AI Paper Atlas

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

Powerful and Theoretically Guaranteed Independence Testing on Heterogeneous Federated Clients

Yixin Ren, Hongquan Liu, Juncai Zhang, Yewei Xia, Zichuan Lin, Deheng Ye, Hao Zhang, Jihong Guan, Shuigeng Zhou

ICML 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Non-IID federated learning

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
replace FUIT's naive feature-space aggregation with copula alignment plus stacking aggregationFedIT-CS · synthetic Cov and Freq heterogeneous clientstest powerImproved
use sample splitting to learn aggregation weights (ablation)FedIT-CS-M / FedIT-CS-ML · synthetic datasetstest powerHurt
use mixed linear aggregation (soft client weights) instead of exhaustive subset selection (ablation)FedIT-CS · synthetic datasetstest powerImproved
apply FedIT-CS variants instead of FUIT on real dataFedIT-CS · Sachs dataset (3 of 7 clients)Type I and Type II errorImproved
use CCA largest canonical correlation instead of Frobenius norm over all eigenvaluesFedIT-CS · heterogeneous clients with opposite correlationsdependence signalImproved
all methods control Type I error in synthetic testsall methods · synthetic datasetsType I errorNo clear effect

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