Graph Foundation Models

Follow this topic Ask about this topic

Momentum

9 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

Jul 13Week of Sep 28

Latest papers 69

All topics

Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors
Apr 21, 2026Jeongwhan Choi, Jongwoo Kim, Woosung Kang +1Synthetic Data Pretraining OOD Generalization
KAIST Daejeon, Republic of Korea
DeXposure-FM: A Time-series, Graph Foundation Model for Credit Exposures and Stability on Decentralized Financial Networks
Feb 3, 2026Aijie Shu, Wenbin Wu, Gbenga Ibikunle +1Financial Services Decentralized Finance
School of Informatics, University of Edinburgh, United Kingdom · Cambridge Centre for Alternative Finance, Judge Business School, University of Cambridge, United Kingdom · Business School, University of Edinburgh, United Kingdom +1
Breaking the Reasoning Horizon in Entity Alignment Foundation Models
Jan 29, 2026Yuanning Cui, Zequn Sun, Wei Hu +2Graph Neural Networks Graph Foundation Models
1Nanjing University of Information Science and Technology · 2State Key Laboratory for Novel Software Technology, Nanjing University · 3National Institute of Healthcare Data Science, Nanjing University, Nanjing +2
KGFR: A Foundation Retriever for Generalized Knowledge Graph Question Answering
Nov 6, 2025Yuanning Cui, Zequn Sun, Wei Hu +1Multi-Hop QA LLM Grounding
School of Computer Science, Nanjing University of Information Science and Technology, Nanjing 210044, China · State Key Laboratory for Novel Software Technology, Nanjing University, Nanjing 210023, China · National Institute of Healthcare Data Science, Nanjing University, Nanjing 210093, China +2
Graph Optimization Foundation Model: Tokenizing Graph via A Language-Model Paradigm
Sep 29, 2025Yunhao Liang, Pujun Zhang, Yuan Qu +3Graph SSL Combinatorial Optimization
Faculty of Engineering, The University of Hong Kong, Hong Kong SAR, China · Costello College of Business, George Mason University, VA, USA · Faculty of Business and Economics, The University of Hong Kong, Hong Kong, China +1
GraphPFN: A Prior-Data Fitted Graph Foundation Model
Sep 25, 2025Dmitry Eremeev, Oleg Platonov, Gleb Bazhenov +2Synthetic Data Pretraining In-Context Learning
1HSE University · 2Yandex Research
Turning Tabular Foundation Models into Graph Foundation Models
Aug 28, 2025Dmitry Eremeev, Gleb Bazhenov, Oleg Platonov +2Graph Foundation Models Node Classification
HSE University · Yandex Research
Relation-Aware Graph Foundation Model
May 17, 2025Jianxiang Yu, Jiapeng Zhu, Yibo Zhao +4Graph Neural Networks Graph Representation Learning
School of Data Science and Engineering, East China Normal University · Ant Group
LLM as GNN: Graph Vocabulary Learning for Text-Attributed Graph Foundation Models
Mar 5, 2025Xi Zhu, Haochen Xue, Ziwei Zhao +7Text-Attributed Graph Learning Graph Foundation Models
1Rutgers University · 2Mohamed bin Zayed University of Artificial Intelligence (MBZUAI) · University of Science and Technology of China +2

Apr 21, 2026, cs.LGJ/K move · Enter open · S save

Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priors

Jeongwhan Choi, Jongwoo Kim, Woosung Kang, Noseong Park

KAIST Daejeon, Republic of Korea

Synthetic Data Pretraining OOD Generalization In-Context Learning Graph Foundation Models Node Classification

Open paper AskPDF arXiv

One of the most challenging problems in graph machine learning is generalizing across graphs with diverse properties. Graph neural networks (GNNs) face a fundamental limitation: they require separate training for each new graph, preventing universal generalization across diverse graph datasets. A critical challenge facing GNNs lies in their reliance on labeled training data for each individual graph, a requirement that hinders the capacity for universal node classification due to the heterogeneity inherent in graphs -- differences in homophily levels, community structures, and feature distributions across datasets. Inspired by the success of large language models (LLMs) that achieve in-context learning through massive-scale pre-training on diverse datasets, we introduce NodePFN. This universal node classification method generalizes to arbitrary graphs without graph-specific training. NodePFN learns posterior predictive distributions (PPDs) by training only on thousands of synthetic graphs generated from carefully designed priors. Our synthetic graph generation covers real-world graphs through the use of random networks with controllable homophily levels and structural causal models for complex feature-label relationships. We develop a dual-branch architecture combining context-query attention mechanisms with local message passing to enable graph-aware in-context learning. Extensive evaluation on 23 benchmarks demonstrates that a single pre-trained NodePFN achieves 71.27 average accuracy. These results validate that universal graph learning patterns can be effectively learned from synthetic priors, establishing a new paradigm for generalization in node classification.

Momentum

Related topics

Latest papers 69