AI Paper Atlas

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

Federated Graph-level Clustering Network with Attribute Inference

Renda Han, Junlong Wu, Wenxuan Tu, Jingxin Liu, Haotian Wang, Jieren Cheng

AAAI 2026 · Federated learning and privacy › Personalized and heterogeneous FL · approach: Federated semi-supervised and graph learning · 2 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
enable KAIS attribute inference and kernel-aware aggregation (ablation)FedAI · SM (7 clients)ACC: 54.3 -> 78.6Improved
enable KAIS attribute inference (ablation)FedAI · SN-SY (2 clients)ACC: 8.7 -> 24.6Improved
FedAI instead of FedGCNfederated graph-level clustering · SM-BIO (9 clients)ACC: 69.2 -> 73.2Improved
FedAI instead of FedGCNfederated graph-level clustering · CV (3 clients)NMI: 31.8 -> 33.3No clear effect
FedAI instead of FedGCN with 16 clientsfederated graph-level clustering · 16 clients, larger-scaleACC: 65.3 -> 72.3Improved
use personalized affinity-based aggregation instead of FedAvg (ablation)FedAI · SM (7 clients)ACC: 76.0 -> 78.6Improved
use personalized affinity-based aggregation instead of FedProx (ablation)FedAI · SM-BIO-SY (10 clients)ACC: 70.8 -> 72.3Improved
use HRW graph kernel instead of SP, LT, RW, WL kernels (ablation)FedAI · two non-IID settingsclustering metricsImproved
increase proportion gamma of uploaded samples (ablation)FedAI · non-IID settingsclustering metricsMixed

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