Research map / Federated learning and privacy / Communication-efficient FL
Re-architecting Personalized Federated Learning for Demanding Edge Environments
Quyang Pan, Sheng Sun, Tingting Wi, Zhiyuan Wu, Yuwei Wang, Min Liu, Bo Gao, Jingyuan Wang
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 |
|---|---|---|---|
| replace logits with distilled data as cached knowledge (DistilCacheFL vs FedCache) | knowledge cache-driven FL · CIFAR-10 (alpha=0.5, homogeneous models) | average user accuracy (%): 42.1 -> 51.1 | Improved |
| replace logits with distilled data as cached knowledge (DistilCacheFL vs FedCache) | knowledge cache-driven FL · CIFAR-100 (alpha=2, homogeneous models) | average user accuracy (%): 14.7 -> 23.3 | Improved |
| increase cache sampling tau from 0 to 0.3 (ablation) | DistilCacheFL · CIFAR-10 (alpha=0.5, homogeneous models) | average user accuracy (%): 51.3 -> 51.7 | Improved |
| increase cache sampling tau toward 1.0 (sample whole cache) (ablation) | DistilCacheFL · CIFAR-10 (alpha=0.5, homogeneous models) | average user accuracy (%): 51.7 -> 48.6 | Hurt |
| use heterogeneous ResNet-S/M/L models instead of homogeneous ResNet-S (ablation) | DistilCacheFL · CIFAR-10 (alpha=0.5) | average user accuracy (%): 46.6 -> 51.1 | Improved |
| use heterogeneous ResNet-S/M/L models instead of homogeneous ResNet-S (ablation) | DistilCacheFL · CIFAR-100 (alpha=0.5) | average user accuracy (%): 31.5 -> 35.8 | Improved |
| use heterogeneous ResNet-S/M/L models instead of homogeneous ResNet-S (ablation) | FedCache · CIFAR-10 (alpha=0.5) | average user accuracy (%): 40.5 -> 41.3 | Improved |
| model heterogeneity vs homogeneity in the baselines FedKD and FedCache | FedCache, FedKD · CIFAR-10 (alpha=2) | average user accuracy (%): FedCache 23.9 -> 22.2 | No clear effect |
Closest papers by meaning
- FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing (AAAI 2024 · similarity 0.87)
- DapperFL: Domain Adaptive Federated Learning with Model Fusion Pruning for Edge Devices (NeurIPS 2024 · similarity 0.87)
- Towards Diverse Device Heterogeneous Federated Learning via Task Arithmetic Knowledge Integration (NeurIPS 2024 · similarity 0.86)
- Resource-Constrained Federated Continual Learning: What Does Matter? (NeurIPS 2025 · similarity 0.85)
- Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data Heterogeneity (AAAI 2024 · similarity 0.85)
- FedSPU: Personalized Federated Learning for Resource-Constrained Devices with Stochastic Parameter Update (AAAI 2025 · 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.
