EUVIMEDEUVIMED entdecken
Crossref

Representation Learning for Tabular Data: A Comprehensive Survey

Jun-Peng Jiang, Si-Yang Liu, Hao-Run Cai, Qi-Le Zhou, Han-Jia Ye

IEEE Transactions on Pattern Analysis and Machine Intelligence · 2026-06 · 48 (6) · 6488-6508

DOI: 10.1109/tpami.2026.3657217 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Transactions on Pattern Analysis and Machine Intelligence, 2026-06. Verfasst von Jun-Peng Jiang und 4 weiteren Autor:innen. Die Arbeit wurde bisher 34-mal zitiert (Crossref) und nennt 263 Literaturangaben. Gefördert von: Natural Science Foundation of Jiangsu Province of China, National Natural Science Foundation of China, Collaborative Innovation Center of Novel Software Technology and Industrialization.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Tabular data, structured as rows and columns, is among the most prevalent data types in machine learning classification and regression applications. Models for learning from tabular data have continuously evolved, with Deep Neural Networks (DNNs) recently demonstrating promising results through their capability of representation learning. In this survey, we systematically introduce the field of tabular representation learning, covering the background, challenges, and benchmarks, along with the pros and cons of using DNNs. We organize existing methods into three main categories according to their generalization capabilities: specialized, transferable, and general models. Specialized models focus on tasks where training and evaluation occur within the same data distribution. We introduce a hierarchical taxonomy for specialized models based on the key aspects of tabular data-features, samples, and objectives-and delve into detailed strategies for obtaining high-quality feature- and sample-level representations. Transferable models are pre-trained on one or more datasets and subsequently fine-tuned on downstream tasks, leveraging knowledge acquired from homogeneous or heterogeneous sources, or even cross-modalities such as vision and language. General models, also known as tabular foundation models, extend this concept further, allowing direct application to downstream tasks without additional fine-tuning. We group these general models based on the strategies used to adapt across heterogeneous datasets. Additionally, we explore ensemble methods, which integrate the strengths of multiple tabular models. Finally, we discuss representative extensions of tabular learning, including open-environment tabular machine learning, multimodal learning with tabular data, and tabular understanding tasks.

Förderung

  • Natural Science Foundation of Jiangsu Province of China
  • National Natural Science Foundation of China
  • Collaborative Innovation Center of Novel Software Technology and Industrialization

Zitieren

APA

Jiang, J. P., Liu, S. Y., Cai, H. R., Zhou, Q. L., & Ye, H. J. (2026). Representation Learning for Tabular Data: A Comprehensive Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, 48(6), 6488-6508. https://doi.org/10.1109/tpami.2026.3657217

Vancouver

Jiang JP, Liu SY, Cai HR, Zhou QL, Ye HJ. Representation Learning for Tabular Data: A Comprehensive Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence. 2026;48(6):6488-6508. doi:10.1109/tpami.2026.3657217

BibTeX
@article{Jiang2026,
  author = {Jiang, Jun-Peng and Liu, Si-Yang and Cai, Hao-Run and Zhou, Qi-Le and Ye, Han-Jia},
  title = {Representation Learning for Tabular Data: A Comprehensive Survey},
  journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year = {2026},
  volume = {48},
  number = {6},
  pages = {6488--6508},
  doi = {10.1109/tpami.2026.3657217}
}
Kostenlos starten →