# GraphPFN: A Prior-Data Fitted Graph Foundation Model

arXiv: https://arxiv.org/abs/2509.21489 · HTML: https://mlsanity.com/paper/2509.21489/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Builds on 49 of its 73 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 30 of 49)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Benchmarking Graph Neural Networks](https://mlsanity.com/paper/2003.00982/) (2020)
- [TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second](https://mlsanity.com/paper/2207.01848/) (2022)
- [Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1905.07953/) (2019)
- [Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification](https://mlsanity.com/paper/2009.03509/) (2020)
- [Transformers Can Do Bayesian Inference](https://mlsanity.com/paper/2112.10510/) (2021)
- [A critical look at the evaluation of GNNs under heterophily: Are we really making progress?](https://mlsanity.com/paper/2302.11640/) (2023)
- [TabICL: A Tabular Foundation Model for In-Context Learning on Large Data](https://mlsanity.com/paper/2502.05564/) (2025)
- [One for All: Towards Training One Graph Model for All Classification Tasks](https://mlsanity.com/paper/2310.00149/) (2023)
- [The Surprising Power of Graph Neural Networks with Random Node Initialization](https://mlsanity.com/paper/2010.01179/) (2020)
- [Random Features Strengthen Graph Neural Networks](https://mlsanity.com/paper/2002.03155/) (2020)
- [Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks](https://mlsanity.com/paper/1911.07323/) (2019)
- [TabArena: A Living Benchmark for Machine Learning on Tabular Data](https://mlsanity.com/paper/2506.16791/) (2025)
- [Characteristic Functions on Graphs: Birds of a Feather, from Statistical Descriptors to Parametric Models](https://mlsanity.com/paper/2005.07959/) (2020)
- [TabDPT: Scaling Tabular Foundation Models on Real Data](https://mlsanity.com/paper/2410.18164/) (2024)
- [Decoupling the Depth and Scope of Graph Neural Networks](https://mlsanity.com/paper/2201.07858/) (2022)
- [All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretraining](https://mlsanity.com/paper/2402.09834/) (2024)
- [Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classification](https://mlsanity.com/paper/2406.08993/) (2024)
- [GFT: Graph Foundation Model with Transferable Tree Vocabulary](https://mlsanity.com/paper/2411.06070/) (2024)
- [What's Behind the Mask: Understanding Masked Graph Modeling for Graph Autoencoders](https://mlsanity.com/paper/2205.10053/) (2022)

## Built on by (most cited first, 21 of 21)

- [Relational In-Context Learning via Synthetic Pre-training with Structural Prior](https://mlsanity.com/paper/2603.03805/) (2026)
- [No Need to Train Your RDB Foundation Model](https://mlsanity.com/paper/2602.13697/) (2026)
- [TFMLinker: Universal Link Predictor by Graph In-Context Learning with Tabular Foundation Models](https://mlsanity.com/paper/2602.08592/) (2026)
- [OpenRFM: Dissecting Relational In-Context Learning](https://mlsanity.com/paper/2606.04320/) (2026)
- [SurvPFN: Towards Foundation Models for Survival Predictions](https://mlsanity.com/paper/2606.04564/) (2026)
- [A Fair Evaluation of Graph Foundation Models for Node Property Prediction](https://mlsanity.com/paper/2606.24509/) (2026)
- [KGPFN: Unlocking the Potential of Knowledge Graph Foundation Model via In-Context Learning](https://mlsanity.com/paper/2605.14907/) (2026)
- [DeXposure-FM: A Time-series, Graph Foundation Model for Credit Exposures and Stability on Decentralized Financial Networks](https://mlsanity.com/paper/2602.03981/) (2026)
- [Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignment](https://mlsanity.com/paper/2607.11374/) (2026)
- [LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Models](https://mlsanity.com/paper/2609.05955/) (2026)
- [Out-of-Distribution Generalization in Graph Foundation Models](https://mlsanity.com/paper/2601.21067/) (2026)
- [Can Graph Foundation Models Generalize Over Architecture?](https://mlsanity.com/paper/2603.22984/) (2026)
- [PluRel-to-RDB-PFN: Schema-Guided Synthetic Relational Pretraining](https://mlsanity.com/paper/2607.29129/) (2026)
- [Neural Message Passing on Structural Interaction Graphs for Fully-Inductive Graph Neural Networks](https://mlsanity.com/paper/2608.08567/) (2026)
- [GraphFAS: A Distributed System for Automated Graph Feature Generation and Selection in Industrial Transaction Networks](https://mlsanity.com/paper/2609.08970/) (2026)
- [Training Graph Foundation Models on The Web Graph](https://mlsanity.com/paper/2609.30894/) (2026)
- [The Universal Classifier for Graph Learning](https://mlsanity.com/paper/2609.36302/) (2026)
- [Message Passing Does More with Less for In-Context Learning on Graphs](https://mlsanity.com/paper/2609.37057/) (2026)
- [NodeGround: A Node Classification Benchmark in the Graph Foundation Model Era](https://mlsanity.com/paper/2609.39673/) (2026)
- [Valid for Free: Homophily-Gated Conformal Prediction for Training-Free Node Classification with Tabular Foundation Models](https://mlsanity.com/paper/2610.08564/) (2026)
- [Is Real-World Training Data Necessary for Generalist Graph Anomaly Detection?](https://mlsanity.com/paper/2610.12167/) (2026)

## Abstract (arXiv)

Graph foundation models face several fundamental challenges including transferability across diverse domains and data scarcity, which calls into question the very feasibility of creating such models. However, despite similar challenges, the tabular domain has recently witnessed the emergence of the first successful foundation models such as TabPFN. These models are based on the prior-data fitted networks (PFN) framework, in which models are pretrained on carefully designed synthetic datasets to make predictions in an in-context learning setting. Recently, G2T-FM, a framework that converts graph node-level tasks into tabular tasks, has made the first step towards adopting PFNs for graphs, yet it is limited to hand-crafted features and was never pretrained on graph data. In this work, we make the next step by proposing GraphPFN, a PFN-based model designed and pretrained specifically for graph node-level tasks. Following the PFN framework, we first design a prior distribution of synthetic attributed graphs by using a novel combination of multi-level stochastic block models and a preferential attachment process for structure generation and graph-aware structured causal models for attribute generation. Then, we augment the tabular foundation model LimiX with attention-based graph neighborhood aggregation layers and train it on millions of synthetic graphs sampled from our prior. On diverse real-world graph datasets with node-level tasks, GraphPFN achieves state-of-the-art results in both in-context learning and finetuning regimes, outperforming G2T-FM, prior GFMs, and task-specific GNNs trained from scratch. More broadly, GraphPFN shows the potential of PFN-based models for building graph foundation models.