Research map / Federated learning and privacy / Communication-efficient FL
DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training
Rong Dai, Li Shen, Fengxiang He, Xinmei Tian, Dacheng Tao
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 personalized sparse masks and decentralized sparse training | Dis-PFL · CIFAR-10 Dir Part | accuracy: 83.90$\pm$0.2 -> 85.70$\pm$0.2 | Improved |
| Use personalized sparse masks and decentralized sparse training | Dis-PFL · CIFAR-10 Path Part | accuracy: 90.87$\pm$0.2 -> 91.05$\pm$0.2 | Improved |
| Use personalized sparse masks and decentralized sparse training | Dis-PFL · CIFAR-100 Dir Part | accuracy: 51.42$\pm$0.4 -> 53.48$\pm$0.3 | Improved |
| Use personalized sparse masks and decentralized sparse training | Dis-PFL · CIFAR-100 Path Part | accuracy: 67.24$\pm$0.1 -> 68.64$\pm$0.4 | Improved |
| Use personalized sparse masks and decentralized sparse training | Dis-PFL · Tiny-Imagenet Dir Part | accuracy: 15.69$\pm$0.2 -> 16.95$\pm$0.4 | Improved |
| Use personalized sparse masks and decentralized sparse training | Dis-PFL · Tiny-Imagenet Path Part | accuracy: 28.60$\pm$0.3 -> 31.71$\pm$0.4 | Improved |
| Increase sparsity from 0.5 to 0.8 (ablation) | Dis-PFL · CIFAR-10 Dir Part | accuracy: 85.70 -> 83.27 | Hurt |
| Increase sparsity from 0.5 to 0.6 (ablation) | Dis-PFL · CIFAR-10 Dir Part | accuracy: 85.70 -> 84.08 | Hurt |
| Decrease sparsity from 0.5 to 0.4 (ablation) | Dis-PFL · CIFAR-10 Dir Part | accuracy: 85.70 -> 84.22 | Hurt |
| Decrease sparsity from 0.5 to 0.2 (ablation) | Dis-PFL · CIFAR-10 Dir Part | accuracy: 85.70 -> 84.10 | Hurt |
| Increase sparsity from 0.5 to 0.8 (ablation) | Dis-PFL · CIFAR-10 Dir Part | communication cost (MB): 223.4 -> 89.30 | Improved |
Later papers that compared with this method
1 later accepted paper reports DisPFL as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.
- DecFus: Decentralized Layer-wise Fusion with Dynamic Exploration and Exploitation (ICML 2026 · better on 3 of 3 shared results)
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.
- Ditto — Ditto: Fair and Robust Federated Learning Through Personalization (ICML 2021) · better on 1 of 1 shared result
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 Directed Collaboration for Personalized Federated Learning (CVPR 2024 · similarity 0.92)
- SpaFL: Communication-Efficient Federated Learning With Sparse Models And Low Computational Overhead (NeurIPS 2024 · similarity 0.91)
- Understanding the Statistical Accuracy-Communication Trade-off in Personalized Federated Learning with Minimax Guarantees (ICML 2025 · similarity 0.90)
- PeFLL: Personalized Federated Learning by Learning to Learn (ICLR 2024 · similarity 0.90)
- Low Precision Local Training is Enough for Federated Learning (NeurIPS 2024 · similarity 0.89)
- SparsyFed: Sparse Adaptive Federated Learning (ICLR 2025 · similarity 0.89)
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.
