links | |
|---|---|---|
| FedKT-CSDHeterogeneity Type=Practical, Backbone=ResNet-18, Number of clients=20, Participation=Full, Communication rounds=1 round (synthetic pretraining) + local fine-tuning2026.07 | 59.89 | |
| APPLEHeterogeneity Type=Practical, Backbone=ResNet-18, Number of clients=20, Participation=Full, Communication rounds=502026.07 | 52.14 | |
| FedPHPHeterogeneity Type=Practical, Backbone=ResNet-18, Number of clients=20, Participation=Full, Communication rounds=502026.07 | 51.21 | |
| PartialFedHeterogeneity Type=Practical, Backbone=ResNet-18, Number of clients=20, Participation=Full, Communication rounds=502026.07 | 49.85 | |
| FedAMPHeterogeneity Type=Practical, Backbone=ResNet-18, Number of clients=20, Participation=Full, Communication rounds=502026.07 | 49.68 | |
| pFedMeHeterogeneity Type=Practical, Backbone=ResNet-18, Number of clients=20, Participation=Full, Communication rounds=502026.07 | 48.12 | |
| FedFomoHeterogeneity Type=Practical, Backbone=ResNet-18, Number of clients=20, Participation=Full, Communication rounds=502026.07 | 46.21 | |
| Per-FedAvgHeterogeneity Type=Practical, Backbone=ResNet-18, Number of clients=20, Participation=Full, Communication rounds=502026.07 | 45.38 | |
| FedAvgHeterogeneity Type=Practical, Backbone=ResNet-18, Number of clients=20, Participation=Full, Communication rounds=502026.07 | 32.77 |