AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Graph Geometry Interaction Learning

Shichao Zhu, Shirui Pan, Chuan Zhou, Jia Wu, Yanan Cao, Bin Wang

NeurIPS 2020 · Graph learning › Graph self-supervised learning · approach: Heterophily and imbalance on graphs · 21 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
geometry interaction learning (GIL) instead of simple concatenation of Euclidean and hyperbolic embeddings (EucHyp) (ablation)Euclidean+hyperbolic GNN · Citeseer node classificationaccuracy: 68.89 -> 72.97Improved
GIL instead of EucHyp (ablation)Euclidean+hyperbolic GNN · Cora link predictionROC AUC: 93.63 -> 98.28Improved
GIL instead of EucHyp (ablation)Euclidean+hyperbolic GNN · Disease link predictionROC AUC: 97.91 -> 99.90Improved
GIL instead of HGCNhyperbolic GNN · Citeseer link predictionROC AUC: 96.63 -> 99.85Improved
GIL instead of GATEuclidean GNN · Disease node classificationF1: 70.40 -> 90.70Improved
add dual feature fusion between Euclidean and hyperbolic spaces (vs none or one direction) (ablation)GIL · node classificationaccuracyImproved
add hyperbolic-distance-aware attention in hyperbolic message propagation (ablation)GIL · node classification (all datasets)accuracyImproved

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