AI Paper Atlas

Research map / Graph learning / GNN architectures

Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors

Jeongwhan Choi, Jongwoo Kim, Woosung Kang, Noseong Park

ICLR 2026 · Graph learning › GNN architectures · approach: GNN generalization theory · 5 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
add the cSBM component to ER-only prior (ablation)NodePFN · Coraaccuracy: 80.62 -> 82.06Improved
add ER graphs to cSBM-only (full range) prior (ablation)NodePFN · Coraaccuracy: 81.26 -> 82.06Improved
train on the full homophily range instead of 0.1-0.3 only (ablation)NodePFN · Coraaccuracy: 79.89 -> 81.26Improved
mix ER and cSBM instead of only BA networks (ablation)NodePFN · Coraaccuracy: 74.18 -> 82.06Improved
mix ER and cSBM instead of only BA networks (ablation)NodePFN · Tolokersaccuracy: 74.63 -> 78.61Improved
mix ER and cSBM instead of only ER (ablation)NodePFN · Wisconsinaccuracy: 80.39 -> 81.18Improved
add graph-aware dual-branch design over TabPFN (average, homophily)NodePFN · 13 homophily graphsaccuracy: 55.62 -> 77.39Improved
add graph-aware dual-branch design over TabPFN (average, heterophily)NodePFN · 10 heterophily graphsaccuracy: 53.47 -> 65.14Improved
use NodePFN instead of GAT on heterophily graphsNodePFN · 10 heterophily graphsaccuracy: 59.11 -> 65.14Improved
use NodePFN instead of GCNNodePFN · 23 benchmarksaccuracy: 66.63 -> 71.27Improved
scale synthetic prior graphs up to about 250,000 (ablation)NodePFN · Texasaccuracy: 53% -> 76%Improved
use NodePFN instead of GraphAny trained on Cora on Wisconsin-type dataNodePFN · Wisconsinaccuracy: 61.18 -> 79.22Improved

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