AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

Modality-free Graph In-context Alignment

Wei Zhuo, Siqiang Luo

ICLR 2026 · Graph learning › Graph self-supervised learning · approach: LLMs and graph foundation models · 1 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 MF-GIA instead of the second-best baselinefew-shot node classification · Cora 7-way 5-shotaccuracy: 52.64 -> 63.98Improved
use MF-GIA in-context inference instead of fine-tuned GFT/AutoGFMgraph foundation models · node classification (15 configurations)accuracyImproved
add domain-conditioned alignment (domain embedder) vs Prodigygraph ICL · unseen-domain node classificationaccuracy: Cora 5-shot 44.29 -> 63.98Improved
use episodic pretraining and inference instead of supervised pretraining with prototypes (ablation)MF-GIA · Computersaccuracy: 38.73 -> 41.49Improved
use episodic pretraining and inference instead of supervised pretraining with prototypes (ablation)MF-GIA · Physicsaccuracy: 75.26 -> 79.12Improved
add feature alignment, label alignment and DPAA to GraphSAGE+FT (ablation)MF-GIA · node classificationaccuracyImproved
swap GNN backbone (ablation)MF-GIA · 1-shot node classificationaccuracyNo clear effect
apply MF-GIA pretrained on node tasks only to WN18RR 10-way edge classificationMF-GIA · WN18RR 10-wayaccuracy: 35.12 vs 40.02 (AutoGFM) at 5-shotHurt
apply MF-GIA to FB15K237 40-way 1-shotMF-GIA · FB15K237 40-wayaccuracy: 57.17 vs 60.79 (GFT)Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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