Research map / Federated learning and privacy / Communication-efficient FL
FedFit: Federated Dynamic Sparse Training via Fisher Information scoring
Meng Bi, Hong Huang, Jinlong Song, Charles Wang, Chengming Hu, Xi Chen, Ting Yu, Xue Liu
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Fisher-based scoring in the pruning stage (ablation) | FedFit · CIFAR-10 (Fig. 6) | mean accuracy | Improved |
| add Fisher-based scoring in the growing stage (ablation) | FedFit · CIFAR-10 (Fig. 6) | mean accuracy | Improved |
| use FedFit Fisher prune/grow scores instead of FedDST heuristics (ablation) | FedDST · CIFAR-10 (Fig. 6) | mean accuracy | Improved |
| use FedFit instead of strongest baseline across datasets | strongest baseline · Table 1 (CV tasks) | test accuracy: roughly 3.8% | Improved |
| use FedFit instead of FedRTS at low density | FedRTS · CIFAR10 ResNet18 rho=0.1 | test accuracy: 64.54 -> 65.51 | Improved |
| use FedFit instead of FedRTS at low density | FedRTS · SVHN ShuffleNetV2 rho=0.1 | test accuracy: 33.67 -> 50.63 | Improved |
| use FedFit instead of FedRTS | FedRTS · Tiny ImageNet ResNet18 rho=0.2 | test accuracy: 5.60 -> 5.38 | Hurt |
| use FedFit instead of FedSGC at rho=0.3 | FedSGC · SVHN ShuffleNetV2 rho=0.3 | test accuracy: 70.24 -> 69.15 | Hurt |
| use FedFit at density 0.3 instead of dense FedAvg | FedAvg · CIFAR10 ResNet18 | test accuracy: 77.25 -> 76.43 | Hurt |
| use FedFit at density 0.3 instead of dense FedAvg | FedAvg · Tiny ImageNet ResNet18 | test accuracy: 8.97 -> 7.61 | Hurt |
| lower participation ratio of clients | FedFit · CIFAR-10 (Fig. 5) | accuracy | Mixed |
| increase data heterogeneity (smaller Dirichlet a) | FedFit · CIFAR-10 (Fig. 4) | accuracy | No clear effect |
Closest papers by meaning
- SparsyFed: Sparse Adaptive Federated Learning (ICLR 2025 · similarity 0.90)
- An Efficient and Accurate Dynamic Sparse Training Framework Based on Parameter-Freezing (AAAI 2025 · similarity 0.87)
- SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead (NeurIPS 2024 · similarity 0.87)
- FedMef: Towards Memory-efficient Federated Dynamic Pruning (CVPR 2024 · similarity 0.87)
- FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling (NeurIPS 2025 · similarity 0.86)
- Advancing Dynamic Sparse Training by Exploring Optimization Opportunities (ICML 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
