# Turning Tabular Foundation Models into Graph Foundation Models

## TL;DR

This paper introduces G2T-FM, a framework that adapts tabular foundation models for graph learning by augmenting node features and adding structural information, achieving superior results over existing graph models.

## Contribution

The paper proposes G2T-FM, a novel method to convert tabular foundation models into effective graph foundation models, addressing diverse node feature challenges.

## Key findings

- G2T-FM outperforms existing GFMs and GNNs in various tasks.
- Finetuned G2T-FM surpasses well-tuned GNN baselines.
- Combining G2T-FM with LimiX yields significant performance improvements.

## Abstract

While foundation models have revolutionized such fields as natural language processing and computer vision, their potential in graph machine learning remains largely unexplored. One of the key challenges in designing graph foundation models (GFMs) is handling diverse node features that can vary across different graph datasets. While many works on GFMs have focused exclusively on text-attributed graphs, the problem of handling arbitrary features of other types in GFMs has not been fully addressed. However, this problem is not unique to the graph domain, as it also arises in the field of machine learning for tabular data. In this work, motivated by the recent success of tabular foundation models (TFMs) like TabPFNv2 or LimiX, we propose G2T-FM, a simple framework for turning tabular foundation models into graph foundation models. Specifically, G2T-FM augments the original node features with neighborhood feature aggregation, adds structural embeddings, and then applies a TFM to the constructed node representations. Even in a fully in-context regime, our model achieves strong results, significantly outperforming publicly available GFMs and performing competitively with, and often better than, well-tuned GNNs trained from scratch. Moreover, after finetuning, G2T-FM surpasses well-tuned GNN baselines. In particular, when combined with LimiX, G2T-FM often outperforms the best GNN by a significant margin. In summary, our paper reveals the potential of a previously overlooked direction of utilizing tabular foundation models for graph machine learning tasks.