CIFAR-100 cifar-100 Leaderboard
Auto-discovered from papers reporting CIFAR-100 (Accuracy). Β· Metric: Accuracy (higher is better)
| # | Model | Accuracy | Paper |
|---|---|---|---|
| 1 | QuantFL: Sustainable Federated Learning for Edge IoT via Pre-Trained Model Quantisation | 66.89 | β |
| 2 | HEART-PFL: Stable Personalized Federated Learning under Heterogeneity with Hierarchical Directional Alignment and Adversarial Knowledge Transfer | 63.42 | β |
| 3 | RIFLE: Robust Distillation-based FL for Deep Model Deployment on Resource-Constrained IoT Networks | 28.30 | β |
| 4 | FedEMA-Distill: Exponential Moving Average Guided Knowledge Distillation for Robust Federated Learning | 6.00 | β |
| 5 | Taming Preconditioner Drift: Unlocking the Potential of Second-Order Optimizers for Federated Learning on Non-IID Data | 5.80 | β |