Research map / Federated learning and privacy / Personalized and heterogeneous FL
Factor-Assisted Federated Learning for Personalized Optimization With Heterogeneous Data
Feifei Wang, Huiyun Tang, Yang Li
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 |
|---|---|---|---|
| use dynamic decomposition instead of static decomposition (ablation) | FedFac · CIFAR10 pi=1 | accuracy: 0.7047 -> 0.7153 | Improved |
| use dynamic decomposition instead of static (ablation) | FedFac · CIFAR100 S=30 | accuracy: 0.6107 -> 0.6275 | Improved |
| use dynamic decomposition instead of static (ablation) | FedFac · FEMNIST | accuracy: 0.8139 -> 0.8301 | Improved |
| use dynamic decomposition instead of static (ablation) | FedFac · CIFAR100 S=5 | accuracy: 0.7138 -> 0.7136 | No clear effect |
| use dynamic decomposition instead of static (ablation) | FedFac · CIFAR10 pi=0.1 | accuracy: 0.8307 -> 0.8307 | No clear effect |
| factor-analysis split of shared and personalized neurons instead of FedAvg | FedFac · CIFAR100 S=5 | accuracy: 0.0710 -> 0.7136 | Improved |
| factor-analysis split instead of FedAvg | FedFac · CIFAR10 pi=0.1 | accuracy: 0.8033 -> 0.8307 | Improved |
| factor-analysis split instead of FedEM | FedFac · CIFAR100 S=30 | accuracy: 0.6183 -> 0.6107 | Hurt |
| use Ensemble instead of LocalTrain for new clients (ablation) | FedFac · CIFAR10 new clients pi=0.5 | accuracy: 0.5750 -> 0.7154 | Improved |
| use Ensemble instead of LocalTrain for new clients (ablation) | FedFac · CIFAR10 new clients pi=0.1 | accuracy: 0.6113 -> 0.6410 | Improved |
| random decomposition instead of factor-analysis decomposition (ablation) | FedFac · Simulation | accuracy | Hurt |
| decompose deeper layers (largest Lambda) (ablation) | FedFac · CIFAR100 VGG-16 | accuracy | Improved |
Closest papers by meaning
- pFedClub: Controllable Heterogeneous Model Aggregation for Personalized Federated Learning (NeurIPS 2024 · similarity 0.88)
- Adaptive Latent-Space Constraints in Personalized Federated Learning (NeurIPS 2025 · similarity 0.88)
- Fed-QSSL: A Framework for Personalized Federated Learning under Bitwidth and Data Heterogeneity (AAAI 2024 · similarity 0.88)
- pFedMxF: Personalized Federated Class-Incremental Learning with Mixture of Frequency Aggregation (CVPR 2025 · similarity 0.87)
- FedLMT: Tackling System Heterogeneity of Federated Learning via Low-Rank Model Training with Theoretical Guarantees (ICML 2024 · similarity 0.87)
- A Bayesian Approach for Personalized Federated Learning in Heterogeneous Settings (NeurIPS 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.
