Research map / Federated learning and privacy / Communication-efficient FL
Boosting the Performance of Decentralized Federated Learning via Catalyst Acceleration
Qinglun Li, Miao Zhang, Yingqi Liu, Quanjun Yin, Li Shen, Xiaochun Cao
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 Nesterov acceleration at aggregation (ablation) | DFedCata with Moreau envelope · CIFAR-10 Dir 0.3 | top-1 accuracy: 77.17 -> 82.88 | Improved |
| add Moreau envelope (ablation) | DFedCata with Nesterov acceleration · CIFAR-10 Dir 0.3 | top-1 accuracy: 82.42 -> 82.88 | Improved |
| add Moreau envelope alone (ablation) | baseline without both · CIFAR-10 Dir 0.3 | top-1 accuracy: 77.25 -> 77.17 | No clear effect |
| increase catalyst parameter beta from 0 to 0.99 (ablation) | DFedCata · CIFAR-10 Dir 0.3 | top-1 accuracy: 77.17 -> 81.69 | Improved |
| increase catalyst parameter beta from 0 to 0.99 (ablation) | DFedCata · CIFAR-10 Dir 0.3 | rounds to 75% accuracy: 211 -> 75 | Improved |
| use lambda = 0.05 for penalty (ablation) | DFedCata · CIFAR-10 Dir 0.3 | top-1 accuracy | Improved |
| use K = 5 local epochs instead of larger K (ablation) | DFedCata · CIFAR-10 Dir 0.3 | top-1 accuracy | Mixed |
| use 50 or 100 clients rather than 200 (ablation) | DFedCata · CIFAR-10 Dir 0.3 | top-1 accuracy | Mixed |
| use DFedCata instead of DFedSAM on ring topology | decentralized FL · CIFAR-10 Dir 0.3, ring | top-1 accuracy: 65.12 -> 72.22 | Improved |
| use DFedCata instead of DFedSAM | decentralized FL · CIFAR-100 Path 10 | top-1 accuracy: 47.98 -> 54.70 | 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.
- SCAFFOLD — SCAFFOLD: Stochastic Controlled Averaging for Federated Learning (ICML 2020) · better on 2 of 2 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
- Decentralized Sporadic Federated Learning: A Unified Algorithmic Framework with Convergence Guarantees (ICLR 2025 · similarity 0.91)
- Decentralized Directed Collaboration for Personalized Federated Learning (CVPR 2024 · similarity 0.89)
- Overcoming Data and Model heterogeneities in Decentralized Federated Learning via Synthetic Anchors (ICML 2024 · similarity 0.89)
- SemiDFL: A Semi-Supervised Paradigm for Decentralized Federated Learning (AAAI 2025 · similarity 0.89)
- Exact and Linear Convergence for Federated Learning under Arbitrary Client Participation is Attainable (NeurIPS 2025 · similarity 0.87)
- Communication-Efficient Federated Learning with Accelerated Client Gradient (CVPR 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.
