View-Aware Contrastive Learning for Incomplete Tabular Data with Low-Label Regimes

View-Aware Contrastive Learning for Incomplete Tabular Data with Low-Label Regimes

To address the challenges of label sparsity and feature incompleteness in structured data, a self-supervised representation learning method based on multi-view consistency constraints is proposed in this paper. Robust modeling of high-dimensional sparse tabular data is achieved through integration o...

Full description

Saved in:
Bibliographic Details
Main Authors: Yingqiu Yang, Qianye Lin, Zeyue Li, Yakui Wang, Siyu Liang, Siyuan Zhang, Yiyan Wang, Chunli Lv
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
multi-view self-supervised learning
intra-view and cross-view alignment
robust feature encoding
low-label regime generalization
Online Access:https://www.mdpi.com/2076-3417/15/11/6001
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://www.mdpi.com/2076-3417/15/11/6001

Similar Items