TabPFN
≈ 1 min read
Names in other languages
No names in other languages are held for this entry yet.
Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.
TabPFN (Tabular Prior-data Fitted Network) is a machine learning model for tabular datasets proposed in 2022. It uses a transformer architecture. It is intended for supervised classification and regression analysis on tabular datasets, particularly focusing on small- to medium-sized datasets. The latest version, TabPFN-3.5, was released in September 20261. It uses a single model for both classification and regression and is recommended by its developers for datasets with up to one million rows and 6,000 features.
TabPFN (Tabular Prior-data Fitted Network) is a machine learning model for tabular datasets proposed in 2022. It uses a transformer architecture. It is intended for supervised classification and regression analysis on tabular datasets, particularly focusing on small- to medium-sized datasets. The latest version, TabPFN-3.5, was released in September 2026. It uses a single model for both classification and regression and is recommended by its developers for datasets with up to one million rows and 6,000 features.
See also
XGBoost LightGBM CatBoost
Text derived from https://en.wikipedia.org/w/index.php?oldid=1378472656 under CC BY-SA 4.0; modifications have been made.