| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Image Classification | FEMNIST (test) | Accuracy97.31 | 83 | |
| Image Classification | FEMNIST (LEAF) (test) | Accuracy82.45 | 39 | |
| Image Classification | FEMNIST | Accuracy81.1 | 15 | |
| Image Classification | FEMNIST C=10 original (test) | Accuracy82.02 | 13 | |
| Image Classification | FEMNIST (non-iid) | Accuracy84 | 13 | |
| Multi-class classification | FEMNIST realistic non-IID LEAF benchmark (test) | Top-1 Acc85.2 | 11 | |
| Image Classification | FEMNIST LEAF | Accuracy80.61 | 10 | |
| Image Classification | FEMNIST 10 new writers (test) | Overall Accuracy88.18 | 9 | |
| Federated Image Classification | FEMNIST non-i.i.d. | Test Error14.76 | 8 | |
| Federated Image Classification | FEMNIST i.i.d. | Test Error Rate14.79 | 8 | |
| Image Classification | FEMNIST non-i.i.d. | Test Error Rate14.76 | 8 | |
| Image Classification | FEMNIST (i.i.d.) | Test Error14.79 | 8 | |
| Handwritten character recognition | FEMNIST 7 (test) | Avg Accuracy79.9 | 7 | |
| Personalized Federated Learning | FEMNIST (test) | Top 10% Most Samples Accuracy76.24 | 5 | |
| Malicious Client Detection | FEMNIST | Accuracy79.37 | 4 | |
| Federated Learning Classification | FEMNIST FedAvg 0.8235 (test) | Accuracy81.45 | 4 | |
| Handwriting image classification | FEMNIST LEAF (test) | Personalization Accuracy71.84 | 3 | |
| Federated Image Classification | FEMNIST unseen clients (test) | Test Accuracy79.1 | 3 | |
| Image Classification | FEMNIST LEAF (non-i.i.d.) | Accuracy- | 0 |