Research map / Federated learning and privacy / Communication-efficient FL
Decentralized Federated Learning by Partial Message Exchange
Shan Sha, Shenglong Zhou, Xin Wang, Lingchen Kong, Geoffrey Ye 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 |
|---|---|---|---|
| increase transmission ratio s from 0.1 to 0.6 (ablation) | PaME · Linear regression, m=1000 | MSE: 0.462 -> 0.015 | Improved |
| increase transmission ratio s from 0.1 to 0.6 (ablation) | PaME · Linear regression, m=2000 | MSE: 0.136 -> 0.011 | Improved |
| increase transmission ratio s from 0.1 to 0.6 (ablation) | PaME · Linear regression, m=1000 | iterations to MSE 0.5: 96 -> 39 | Improved |
| increase participation rate v from 0.1 to 0.6 (ablation) | PaME · Linear regression, m=1000 | MSE: 0.136 -> 0.011 | Improved |
| increase participation rate v from 0.1 to 0.6 (ablation) | PaME · Linear regression, m=2000 | iterations to MSE 0.5: 45 -> 28 | Improved |
| increase number of nodes m from 1000 to 2000 at s=0.1 (ablation) | PaME · Linear regression | MSE: 0.462 -> 0.136 | Improved |
| raise transmission rate s/n above 0.2 (ablation) | PaME · Linear regression, m in {32,64,128} | final objective | No clear effect |
| raise participation rate beyond 0.2 (ablation) | PaME · Linear regression, m in {32,64,128} | convergence speed | No clear effect |
| shorten communication period (homogeneous kappa) (ablation) | PaME · Linear regression | final objective | No clear effect |
| use heterogeneous instead of homogeneous communication periods (ablation) | PaME · Linear regression | convergence speed | Hurt |
| increase number of nodes m (ablation) | PaME · Linear regression | convergence speed | Improved |
| use partial message exchange (PaME) versus D-PSGD, DFedSAM, BEER, ANQ-NIDS | PaME · Fashion-MNIST, CIFAR-10, Tiny-ImageNet | accuracy | Improved |
Closest papers by meaning
- Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees (ICLR 2025 · similarity 0.90)
- SemiDFL: A Semi-Supervised Paradigm for Decentralized Federated Learning (AAAI 2025 · similarity 0.88)
- Decentralized Directed Collaboration for Personalized Federated Learning (CVPR 2024 · similarity 0.87)
- Overcoming Data and Model heterogeneities in Decentralized Federated Learning via Synthetic Anchors (ICML 2024 · similarity 0.86)
- NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel (ICML 2025 · similarity 0.86)
- Achieving Dimension-Free Communication in Federated Learning via Zeroth-Order Optimization (ICLR 2025 · similarity 0.85)
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.
