Image Classification on CIFAR-10 ρ=0 (test)
93.56AccuracySplitGP + FT
Evaluation results
| Method | Links | ||
|---|---|---|---|
| SplitGP + FTBackbone=VGG-11, Number of Clients (N)=50, Data Partitioning (Shard)=2, Personalization Intensity (λ)=0.2, Evaluation Protocol (Fine-tuning)=on-device fine-tuning2026.05 | 93.56 | 20.01 | |
| SplitGPBackbone=VGG-11, Number of Clients (N)=50, Data Partitioning (Shard)=2, Personalization Intensity (λ)=0.92026.05 | 93 | 26.5 | |
| HARMONYBackbone=VGG-11, Number of Clients (N)=50, Data Partitioning (Shard)=22026.05 | 92.34 | 21.39 | |
| SplitGPBackbone=VGG-11, Number of Clients (N)=50, Data Partitioning (Shard)=2, Personalization Intensity (λ)=0.22026.05 | 88.94 | 20.74 | |
| Multi-exit SFLBackbone=VGG-11, Number of Clients (N)=50, Data Partitioning (Shard)=22026.05 | 67.13 | 41.57 | |
| SplitFedBackbone=VGG-11, Number of Clients (N)=50, Data Partitioning (Shard)=22026.05 | 47.93 | 104.8 |