Research map / Federated learning and privacy / Communication-efficient FL
MSCFL: Model Structure-Aware Clustered Federated Learning for System Heterogeneity and Data Drift
Yang Xu, Xiaowei Wu, Zifeng Xu, Cheng Zhang, Ju Ren, Yaoxue Zhang
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 cluster migration strategy (Hamming-distance drift detection) (ablation) | MSCFL · CIFAR-10 under feature/label drift | accuracy | Improved |
| add cluster migration strategy (ablation) | MSCFL · CIFAR100 clustering time | time (s): 3.58 -> 10.18 | Hurt |
| add cluster migration strategy (ablation) | MSCFL · SVHN clustering time | time (s): 0.72 -> 1.08 | Hurt |
| use model-structure similarity (MSCFL) instead of FL+HC on pruned models | MSCFL · CIFAR10 Feature Non-IID | accuracy (%): 54.29 -> 64.38 | Improved |
| use MSCFL vs IFCA under label Non-IID | MSCFL · FMNIST Label Non-IID | accuracy (%): 99.45 -> 99.37 | No clear effect |
| use MSCFL vs IFCA under label Non-IID | MSCFL · CIFAR10 Label Non-IID | accuracy (%): 83.10 -> 91.84 | Improved |
| use structure-masked similarity vs plain shared-part or NXOR similarity when combining CFL with MP (ablation) | MSCFL · CIFAR-10 clustering accuracy | clustering accuracy | Improved |
| MSCFL clustering time vs IFCA | MSCFL · CIFAR100 clustering time | time (s): 82.22 -> 10.18 | Improved |
Closest papers by meaning
- Clustered Federated Learning via Gradient-based Partitioning (ICML 2024 · similarity 0.90)
- Enhancing Clustered Federated Learning: Integration of Strategies and Improved Methodologies (ICLR 2025 · similarity 0.90)
- Cluster Based Heterogeneous Federated Foundation Model Adaptation and Fine-Tuning (AAAI 2025 · similarity 0.88)
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts (NeurIPS 2025 · similarity 0.88)
- FedGPS: Statistical Rectification Against Data Heterogeneity in Federated Learning (NeurIPS 2025 · similarity 0.88)
- One-Shot Heterogeneous Federated Learning with Local Model-Guided Diffusion Models (ICML 2025 · 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.
