Accurate predictions on small data with a tabular foundation model

By Noah Hollmann, Samuel G. Müller, Lennart Purucker, Arjun Krishnakumar, Max Körfer, Shi Bin Hoo, Robin Tibor Schirrmeister, Frank Hutter. Nature, 2025

1,171 citations recorded by the source corpus.

Tabular data, spreadsheets organized in rows and columns, are ubiquitous across scientific fields, from biomedicine to particle physics to economics and climate science1,2. The fundamental prediction task of filling in missing values of a label column based on the rest of the columns is essential for various applications as diverse as biomedical risk models, drug discovery and materials science. Although deep learning has revolutionized learning from raw data and led to numerous high-profile success stories3, 4–5, gradient-boosted decision trees6, 7, 8–9 have dominated tabular data for the past 20 years. Here we present the Tabular Prior-data Fitted Network (TabPFN), a tabular foundation model that outperforms all previous methods on datasets with up to 10,000 samples by a wide margin, using substantially less training time. In 2.8 s, TabPFN outperforms an ensemble of the strongest baselines tuned for 4 h in a classification setting. As a generative transformer-based foundation model, this model also allows fine-tuning, data generation, density estimation and learning reusable embeddings. TabPFN is a learning algorithm that is itself learned across millions of synthetic datasets, demonstrating the power of this approach for algorithm development. By improving modelling abilities across diverse fields, TabPFN has the potential to accelerate scientific discovery and enhance important decision-making in various domains. Tabular Prior-data Fitted Network, a tabular foundation model, provides accurate predictions on small data and outperforms all previous methods on datasets with up to 10,000 samples by a wide margin.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/6b238b17e419c7dd3912b9845449496bfb0a571a

Citations in the corpus

• A Fair Benchmarking of Deep Relational Database Learning Models (2026, unknown): “TabPFN 2.5, which was pretrained on 130 million synthetic datasets [13], may have seen comparable distributional structures during this pretraining, which could give TabPFN 2.5 an advantage over this specific regression task.”
• Griffin: Towards a Graph-Centric Relational Database Foundation Model (2025, unknown): “We also conducted few-shot experiments compared with TabPFNv2 combined with DFS as a reference, as detailed in Appendix E. TabPFNv2 (Hollmann et al., 2025) is a powerful single-table model that supports few-shot learning and even outperforms some state-of-the-art models on certain datasets.”