Research map / Federated learning and privacy / Communication-efficient FL
No One Idles: Efficient Heterogeneous Federated Learning with Parallel Edge and Server Computation
Feilong Zhang, Xianming Liu, Shiyi Lin, Gang Wu, Xiong Zhou, Junjun Jiang, Xiangyang Ji
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 |
|---|---|---|---|
| Swap order so server broadcasts stale global model before aggregation (asynchronous PFL) | FedAvg-style FL with average aggregation · CIFAR-10 i.i.d | speedup per global clock: 3.28x vs FedAvg 1x | Improved |
| Synchronous parallel FL (swap aggregation and broadcast order) | FedAvg · CIFAR-10 i.i.d | accuracy (%): 85.57 vs 85.41 | No clear effect |
| Asynchronous parallel FL | FedAvg · MNIST / CIFAR-10 / Tiny-ImageNet, i.i.d and non-i.i.d | accuracy (%): APFL within about 0.3 of FedAvg on most settings | No clear effect |
| Parallel FL with straggler reconnection time ratio Tw/Tl=5 | FedAvg · CIFAR-10 speedup | speedup: up to 5.56x vs MIFA 3.16x | Improved |
| Parallel FL with distillation-based aggregation | FedAvg with distillation aggregation · CIFAR-10, MNIST, Tiny-ImageNet (local epoch 5/10/15) | speedup and accuracy: speedups 1.32x to 1.97x; accuracy within about 0.1 of FedAvg | Improved |
| Stale global model in parallel FL (early training) | PFL vs FedAvg · CIFAR-10, 20 devices | accuracy convergence: lower accuracy and stronger oscillations early; similar at convergence | Hurt |
| Asynchronous parallel FL (DGA baseline comparison) | Delayed gradient averaging baseline · CIFAR-10 i.i.d | speedup per global clock: 1x for DGA | No clear effect |
| Synchronous parallel FL on MNIST/CIFAR-10/Tiny-ImageNet with stragglers (ablation) | FedAvg · Tw/Tl=3 straggler setting | speedup per global clock: SPFL 1.22x-1.33x vs APFL 2.20x-3.91x | Mixed |
Closest papers by meaning
- Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning (ICML 2025 · similarity 0.88)
- FedLPS: Heterogeneous Federated Learning for Multiple Tasks with Local Parameter Sharing (AAAI 2024 · similarity 0.88)
- Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees (ICLR 2025 · similarity 0.88)
- Efficient Asynchronous Federated Learning with Prospective Momentum Aggregation and Fine-Grained Correction (AAAI 2024 · similarity 0.88)
- Efficient Federated Learning against Heterogeneous and Non-stationary Client Unavailability (NeurIPS 2024 · similarity 0.88)
- Low Precision Local Training is Enough for Federated Learning (NeurIPS 2024 · similarity 0.88)
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.
