AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

ERAlign: Energy-based Representation Alignment of GNNs and LLMs on Text-attributed Graphs

Xianlin Zeng, Fan Xia, Xiangyu Chen

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
align at medium interval {4,12,20,28} instead of output only (ablation)ERAlignGNN · Coraaccuracy (%): 87.14 -> 90.75Improved
use medium instead of sparse alignment interval (ablation)ERAlignGNN · PubMedaccuracy (%): 87.88 -> 92.17Improved
use dense instead of medium alignment interval (ablation)ERAlignGNN · Cora, PubMed, Photoaccuracy (%): Cora 90.75 -> 90.21; PubMed 92.17 -> 92.47Mixed
use Cramer distance with EBM via ED instead of cosine with InfoNCE (ablation)ERAlignGNN · PubMedaccuracy (%): 89.19 -> 92.17Improved
use Cramer distance instead of Euclidean distance (EBM via ED) (ablation)ERAlignGNN · Coraaccuracy (%): 87.32 -> 90.75Improved
use Cramer distance instead of Wasserstein with Sinkhorn OT (ablation)ERAlignGNN · Photoaccuracy (%): 88.40 -> 89.38Improved
train EBM with ED instead of CD (ablation)ERAlignGNN (Cramer) · Coraaccuracy (%): 90.50 -> 90.75Improved
train EBM with ED instead of SM (ablation)ERAlignGNN (Cramer) · Coraaccuracy (%): 88.35 -> 90.75Improved
add w-stabilization (w=0.1) to ED (ablation)ERAlign · Coratraining loss convergenceImproved
increase fusion strength alpha from 0.05 to 0.5 (ablation)ERAlignGNN · Coraaccuracy (%): 87.52 -> 90.75Improved
increase fusion strength alpha from 0.5 to 0.95 (ablation)ERAlignGNN · Coraaccuracy (%): 90.75 -> 89.27Hurt
increase perturbed samples M beyond 8 (ablation)ERAlign · Cora, CiteSeeraccuracyNo clear effect

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