Research map / Federated learning and privacy / Personalized and heterogeneous FL
FedEMoE: Improving Personalization on Heterogeneous Federated Learning via Elastic Mixture of Experts Architecture
Haizhou Du, Lixin Huang, Zonghan Wu, Huan Huo
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 knowledge exchange between personalized and shared experts (ablation) | FedEMoE · CIFAR-100 (K=50) | accuracy: 43.85 -> 47.69 | Improved |
| add personalized expert group multi-scale extraction (ablation) | FedEMoE · CIFAR-100 (K=50) | accuracy: 35.46 -> 47.69 | Improved |
| add shared experts with elastic EMoE architecture (ablation) | FedEMoE · CIFAR-100 (K=50) | accuracy: 42.25 -> 47.69 | Improved |
| use FedEMoE instead of best baseline FedMRL | HtFL · CIFAR-100 (K=50) | accuracy: 36.01 -> 47.69 | Improved |
| use FedEMoE instead of best baseline FedSA | HtFL · Tiny-ImageNet (K=50) | accuracy: 21.27 -> 29.91 | Improved |
| use FedEMoE instead of best baseline FedMRL | HtFL · CIFAR-10 (K=50) | accuracy: 78.37 -> 79.83 | Improved |
| use FedEMoE instead of FedGC in homogeneous setting | FL · CIFAR-100 homogeneous (K=50) | accuracy: 38.71 -> 47.53 | Improved |
| use FedEMoE instead of FedGC in homogeneous setting | FL · CIFAR-10 homogeneous (K=50) | accuracy: 78.68 -> 79.22 | Improved |
| increase clients from 20 to 100 (ablation) | FedEMoE · CIFAR-100 | accuracy: 49.03 -> 41.76 | Hurt |
| restrict gate to topK=1 instead of topK=2 at N=3 (ablation) | FedEMoE · CIFAR-100 (K=20) | accuracy: 49.03 -> 49.60 | No clear effect |
| increase shared experts from N=3 to N=5 (ablation) | FedEMoE · CIFAR-100 (K=20) | accuracy: 49.03 -> 46.88 | Hurt |
| expansion threshold v0=0.85 rather than 0.95 at gamma=0.07 (ablation) | FedEMoE · CIFAR-100 (K=20) | accuracy: 47.26 -> 49.03 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- FedSA — FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning (AAAI 2025) · better on 3 of 3 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- Towards Personalized Federated Learning via Heterogeneous Model Reassembly (NeurIPS 2023 · similarity 0.87)
- FedEL: Federated Elastic Learning for Heterogeneous Devices (NeurIPS 2025 · similarity 0.87)
- FedSelect: Personalized Federated Learning with Customized Selection of Parameters for Fine-Tuning (CVPR 2024 · similarity 0.87)
- Personalized Federated Learning with First Order Model Optimization (ICLR 2021 · similarity 0.87)
- FedMerge: Federated Model Merging for Personalization (AAAI 2026 · similarity 0.86)
- pFedES: Generalized Proxy Feature Extractor Sharing for Model Heterogeneous Personalized Federated Learning (AAAI 2025 · similarity 0.86)
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.
