mlsanityData to 7 Oct 2026

Can TabPFN Compete with GNNs for Node Classification via Graph Tabularization?

arXiv 2512.08798 ↗First posted 9 Dec 2025cs.LG cs.AIcited by 8

Not on the map. Why?

Abstract (arXiv)

Foundation models pretrained on large data have demonstrated remarkable zero-shot generalization capabilities across domains. Building on the success of TabPFN for tabular data and its recent extension to time series, we investigate whether graph node classification can be effectively reformulated as a tabular learning problem. We introduce TabPFN-GN, which transforms graph data into tabular features by extracting node attributes, structural properties, positional encodings, and optionally smoothed neighborhood features. This enables TabPFN to perform direct node classification without any graph-specific training or language model dependencies. Our experiments on 12 benchmark datasets reveal that TabPFN-GN achieves competitive performance with GNNs on homophilous graphs and consistently outperforms them on heterophilous graphs. These results demonstrate that principled feature engineering can bridge the gap between tabular and graph domains, providing a practical alternative to task-specific GNN training and LLM-dependent graph foundation models.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 41 of its 49 references that are in the map. First posted on arXiv 9 Dec 2025.

Builds on

41 of 49 references.

References · 41

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2017Graph Attention Networkscited by 8,854
  4. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
  5. 2017Inductive Representation Learning on Large Graphscited by 6,284
  6. 2019BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehensioncited by 5,874
  7. 2018How Powerful are Graph Neural Networks?cited by 4,355
  8. 2019ALBERT: A Lite BERT for Self-supervised Learning of Language Representationscited by 2,772
  9. 2019Simplifying Graph Convolutional Networkscited by 1,470
  10. 2020Geom-GCN: Geometric Graph Convolutional Networkscited by 821
  11. 2020TUDataset: A collection of benchmark datasets for learning with graphscited by 718
  12. 2022Recipe for a General, Powerful, Scalable Graph Transformercited by 702
29 more
  1. 2023A decoder-only foundation model for time-series forecastingcited by 650
  2. 2022TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Secondcited by 643
  3. 2020Adaptive Universal Generalized PageRank Graph Neural Networkcited by 592
  4. 2019Multi-scale Attributed Node Embeddingcited by 543
  5. 2020Principal Neighbourhood Aggregation for Graph Netscited by 477
  6. 2023A critical look at the evaluation of GNNs under heterophily: Are we really making progress?cited by 332
  7. 2021OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphscited by 328
  8. 2023One for All: Towards Training One Graph Model for All Classification Taskscited by 239
  9. 2023GraphGPT: Graph Instruction Tuning for Large Language Modelscited by 223
  10. 2023Language is All a Graph Needscited by 219
  11. 2023Sequential Modeling Enables Scalable Learning for Large Vision Modelscited by 212
  12. 2023Exphormer: Sparse Transformers for Graphscited by 166
  13. 2023Harnessing Explanations: LLM-to-LM Interpreter for Enhanced Text-Attributed Graph Representation Learningcited by 132
  14. 2023GraphText: Graph Reasoning in Text Spacecited by 110
  15. 2025TiRex: Zero-Shot Forecasting Across Long and Short Horizons with Enhanced In-Context Learningcited by 107
  16. 2023GraphLLM: Boosting Graph Reasoning Ability of Large Language Modelcited by 105
  17. 2024Moirai-MoE: Empowering Time Series Foundation Models with Sparse Mixture of Expertscited by 88
  18. 2024All in One and One for All: A Simple yet Effective Method towards Cross-domain Graph Pretrainingcited by 84
  19. 2024Classic GNNs are Strong Baselines: Reassessing GNNs for Node Classificationcited by 83
  20. 2024Polynormer: Polynomial-Expressive Graph Transformer in Linear Timecited by 64
  21. 2022GREAD: Graph Neural Reaction-Diffusion Networkscited by 54
  22. 2024AnyGraph: Graph Foundation Model in the Wildcited by 51
  23. 2025From Tables to Time: Extending TabPFN-v2 to Time Series Forecastingcited by 49
  24. 2024Text-space Graph Foundation Models: Comprehensive Benchmarks and New Insightscited by 44
  25. 2024Fully-inductive Node Classification on Arbitrary Graphscited by 36
  26. 2024GLBench: A Comprehensive Benchmark for Graph with Large Language Modelscited by 36
  27. 2025Turning Tabular Foundation Models into Graph Foundation Modelscited by 30
  28. 2025Equivariance Everywhere All At Once: A Recipe for Graph Foundation Modelscited by 17
  29. 2024Sequential Signal Mixing Aggregation for Message Passing Graph Neural Networkscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 8.

8 papers.

  1. 2026Learning Posterior Predictive Distributions for Node Classification from Synthetic Graph Priorscited by 10
  2. 2026No Need to Train Your RDB Foundation Modelcited by 8
  3. 2026A Fair Evaluation of Graph Foundation Models for Node Property Predictioncited by 4
  4. 2026Fixed Aggregation Features Can Rival GNNscited by 2
  5. 2026Surprisingly Simple and Effective Multi-Domain Graph Foundation Model through Graph-to-Table Alignmentcited by 1
  6. 2026LoGIC: Budgeted Context Construction for Node-Level Graph In-Context Learning with Tabular Foundation Modelscited by 0
  7. 2026GraphFAS: A Distributed System for Automated Graph Feature Generation and Selection in Industrial Transaction Networkscited by 0
  8. 2026Training Graph Foundation Models on The Web Graphcited by 0