AI Paper Atlas

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

FedSST: Rethinking Fair Federated Graph Learning under Structural Shift

Dingyi Zhao

CVPR 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated semi-supervised and graph 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
add SSCA to FedAvg baseline (ablation)FedAvg · SMaverage accuracy: 75.04 -> 78.75Improved
add SLTA to FedAvg baseline (ablation)FedAvg · SMaverage accuracy: 75.04 -> 80.07Improved
add SLTA on top of SSCA (ablation)FedSST · SMaverage accuracy: 78.75 -> 82.29Improved
add SLTA on top of SSCA (ablation)FedSST · SM-SN-CVclient accuracy STD: 13.80 -> 13.29Improved
add SLTA alone to FedAvg (ablation)FedAvg · SM-SN-CVaverage accuracy: 74.147 -> 74.98No clear effect
add SSCA alone to FedAvg (ablation)FedAvg · SM-SN-CVaverage accuracy: 74.147 -> 77.36Improved
FedSST vs FedSSP on SM-CVFedSST · SM-CVaverage accuracy: 83.70 -> 82.17Hurt
use SLTA to cut communication roundsFedSST · SM, SM-CV, SM-SN-CVcommunication rounds to converge: 200 -> 100 roundsImproved
tune lambda_reg per setting (20, 25, 30) (ablation)FedSST SLTA · chem, chemcv, chemsncvaccuracy and STDMixed

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