AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Learning Graph Foundation Models on Riemannian Graph-of-Graphs

Haokun Liu, Zezhong Ding, Xike Xie

ICML 2026 · Graph learning › Graph self-supervised learning · approach: LLMs and graph foundation models · 0 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
use R-GFM instead of the strongest baselineGFM · Citeseer node classificationrelative improvement: 18.9% improvement on CiteseerImproved
add 50% edge drop robustness (R-GFM vs strongest baseline)R-GFM · edge drop p=0.5accuracy: 46.91% (drop of 5.76) vs around 41.2%Improved
mask 50% of node attributes (R-GFM vs strongest baseline)R-GFM · node masking r=0.5accuracy: 46.84% vs 41.78%Improved
add GoG construction (vs Stage-1 only, w/o GoG pooling, chain-edge GoG) (ablation)R-GFM · Photo, Cora, Chameleon, Texas 1-shotaccuracyImproved
use Riemannian encoder instead of Euclidean on GoG (ablation)R-GFM · Photo, Cora, Chameleon, Texas 1-shotaccuracyImproved
use mixture of manifolds instead of hyperbolic only or hyperspherical only (ablation)R-GFM · Photo, Cora, Chameleon, Texas 1-shotaccuracyImproved
increase hop number KGCOPE extended to K-hop · cross-domain 1-shot node classificationaccuracyNo clear effect
increase hop number KR-GFM · cross-domain 1-shot node classificationaccuracyImproved
use subgraph sampling instead of full-graph trainingR-GFM vs SAMGPT and MDGFM · large LM-feature graphsmemory / accuracy: OOM for SAMGPT and MDGFMImproved
set GoG edge retention ratio beta near 0.6 (ablation)R-GFM · four datasets 1-shotaccuracy: peaks around beta 0.6Improved
use dynamic top-m gating instead of fixed m in 1..5 (ablation)R-GFM · four datasets 1-shotaccuracyImproved
use dynamic candidate expert set instead of manual expert number (ablation)R-GFM · 10-dataset settingaccuracyImproved

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