TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second

By Noah Hollmann, Samuel G. Müller, Katharina Eggensperger, Frank Hutter. International Conference on Learning Representations, 2022

840 citations recorded by the source corpus.

We present TabPFN, a trained Transformer that can do supervised classification for small tabular datasets in less than a second, needs no hyperparameter tuning and is competitive with state-of-the-art classification methods. TabPFN performs in-context learning (ICL), it learns to make predictions using sequences of labeled examples (x, f(x)) given in the input, without requiring further parameter updates. TabPFN is fully entailed in the weights of our network, which accepts training and test samples as a set-valued input and yields predictions for the entire test set in a single forward pass. TabPFN is a Prior-Data Fitted Network (PFN) and is trained offline once, to approximate Bayesian inference on synthetic datasets drawn from our prior. This prior incorporates ideas from causal reasoning: It entails a large space of structural causal models with a preference for simple structures. On the 18 datasets in the OpenML-CC18 suite that contain up to 1 000 training data points, up to 100 purely numerical features without missing values, and up to 10 classes, we show that our method clearly outperforms boosted trees and performs on par with complex state-of-the-art AutoML systems with up to 230$\times$ speedup. This increases to a 5 700$\times$ speedup when using a GPU. We also validate these results on an additional 67 small numerical datasets from OpenML. We provide all our code, the trained TabPFN, an interactive browser demo and a Colab notebook at https://github.com/automl/TabPFN.

Subfields: Artificial Intelligence

View Paper: https://www.semanticscholar.org/paper/4c4f0fcf1ce04f12290d8c876abfbe57817de430

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

TabLLM: Few-shot Classification of Tabular Data with Large Language Models (2022, positive): “Lastly, we include TabPFN, a Bayesian neural network that was pre-trained on synthetic tabular data (Hollmann et al., 2022).”
What learning algorithm is in-context learning? Investigations with linear models (2022, background): “ICL has shown impressive results on synthetic tasks and naturalistic language and vision problems (Garg et al., 2022; Min et al., 2022; Zhou et al., 2022; Hollmann et al., 2022).”
Accurate predictions on small data with a tabular foundation model (2025, positive): “5a,b, we show the robustness of TabPFN to dataset characteristics that are traditionally hard to handle for neural-network-based approaches 14,23 .”
NeurIDA: Dynamic Modeling for Effective In-Database Analytics (2025, unknown): “Implementation details could be found in https://github.com/nusdbsystem/NeurIDA.”
pTNAS: Progressive Neural Architecture Search for Tabular Data (2024, unknown): “TabPFN achieves an average normalized score close to the best results, while TabICL ranks among the top despite being limited to classification.”