Research map / Federated learning and privacy / Personalized and heterogeneous FL
Submodel Extraction for Efficient and Personalized Federated Learning via Optimal Transport
Zheng Jiang, Nan He, Yiming Chen, Lifeng Sun
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 OT-enhanced aggregation with position-based aggregation (i.e. add OTA) (ablation) | SubFLOT · Digit5 | accuracy (%): 78.74 -> 92.58 | Improved |
| add OTA aggregation (ablation) | SubFLOT · CIFAR10 beta=0.1 | accuracy (%): 81.41 -> 83.78 | Improved |
| add SAR regularization (ablation) | SubFLOT · Digit5 | accuracy (%): 89.73 -> 92.58 | Improved |
| add SAR regularization (ablation) | SubFLOT · CIFAR10 beta=0.1 | accuracy (%): 82.77 -> 83.78 | Improved |
| use OT-based pruning instead of fixed-position pruning (ablation) | SubFLOT · Digit5 | accuracy (%): 90.37 -> 92.58 | Improved |
| use OT-based pruning instead of fixed-position pruning (ablation) | SubFLOT · CIFAR10 beta=0.1 | accuracy (%): 83.21 -> 83.78 | Improved |
| use historical client model as OTP proxy instead of random pruning (ablation) | SubFLOT OTP · CIFAR10 beta=0.1 | accuracy (%): 49.82 -> 83.78 | Improved |
| use historical client model as OTP proxy instead of magnitude pruning (ablation) | SubFLOT OTP · CIFAR10 beta=0.1 | accuracy (%): 77.04 -> 83.78 | Improved |
| increase fusion alpha from 0.5 to 0.7 (ablation) | SubFLOT · CIFAR10 beta=0.1 | accuracy (%): 83.78 -> 84.39 | Improved |
| increase SAR lambda from 1 to 10 (ablation) | SubFLOT · CIFAR10 beta=0.1 | accuracy (%): 83.78 -> 82.93 | Hurt |
| increase SAR lambda from 1 to 5 (ablation) | SubFLOT · CIFAR10 beta=0.1 | accuracy (%): 83.78 -> 83.91 | No clear effect |
| use SubFLOT submodels instead of full-model FedAvg | SubFLOT · VGG11 per-client communication | Comm. (MB): 9.23 -> 4.33 | Improved |
Closest papers by meaning
- FedP3: Federated Personalized and Privacy-friendly Network Pruning under Model Heterogeneity (ICLR 2024 · similarity 0.90)
- FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees (ICML 2024 · similarity 0.90)
- FLUX: Efficient Descriptor-Driven Clustered Federated Learning under Arbitrary Distribution Shifts (NeurIPS 2025 · similarity 0.89)
- A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings (NeurIPS 2024 · similarity 0.89)
- FedRTS: Federated Robust Pruning via Combinatorial Thompson Sampling (NeurIPS 2025 · similarity 0.88)
- FIARSE: Model-Heterogeneous Federated Learning via Importance-Aware Submodel Extraction (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.
