Methods › General › Deep Tabular Learning › TABPFN
tabular data Prior-data Fitted Network
TABPFN
Introduced by Noah Hollmann et al. in TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second
archive 2025-07-28 Description, source and code snippet are the archive's method entry.
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 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× speedup. This increases to a 5 700× 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.
In Syntology about another paper, arXiv:2608.30337: no code under this name (no_code; paper_only). The lookup matched 'TabPFN' ignoring case. About another paper: this answer is about arXiv:2608.30337, while the archive credits arXiv:2207.01848, so it does not say whether this method has code.
From the lookup's note on this name: The same name also belongs to the paper “TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second” (arXiv:2207.01848, 912 citations), which the lookup finds cited far more than the paper this answer is about (citations not recorded), so this answer may be about a different sense of the name. For arXiv:2207.01848: its page on this site · ask the lookup about it.
Origin paper of this answer, arXiv:2608.30337 (its page on Syntology).
Syntology's have check for this name (free, it answers coverage only), read 2026-10-05; ask it again live. A level is the served verification level of that one answer; nothing here is summed across methods.
Papers archive 2025-07-28
archive papers tagged: 26 · with a code link: 12 · where Syntology ran a sample: 9 (9 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (9 of 26 tagged: 9 with a run with no instrument failure, 0 where every run was a failure of Syntology's instrument)
Page 1 of 1: papers 1 to 26 of 26, newest first by the archive's date (ties by slug), in archive order.
Repository counts are the archive's code-links table. A Syntology line states what Syntology ran from that paper's harvested code, as “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. It is per sample and not a correctness claim. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from.
-
ConTextTab: A Semantics-Aware Tabular In-Context Learner 12 Jun 2025 · 1 repository · arXiv:2506.10707Syntology official (archive's flag): 1 ran · 3 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified (of 6 harvested samples)
-
On the Robustness of Tabular Foundation Models: Test-Time Attacks and In-Context Defenses 3 Jun 2025 · 0 repositories · arXiv:2506.02978
-
TabPFN: One Model to Rule Them All? 26 May 2025 · 1 repository · arXiv:2505.20003
-
Realistic Evaluation of TabPFN v2 in Open Environments 22 May 2025 · 0 repositories · arXiv:2505.16226
-
Tabular foundation model to detect empathy from visual cues 15 Apr 2025 · 0 repositories · arXiv:2504.10808
-
A Closer Look at TabPFN v2: Strength, Limitation, and Extension 24 Feb 2025 · 0 repositories · arXiv:2502.17361
-
TabPFN Unleashed: A Scalable and Effective Solution to Tabular Classification Problems 4 Feb 2025 · 0 repositories · arXiv:2502.02527
-
Transformers Boost the Performance of Decision Trees on Tabular Data across Sample Sizes 4 Feb 2025 · 1 repository · arXiv:2502.02672
-
The Tabular Foundation Model TabPFN Outperforms Specialized Time Series Forecasting Models Based on Simple Features 6 Jan 2025 · 1 repository · arXiv:2501.02945Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 5 harvested samples)
-
Drift-Resilient TabPFN: In-Context Learning Temporal Distribution Shifts on Tabular Data 15 Nov 2024 · 0 repositories · arXiv:2411.10634
-
A Survey on Deep Tabular Learning 15 Oct 2024 · 0 repositories · arXiv:2410.12034
-
AnnotatedTables: A Large Tabular Dataset with Language Model Annotations 24 Jun 2024 · 0 repositories · arXiv:2406.16349
-
Large Scale Transfer Learning for Tabular Data via Language Modeling 17 Jun 2024 · 2 repositories · arXiv:2406.12031Syntology official (archive's flag): 13 ran · 13 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 10 where Syntology's instrument failed) · 2 unverified (of 15 harvested samples)
-
Grapevine Disease Prediction Using Climate Variables from Multi-Sensor Remote Sensing Imagery via a Transformer Model 11 Jun 2024 · 0 repositories · arXiv:2406.07094
-
Tokenize features, enhancing tables: the FT-TABPFN model for tabular classification 11 Jun 2024 · 0 repositories · arXiv:2406.06891
-
Retrieval & Fine-Tuning for In-Context Tabular Models 7 Jun 2024 · 0 repositories · arXiv:2406.05207
-
TabPFGen -- Tabular Data Generation with TabPFN 7 Jun 2024 · 1 repository · arXiv:2406.05216
-
Fine-tuned In-Context Learning Transformers are Excellent Tabular Data Classifiers 22 May 2024 · 1 repository · arXiv:2405.13396Syntology official (archive's flag): 4 ran · 4 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples)
-
Interpretable Machine Learning for TabPFN 16 Mar 2024 · 1 repository · arXiv:2403.10923Syntology official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 7 where Syntology's instrument failed) · 0 unverified (of 12 harvested samples) · 1 pointer-only (licence)
-
TuneTables: Context Optimization for Scalable Prior-Data Fitted Networks 17 Feb 2024 · 2 repositories · arXiv:2402.11137Syntology official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 7 where Syntology's instrument failed) · 5 unverified (of 17 harvested samples)
-
In-Context Data Distillation with TabPFN 10 Feb 2024 · 0 repositories · arXiv:2402.06971
-
Is Mamba Capable of In-Context Learning? 5 Feb 2024 · 1 repository · arXiv:2402.03170Syntology official (archive's flag): 7 ran · 7 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified (of 8 harvested samples) · 8 pointer-only (licence)
-
MotherNet: Fast Training and Inference via Hyper-Network Transformers 14 Dec 2023 · 1 repository · arXiv:2312.08598Syntology official (archive's flag): 1 ran · 1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified (of 1 harvested sample)
-
Scaling TabPFN: Sketching and Feature Selection for Tabular Prior-Data Fitted Networks 17 Nov 2023 · 0 repositories · arXiv:2311.10609
-
Fine-Tuning the Retrieval Mechanism for Tabular Deep Learning 13 Nov 2023 · 0 repositories · arXiv:2311.07343
-
TabPFN: A Transformer That Solves Small Tabular Classification Problems in a Second 5 Jul 2022 · 7 repositories · arXiv:2207.01848Syntology 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 4 harvested samples) · 1 pointer-only (licence)
Tasks archive 2025-07-28
20 shown of 44 tasks the archive attaches to papers tagged with this method, by distinct papers. A task without a page in the catalog is plain text.
Usage over time archive 2025-07-28
Components: the archive holds no method-to-method composition, so PwC's Components table cannot be rebuilt; the Papers list carries no Results column for the same reason (the archive does not join its leaderboard rows to method tags).
Categories archive 2025-07-28
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections