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

TL;DR

This paper introduces TabPFN-GN, a method that reformulates node classification as a tabular problem, enabling foundation models to compete with GNNs by extracting features from graph data.

Contribution

The paper presents TabPFN-GN, a novel approach that transforms graph data into tabular features, allowing foundation models to perform node classification without graph-specific training.

Findings

TabPFN-GN achieves competitive results on homophilous graphs.

It outperforms GNNs on heterophilous graphs.

Principled feature engineering bridges tabular and graph domains.

Abstract

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.