TabPFN

Last updated
TabPFN
Developer(s) Noah Hollmann, Samuel Müller, Lennart Purucker, Arjun Krishnakumar, Max Körfer, Shi Bin Hoo, Robin Tibor Schirrmeister, Frank Hutter, Leo Grinsztajn, Klemens Flöge, Oscar Key & Sauraj Gambhir [1]
Initial releaseSeptember 16, 2023;23 months ago (2023-09-16) [2] [3]
Written in Python [3]
Operating system Linux, macOS, Microsoft Windows [3]
Type Machine learning
License Apache License 2.0
Website github.com/PriorLabs/TabPFN

TabPFN (Tabular Prior-data Fitted Network) is a machine learning model for tabular datasets proposed in 2022. It uses a transformer architecture. [1] It is intended for supervised classification and regression analysis on small- to medium-sized datasets, e.g., up to 10,000 samples. [1]

Contents

History

TabPFN was first introduced in a 2022 pre-print and presented at ICLR 2023. [2] TabPFN v2 was published in 2025 in Nature (journal) by Hollmann and co-authors. [1] The source code is published on GitHub under a modified Apache License and on PyPi. [4] Writing for ICLR blogs, McCarter states that the model has attracted attention due to its performance on small dataset benchmarks. [5]

Prior Labs, founded in 2024, aims to commercialize TabPFN. [6]

Overview and pre-training

TabPFN supports classification, regression and generative tasks. [1] It leverages "Prior-Data Fitted Networks" [7] models to model tabular data. [8] [ failed verification ] [9] [ failed verification ] By using a transformer pre-trained on synthetic tabular datasets, [2] [5] TabPFN avoids benchmark contamination and costs of curating real-world data. [2]

TabPFN v2 was pre-trained on approximately 130 million such datasets. [1] Synthetic datasets are generated using causal models or Bayesian neural networks; this can include simulating missing values, imbalanced data, and noise. [1] Random inputs are passed through these models to generate outputs, with a bias towards simpler causal structures.[ citation needed ] During pre-training, TabPFN predicts the masked target values of new data points given training data points and their known targets, effectively learning a generic learning algorithm that is executed by running a neural network forward pass. [1] The new dataset is then processed in a single forward pass without retraining. [2] The model’s transformer encoder processes features and labels by alternating attention across rows and columns. [10] TabPFN v2 handles numerical and categorical features, missing values, and supports tasks like regression and synthetic data generation. [1]

Since TabPFN is pre-trained, in contrast to other deep learning methods, it does not require costly hyperparameter optimization. [10]

Research

TabPFN is the subject of on-going research. Applications for TabPFN have been investigated for domains such as chemoproteomics, [11] insurance risk classification, [12] and metagenomics. [13]

Limitations

TabPFN has been criticized for its "one large neural network is all you need" approach to modeling problems. [5] Further, its performance is limited in high-dimensional and large-scale datasets. [14]

See also

References

  1. 1 2 3 4 5 6 7 8 9 Hollmann, N.; Müller, S.; Purucker, L. (2025). "Accurate predictions on small data with a tabular foundation model". Nature. 637 (8045): 319–326. Bibcode:2025Natur.637..319H. doi:10.1038/s41586-024-08328-6. PMC   11711098 . PMID   39780007.
  2. 1 2 3 4 5 Hollmann, Noah (2023). TabPFN: A transformer that solves small tabular classification problems in a second. International Conference on Learning Representations (ICLR).
  3. 1 2 3 Python Package Index (PyPI) - tabpfn https://pypi.org/project/tabpfn/
  4. ↑ PriorLabs/TabPFN, Prior Labs, 2025-06-22, retrieved 2025-06-23
  5. 1 2 3 McCarter, Calvin (May 7, 2024). "What exactly has TabPFN learned to do? | ICLR Blogposts 2024". iclr-blogposts.github.io. Retrieved 2025-06-22.
  6. ↑ Kahn, Jeremy (5 February 2025). "AI has struggled to analyze tables and spreadsheets. This German startup thinks its breakthrough is about to change that". Fortune.
  7. ↑ Müller, Samuel (2022). Transformers can do Bayesian inference. International Conference on Learning Representations (ICLR).
  8. ↑ Shwartz-Ziv, Ravid; Armon, Amitai (2022). "Tabular data: Deep learning is not all you need". Information Fusion. 81: 84–90. arXiv: 2106.03253 . doi:10.1016/j.inffus.2021.11.011.
  9. ↑ Grinsztajn, Léo; Oyallon, Edouard; Varoquaux, Gaël (2022). Why do tree-based models still outperform deep learning on typical tabular data?. Proceedings of the 36th International Conference on Neural Information Processing Systems (NIPS '22). pp. 507–520.
  10. 1 2 McElfresh, Duncan C. (8 January 2025). "The AI tool that can interpret any spreadsheet instantly". Nature. 637 (8045): 274–275. Bibcode:2025Natur.637..274M. doi:10.1038/d41586-024-03852-x. PMID   39780000.
  11. ↑ Offensperger, Fabian; Tin, Gary; Duran-Frigola, Miquel; Hahn, Elisa; Dobner, Sarah; Ende, Christopher W. am; Strohbach, Joseph W.; Rukavina, Andrea; Brennsteiner, Vincenth; Ogilvie, Kevin; Marella, Nara; Kladnik, Katharina; Ciuffa, Rodolfo; Majmudar, Jaimeen D.; Field, S. Denise; Bensimon, Ariel; Ferrari, Luca; Ferrada, Evandro; Ng, Amanda; Zhang, Zhechun; Degliesposti, Gianluca; Boeszoermenyi, Andras; Martens, Sascha; Stanton, Robert; Müller, André C.; Hannich, J. Thomas; Hepworth, David; Superti-Furga, Giulio; Kubicek, Stefan; Schenone, Monica; Winter, Georg E. (26 April 2024). "Large-scale chemoproteomics expedites ligand discovery and predicts ligand behavior in cells". Science. 384 (6694): eadk5864. Bibcode:2024Sci...384k5864O. doi:10.1126/science.adk5864. PMID   38662832.{{cite journal}}: CS1 maint: article number as page number (link)
  12. ↑ Chu, Jasmin Z. K.; Than, Joel C. M.; Jo, Hudyjaya Siswoyo (2024). "Deep Learning for Cross-Selling Health Insurance Classification". 2024 International Conference on Green Energy, Computing and Sustainable Technology (GECOST). pp. 453–457. doi:10.1109/GECOST60902.2024.10475046. ISBN   979-8-3503-5790-5.
  13. ↑ Perciballi, Giulia; Granese, Federica; Fall, Ahmad; Zehraoui, Farida; Prifti, Edi; Zucker, Jean-Daniel (10 October 2024). Adapting TabPFN for Zero-Inflated Metagenomic Data. Table Representation Learning Workshop at NeurIPS 2024.
  14. ↑ "A Closer Look at TabPFN v2: Strength, Limitation, and Extension". arxiv.org. Retrieved 2025-07-08.
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.