The reviewed record of science sign in
Pith

arxiv: 2406.06891 · v1 · pith:H7BNKJ4U · submitted 2024-06-11 · cs.LG · cs.AI

Tokenize features, enhancing tables: the FT-TABPFN model for tabular classification

Reviewed by Pith T0 review T1 audit T2 compute T3 formal T4 kernel pith:H7BNKJ4Urecord.jsonopen to challenge →

classification cs.LG cs.AI
keywords classificationtabpfntabularfeaturesft-tabpfnmodeldatasetslayer
0
0 comments X
read the original abstract

Traditional methods for tabular classification usually rely on supervised learning from scratch, which requires extensive training data to determine model parameters. However, a novel approach called Prior-Data Fitted Networks (TabPFN) has changed this paradigm. TabPFN uses a 12-layer transformer trained on large synthetic datasets to learn universal tabular representations. This method enables fast and accurate predictions on new tasks with a single forward pass and no need for additional training. Although TabPFN has been successful on small datasets, it generally shows weaker performance when dealing with categorical features. To overcome this limitation, we propose FT-TabPFN, which is an enhanced version of TabPFN that includes a novel Feature Tokenization layer to better handle classification features. By fine-tuning it for downstream tasks, FT-TabPFN not only expands the functionality of the original model but also significantly improves its applicability and accuracy in tabular classification. Our full source code is available for community use and development.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. TabPFN-MT: A Natively Multitask In-Context Learner for Tabular Data

    cs.LG 2026-05 unverdicted novelty 7.0

    TabPFN-MT is a multitask in-context learner for tabular data that sets a new state-of-the-art on deep multitask learning for datasets under 1000 samples while reducing inference cost from O(T) to O(1) passes.