Image Classification on MNIST Rotation
94.501Average AccuracyFedFV
Evaluation results
| Method | Links | |||
|---|---|---|---|---|
| FedFV2024.10 | 94.501 | 0.302 | 1.646 | |
| STCH2024.10 | 92.977 | 0.409 | 2.385 | |
| EPO2024.10 | 92.604 | 0.35 | 1.467 | |
| AdaOMDgd-TCHOptimization=Gradient Descent, Weighting=Adaptive2024.10 | 92.593 | 0.341 | 1.296 | |
| AdaOMDeg-TCHOptimization=Exponentiated Gradient, Weighting=Adaptive2024.10 | 92.583 | 0.334 | 1.201 | |
| TCH2024.10 | 92.579 | 0.342 | 1.397 | |
| AdaExcessMTLWeighting=Adaptive2024.10 | 92.52 | 0.326 | 1.117 | |
| LS(FedAvg)Base Algorithm=FedAvg, Loss=LS2024.10 | 92.45 | 0.639 | 4.796 | |
| FERERO2024.10 | 92.443 | 0.64 | 4.807 | |
| FedMGDA+2024.10 | 92.416 | 0.322 | 1.153 | |
| qFFL2024.10 | 91.896 | 0.675 | 5.021 | |
| PropFair2024.10 | 90.622 | 0.742 | 5.454 | |
| OMDeg-TCHOptimization=Exponentiated Gradient2024.10 | 88.664 | 0.518 | 1.68 | |
| OMDgd-TCH(AFL)Optimization=Gradient Descent, Protocol=Agnostic Federated Learning (AFL)2024.10 | 88.597 | 0.514 | 1.658 | |
| ExcessMTL2024.10 | 88.566 | 0.503 | 1.637 |