Image Classification on MNIST DIRICHLET partition (test)
94.71AccuracyFEDADAVR
Evaluation results
| Method | Links | |
|---|---|---|
| FEDADAVROptimiser=ADAM, Server learning rate (ηs)=0.0052026.01 | 94.71 | |
| FEDADAVROptimiser=ADAM, Server learning rate (ηs)=0.012026.01 | 94.093 | |
| FEDADAVR-QUANTOptimiser=ADAM, Server learning rate (ηs)=0.0052026.01 | 93.778 | |
| FEDADAVR-QUANTOptimiser=ADABELIEF, Server learning rate (ηs)=0.012026.01 | 93.691 | |
| FEDADAVROptimiser=YOGI, Server learning rate (ηs)=0.012026.01 | 93.644 | |
| FEDADAVROptimiser=YOGI, Server learning rate (ηs)=0.0052026.01 | 92.924 | |
| FEDADAVROptimiser=ADAGRAD, Server learning rate (ηs)=0.012026.01 | 92.54 | |
| FEDADAVR-QUANTOptimiser=ADABELIEF, Server learning rate (ηs)=0.0052026.01 | 92.165 | |
| FEDADAVR-QUANTOptimiser=YOGI, Server learning rate (ηs)=0.0052026.01 | 91.644 | |
| FEDADAVROptimiser=ADABELIEF, Server learning rate (ηs)=0.0052026.01 | 90.653 | |
| FEDADAVR-QUANTOptimiser=YOGI, Server learning rate (ηs)=0.012026.01 | 90.476 | |
| FEDADAVR-QUANTOptimiser=ADAGRAD, Server learning rate (ηs)=0.012026.01 | 90.082 | |
| CRF-FedProxalpha=0.0032026.06 | 89.8 | |
| CRF-FedAvgalpha=0.0032026.06 | 89.5 | |
| FEDADAVROptimiser=ADAGRAD, Server learning rate (ηs)=0.0052026.01 | 89.272 | |
| FedProxalpha=0.0032026.06 | 89.2 | |
| FedAvgalpha=0.0032026.06 | 89 | |
| FEDADAVROptimiser=ADABELIEF, Server learning rate (ηs)=0.012026.01 | 88.223 | |
| RFAalpha=0.0032026.06 | 87.9 | |
| FEDADAVR-QUANTOptimiser=ADAM, Server learning rate (ηs)=0.012026.01 | 85.748 | |
| FEDADAVR-QUANTOptimiser=ADABELIEF, Server learning rate (ηs)=0.0012026.01 | 85.578 | |
| FEDADAVR-QUANTOptimiser=LAMB, Server learning rate (ηs)=0.012026.01 | 85.297 | |
| FEDADAVROptimiser=ADABELIEF, Server learning rate (ηs)=0.0012026.01 | 84.935 | |
| Geom. Medianalpha=0.0032026.06 | 84 | |
| FEDADAVR-QUANTOptimiser=ADAGRAD, Server learning rate (ηs)=0.0052026.01 | 83.913 | |
| FEDADAVROptimiser=LAMB, Server learning rate (ηs)=0.012026.01 | 82.008 | |
| FedNovaalpha=0.0032026.06 | 81.4 | |
| FEDADAVR-QUANTOptimiser=ADAM, Server learning rate (ηs)=0.0012026.01 | 80.97 | |
| FedVARPServer learning rate (ηs)=1.02026.01 | 80.284 | |
| FEDADAVROptimiser=ADAM, Server learning rate (ηs)=0.0012026.01 | 79.936 | |
| FEDADAVROptimiser=YOGI, Server learning rate (ηs)=0.0012026.01 | 78.241 | |
| Trim. Meanalpha=0.0032026.06 | 75.2 | |
| FEDADAVR-QUANTOptimiser=YOGI, Server learning rate (ηs)=0.0012026.01 | 74.876 | |
| FEDADAVR-QUANTOptimiser=LAMB, Server learning rate (ηs)=0.0052026.01 | 65.166 | |
| FEDADAVROptimiser=LAMB, Server learning rate (ηs)=0.0052026.01 | 62.869 | |
| FEDADAVROptimiser=ADAGRAD, Server learning rate (ηs)=0.0012026.01 | 58.21 | |
| FEDADAVR-QUANTOptimiser=ADAGRAD, Server learning rate (ηs)=0.0012026.01 | 49.605 | |
| FEDADAVR-QUANTOptimiser=LAMB, Server learning rate (ηs)=0.0012026.01 | 17.39 | |
| FEDADAVROptimiser=LAMB, Server learning rate (ηs)=0.0012026.01 | 14.176 | |
| FedVARPServer learning rate (ηs)=0.12026.01 | 11.2 | |
| FedVARPServer learning rate (ηs)=0.012026.01 | 10.896 |