Research map / Federated learning and privacy / Communication-efficient FL
Decentralized Federated Learning With Distributed Aggregation Weight Optimization
Zhiyuan Zhai, Xiaojun Yuan, Xin Wang, 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 the distance-decay exponent v from 2 to 10 (links more reliable) | Proposed weight optimization · MNIST DFL, M=40, r=2 | optimized rho(W-bar): 0.54 -> 0.15 | Improved |
| use distributed subgradient optimization instead of centralized optimization | Proposed weight optimization · FashionMNIST, M=200, r=4, v=2 | average and minimum test accuracy | No clear effect |
| optimize weights versus equal weights ignoring link reliability (ablation) | DFL aggregation weights · FashionMNIST, M=200, r=4, v=2 | test accuracy | Improved |
| optimize weights versus Metropolis-Hastings heuristic weights (ablation) | DFL aggregation weights · FashionMNIST, M=200, r=4, v=2 | test accuracy | Improved |
| lower rho(W-bar) of the aggregation matrix (ablation) | DFL on MNIST · MNIST, M=40 | average and minimum test accuracy | Improved |
| use dynamic (re-randomized positions) instead of static link reliability | Proposed weight optimization · MNIST, M=40, varying r and v | minimum and average test accuracy | Improved |
| increase link unreliability parameter r | Proposed weight optimization · MNIST, M=40 | convergence time of rho(W-bar) | Hurt |
Closest papers by meaning
- Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees (ICLR 2025 · similarity 0.89)
- FedAWA: Adaptive Optimization of Aggregation Weights in Federated Learning Using Client Vectors (CVPR 2025 · similarity 0.87)
- NTK-DFL: Enhancing Decentralized Federated Learning in Heterogeneous Settings via Neural Tangent Kernel (ICML 2025 · similarity 0.86)
- SemiDFL: A Semi-Supervised Paradigm for Decentralized Federated Learning (AAAI 2025 · similarity 0.86)
- Competitive Advantage Attacks to Decentralized Federated Learning (NeurIPS 2025 · similarity 0.85)
- Pursuing Overall Welfare in Federated Learning through Sequential Decision Making (ICML 2024 · 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.
