Improving Deep Tabular Learning
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866912595242385408 |
|---|---|
| author | Sarafian, Sivan Aperstein, Yehudit |
| author_facet | Sarafian, Sivan Aperstein, Yehudit |
| contents | Tabular data remain a dominant form of real-world information but pose persistent challenges for deep learning due to heterogeneous feature types, lack of natural structure, and limited label-preserving augmentations. As a result, ensemble models based on decision trees continue to dominate benchmark leaderboards. In this work, we introduce RuleNet, a transformer-based architecture specifically designed for deep tabular learning. RuleNet incorporates learnable rule embeddings in a decoder, a piecewise linear quantile projection for numerical features, and feature masking ensembles for robustness and uncertainty estimation. Evaluated on eight benchmark datasets, RuleNet matches or surpasses state-of-the-art tree-based methods in most cases, while remaining computationally efficient, offering a practical neural alternative for tabular prediction tasks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2509_16354 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Improving Deep Tabular Learning Sarafian, Sivan Aperstein, Yehudit Machine Learning Tabular data remain a dominant form of real-world information but pose persistent challenges for deep learning due to heterogeneous feature types, lack of natural structure, and limited label-preserving augmentations. As a result, ensemble models based on decision trees continue to dominate benchmark leaderboards. In this work, we introduce RuleNet, a transformer-based architecture specifically designed for deep tabular learning. RuleNet incorporates learnable rule embeddings in a decoder, a piecewise linear quantile projection for numerical features, and feature masking ensembles for robustness and uncertainty estimation. Evaluated on eight benchmark datasets, RuleNet matches or surpasses state-of-the-art tree-based methods in most cases, while remaining computationally efficient, offering a practical neural alternative for tabular prediction tasks. |
| title | Improving Deep Tabular Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2509.16354 |