AI Paper Atlas

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

ICML 2022 · Federated learning and privacy › Communication-efficient FL · approach: Communication-efficient heterogeneous FL · 45 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use personalized sparse masks and decentralized sparse trainingDis-PFL · CIFAR-10 Dir Partaccuracy: 83.90$\pm$0.2 -> 85.70$\pm$0.2Improved
Use personalized sparse masks and decentralized sparse trainingDis-PFL · CIFAR-10 Path Partaccuracy: 90.87$\pm$0.2 -> 91.05$\pm$0.2Improved
Use personalized sparse masks and decentralized sparse trainingDis-PFL · CIFAR-100 Dir Partaccuracy: 51.42$\pm$0.4 -> 53.48$\pm$0.3Improved
Use personalized sparse masks and decentralized sparse trainingDis-PFL · CIFAR-100 Path Partaccuracy: 67.24$\pm$0.1 -> 68.64$\pm$0.4Improved
Use personalized sparse masks and decentralized sparse trainingDis-PFL · Tiny-Imagenet Dir Partaccuracy: 15.69$\pm$0.2 -> 16.95$\pm$0.4Improved
Use personalized sparse masks and decentralized sparse trainingDis-PFL · Tiny-Imagenet Path Partaccuracy: 28.60$\pm$0.3 -> 31.71$\pm$0.4Improved
Increase sparsity from 0.5 to 0.8 (ablation)Dis-PFL · CIFAR-10 Dir Partaccuracy: 85.70 -> 83.27Hurt
Increase sparsity from 0.5 to 0.6 (ablation)Dis-PFL · CIFAR-10 Dir Partaccuracy: 85.70 -> 84.08Hurt
Decrease sparsity from 0.5 to 0.4 (ablation)Dis-PFL · CIFAR-10 Dir Partaccuracy: 85.70 -> 84.22Hurt
Decrease sparsity from 0.5 to 0.2 (ablation)Dis-PFL · CIFAR-10 Dir Partaccuracy: 85.70 -> 84.10Hurt
Increase sparsity from 0.5 to 0.8 (ablation)Dis-PFL · CIFAR-10 Dir Partcommunication cost (MB): 223.4 -> 89.30Improved

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.

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.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy