Distribution Shift Aware Neural Tabular Learning
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918131283263488 |
|---|---|
| author | Ying, Wangyang Gong, Nanxu Wang, Dongjie Wang, Xinyuan Malarkkan, Arun Vignesh Gupta, Vivek Reddy, Chandan K. Fu, Yanjie |
| author_facet | Ying, Wangyang Gong, Nanxu Wang, Dongjie Wang, Xinyuan Malarkkan, Arun Vignesh Gupta, Vivek Reddy, Chandan K. Fu, Yanjie |
| contents | Tabular learning transforms raw features into optimized spaces for downstream tasks, but its effectiveness deteriorates under distribution shifts between training and testing data. We formalize this challenge as the Distribution Shift Tabular Learning (DSTL) problem and propose a novel Shift-Aware Feature Transformation (SAFT) framework to address it. SAFT reframes tabular learning from a discrete search task into a continuous representation-generation paradigm, enabling differentiable optimization over transformed feature sets. SAFT integrates three mechanisms to ensure robustness: (i) shift-resistant representation via embedding decorrelation and sample reweighting, (ii) flatness-aware generation through suboptimal embedding averaging, and (iii) normalization-based alignment between training and test distributions. Extensive experiments show that SAFT consistently outperforms prior tabular learning methods in terms of robustness, effectiveness, and generalization ability under diverse real-world distribution shifts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_19486 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Distribution Shift Aware Neural Tabular Learning Ying, Wangyang Gong, Nanxu Wang, Dongjie Wang, Xinyuan Malarkkan, Arun Vignesh Gupta, Vivek Reddy, Chandan K. Fu, Yanjie Machine Learning Tabular learning transforms raw features into optimized spaces for downstream tasks, but its effectiveness deteriorates under distribution shifts between training and testing data. We formalize this challenge as the Distribution Shift Tabular Learning (DSTL) problem and propose a novel Shift-Aware Feature Transformation (SAFT) framework to address it. SAFT reframes tabular learning from a discrete search task into a continuous representation-generation paradigm, enabling differentiable optimization over transformed feature sets. SAFT integrates three mechanisms to ensure robustness: (i) shift-resistant representation via embedding decorrelation and sample reweighting, (ii) flatness-aware generation through suboptimal embedding averaging, and (iii) normalization-based alignment between training and test distributions. Extensive experiments show that SAFT consistently outperforms prior tabular learning methods in terms of robustness, effectiveness, and generalization ability under diverse real-world distribution shifts. |
| title | Distribution Shift Aware Neural Tabular Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2508.19486 |