Bringing Graphs to the Table: Zero-Shot Node Classification via Tabular Foundation Models

ICLR 2026 Conference Submission20236 Authors

Keywords: graph foundation models, node classification, tabular learning

TL;DR: We reformulate node classification as a tabular problem and show tabular foundation models outperform graph-based ones

Abstract:

Graph foundation models (GFMs) have recently emerged as a promising paradigm for achieving broad generalization across various graph data. However, existing GFMs are often trained on datasets that may not fully reflect real-world graphs, limiting their generalization performance.
In contrast, tabular foundation models (TFMs) not only excel at classical tabular prediction tasks but have also shown strong applicability in other domains such as time series forecasting, natural language processing, and computer vision.
Motivated by this, we take an alternative view to the standard perspective of GFMs and reformulate node classification as a tabular problem. In this reformulation, each node is represented as a row with feature, structure, and label information as columns, enabling TFMs to directly perform zero-shot node classification via in-context learning.
In this work, we introduce TAG, a tabular approach for graph learning that first converts a graph into a table via feature and structural encoders, applies multiple TFMs to diversely subsampled tables, and then aggregates their outputs through ensemble selection.
Through experiments on 28 real-world datasets, TAG achieves consistent improvements over task-specific GNNs and state-of-the-art GFMs, highlighting the potential of tabular reformulation for scalable and generalizable graph learning.

Primary Area: learning on graphs and other geometries & topologies

Submission Number: 20236