AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

T-GINEE: A Tensor-Based Multi-Graph Representation Learning

Maolin Wang, ZiTing Mai, Xuhui Chen, Zhiqi Li, Tianshuo Wei, Yutian Xiao, Wenlin Zhang, Wanyu Wang, Ruocheng Guo, Haoxuan Li, Zenglin Xu, Xiangyu Zhao

ICML 2026 · Graph learning › Graph self-supervised learning · approach: Semi-supervised node representation 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 GEE working-covariance regularization to CP decompositionCP tensor model · Synthetic multilayer networkAUC: 0.4488 -> 0.9395Improved
use T-GINEE instead of best baselinelink prediction · WATAUC: 0.820 -> 0.838Improved
use T-GINEE instead of NMFlink prediction · DBLP (large-scale)AUC: 0.6505 -> 0.6478No clear effect
use T-GINEE instead of SVDlink prediction · Stack OverflowAUC: 0.9682 -> 0.9831Improved
use T-GINEE instead of GCNcommunity detection · PolbooksNMI: 0.021 -> 0.428Improved
use T-GINEE instead of GCNlink prediction · KarateAUC: 0.834 -> 0.817Hurt
use T-GINEE zero-shot instead of retrained MGCNnew-layer link prediction · DBLP-5KAUC: 0.7089 -> 0.7733Improved
add learned working covariance to CP on heterogeneous synthetic layers (ablation)T-GINEE · Synthetic heterogeneous layersAUC: 0.5897 -> 0.5822No clear effect
increase overdetermination ratio (density 3% to 15%, n=500)T-GINEE · Synthetic n=500AUC std: 0.0781 -> 0.0312Improved

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