|
|
--- |
|
|
base_model: |
|
|
- intfloat/e5-small-v2 |
|
|
license: cc-by-4.0 |
|
|
pipeline_tag: tabular-regression |
|
|
--- |
|
|
|
|
|
# Paper title and link |
|
|
|
|
|
The model was presented in the paper [TabSTAR: A Foundation Tabular Model With Semantically Target-Aware |
|
|
Representations](https://arxiv.org/abs/2505.18125). |
|
|
|
|
|
# Paper abstract |
|
|
|
|
|
The abstract of the paper is the following: |
|
|
|
|
|
While deep learning has achieved remarkable success across many domains, it |
|
|
has historically underperformed on tabular learning tasks, which remain |
|
|
dominated by gradient boosting decision trees (GBDTs). However, recent |
|
|
advancements are paving the way for Tabular Foundation Models, which can |
|
|
leverage real-world knowledge and generalize across diverse datasets, |
|
|
particularly when the data contains free-text. Although incorporating language |
|
|
model capabilities into tabular tasks has been explored, most existing methods |
|
|
utilize static, target-agnostic textual representations, limiting their |
|
|
effectiveness. We introduce TabSTAR: a Foundation Tabular Model with |
|
|
Semantically Target-Aware Representations. TabSTAR is designed to enable |
|
|
transfer learning on tabular data with textual features, with an architecture |
|
|
free of dataset-specific parameters. It unfreezes a pretrained text encoder and |
|
|
takes as input target tokens, which provide the model with the context needed |
|
|
to learn task-specific embeddings. TabSTAR achieves state-of-the-art |
|
|
performance for both medium- and large-sized datasets across known benchmarks |
|
|
of classification tasks with text features, and its pretraining phase exhibits |
|
|
scaling laws in the number of datasets, offering a pathway for further |
|
|
performance improvements. |
|
|
|
|
|
We’re working on making **TabSTAR** available to everyone. In the meantime, you can find the research code to pretrain the model here: |
|
|
|
|
|
[🔗 GitHub Repository: alanarazi7/TabSTAR](https://github.com/alanarazi7/TabSTAR) |
|
|
|
|
|
Project page: https://eilamshapira.com/TabSTAR/ |
