AI Paper Atlas

Research map / Federated learning and privacy / Personalized and heterogeneous FL

Heterogeneity-aware Clustered Distributed Learning for Multi-source Data Analysis

Yuanxing Chen, Qingzhao Zhang, Shuangge Ma, Kuangnan Fang

JMLR 2024 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning · 3 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 ICR fused clustering penalty instead of Local per-client fittingICR · Example 1 (p=100, K=64)model size (true 16): 1056.990 -> 16.000Improved
use ICR instead of SK(har) two-step clusteringICR · Example 1 (p=100, K=64)ARI: 0.462 -> 1.000Improved
use ICR instead of SK(gap) two-step clusteringICR · Example 1 (p=100, K=64)FPR: 0.964 -> 0.000Improved
use ICR instead of SK(gap) for clustering accuracyICR · Example 1 (p=100, K=64)ARI: 1.000 -> 1.000No clear effect
use ICR instead of SHIR full poolingICR · Example 1 (p=100, K=64)model size (true 16): 512.670 -> 16.000Improved
increase number of clients K from 16 to 32ICR · Example 1 (p=500)TPR: 0.921 -> 0.999Improved
increase number of clients K from 16 to 64ICR · Example 1 (p=100)FPR: 0.000 -> 0.000No clear effect
increase dimension p from 100 to 500ICR · Example 1 (K=16)TPR: 0.990 -> 0.921Hurt
use Local estimation instead of SHIR integrationLocal · Example 1 (p=100, K=64)TPR: 1.000 -> 0.891Hurt
use ICR instead of SK(har) clusteringICR · Example 1 (p=500, K=16)ARI: 0.570 -> 1.000Improved

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