Research map / Federated learning and privacy / Communication-efficient FL
SMoFi: Step-wise Momentum Fusion for Split Federated Learning on Heterogeneous Data
Mingkun Yang, Ran Zhu, Qing Wang, Jie Yang
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 SMoFi step-wise momentum fusion | FedAvg · CIFAR-10 (Dir 0.2) | top-1 accuracy: 77.16 -> 81.82 | Improved |
| add SMoFi | FedAvg · CIFAR-100 (Dir 0.2) | top-1 accuracy: 48.10 -> 53.83 | Improved |
| add SMoFi | FedAvg · Tiny-ImageNet (Dir 0.2) | top-1 accuracy: 33.43 -> 39.73 | Improved |
| add SMoFi | FedProx · Tiny-ImageNet (Dir 0.2) | top-1 accuracy: 34.86 -> 40.79 | Improved |
| add SMoFi instead of FedAvgM/SlowMo/FedNAG | FedAvg · CIFAR-10 (Dir 0.2) | top-1 accuracy: 79.19 (FedAvgM) -> 81.82 | Improved |
| add FedNAG local momentum | FedAvg · Tiny-ImageNet (Dir 0.2) | top-1 accuracy: 33.43 -> 30.94 | Hurt |
| add FedAvgM | FedAvg · Tiny-ImageNet (Dir 0.2) | top-1 accuracy: 33.43 -> 33.58 | No clear effect |
| add SlowMo | FedAvg · CIFAR-10 (Dir 0.2) | top-1 accuracy: 77.16 -> 76.54 | Hurt |
| add SMoFi | FedAvg · Tiny-ImageNet (Dir 0.2) | rounds-to-target speedup: 1.00x -> 10.06x | Improved |
| aggregate SFLV1 server models each step instead of each epoch (ablation) | SFLV1 · CIFAR-10 (Dir 0.2) | top-1 accuracy: 77.84 -> 68.10 | Hurt |
| use smaller staleness factor alpha (e.g. -1) (ablation) | SMoFi · CIFAR-10 | accuracy / convergence | Mixed |
| move cut layer deeper (ablation) | SMoFi · CIFAR-10 | accuracy gain | Mixed |
Closest papers by meaning
- FedWMSAM: Fast and Flat Federated Learning via Weighted Momentum and Sharpness-Aware Minimization (NeurIPS 2025 · similarity 0.90)
- Convergence Analysis of Split Federated Learning on Heterogeneous Data (NeurIPS 2024 · similarity 0.89)
- Momentum Benefits Non-iid Federated Learning Simply and Provably (ICLR 2024 · similarity 0.89)
- Momentum-Driven Adaptivity: Towards Tuning-Free Asynchronous Federated Learning (ICML 2025 · similarity 0.89)
- FedQS: Optimizing Gradient and Model Aggregation for Semi-Asynchronous Federated Learning (NeurIPS 2025 · similarity 0.87)
- On the Role of Server Momentum in Federated Learning (AAAI 2024 · similarity 0.87)
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.
