AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Glance for Context: Learning When to Leverage LLMs for Node-Aware GNN-LLM Fusion

Donald Loveland, Yao-An Yang, Danai Koutra

ICLR 2026 · Graph learning › Graph self-supervised learning · approach: LLMs and graph foundation models

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
Route nodes to the LLM with a learned router instead of using GNN or LLM-enhanced GNN uniformlyGNN backbones · Arxiv23accuracy: 80.2 -> 82.1Improved
Add GLANCE routing on heterophilous nodes (h<0.25)GNN with LLM enhancement · Coraaccuracy by homophily bin: 32.0 -> 46.4Improved
Add GLANCE on Pubmed overallLLM-enhanced GNNs · Pubmedaccuracy: 92.2 -> 92.6Improved
Use uncertainty routing heuristic across datasetsGCN enhanced with LLM routing · Cora vs Pubmednet correction score: Cora -0.09; Pubmed 0.20Mixed
Route by estimated local homophily instead of randomGCN enhanced · Coranet correction score: -0.02 -> -0.07Hurt
Route by estimated local homophily instead of randomGCN enhanced · Pubmednet correction score: 0.06 -> 0.20Improved
Use LOGIN-filtered graphs instead of LLM-enhanced featuresGCN · Arxiv23accuracy: 76.2 -> 65.7Hurt
Increase routing budget K from 8 to 12 to 16 (ablation)GLANCE · Pubmed and Arxiv23, h_v<0.25accuracy: +3.4% then +3.0%Improved
Increase K from 8 to 12 (ablation)GLANCE · Cora, h_v<0.25accuracyHurt
Add the homophily routing feature (vs ablating it) (ablation)GLANCE · Cora, h_v<0.5accuracy: -6.5% when removedImproved
Add all routing features (vs disabling each one) (ablation)GLANCE · Cora, Pubmed, Arxiv23accuracy: -0.38%, -1.07%, -0.65% average dropImproved
Apply GLANCE to large graph at ~6.25% query rateGCNII enhanced · Arxiv-Yearaccuracy: 49.6 -> 49.8Improved

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