Can I read Semi-Supervised Learning with Data Augmentation for Tabular Data on EtoBox?

Semi-Supervised Learning with Data Augmentation for Tabular Data by Junpeng Fang; Caizhi Tang; Qing Cui; Feng Zhu; Longfei Li; Jun Zhou; Wei Zhu is a scholarly article available to read on EtoBox.

What is Semi-Supervised Learning with Data Augmentation for Tabular Data about?

Data augmentation-based semi-supervised learning (SSL) methods have made great progress in computer vision and natural language processing areas. One of the most important factors is that the semantic structure invariance of these data allows the augmentation procedure (e.g., rotating images or masking words) to thoroughly utilize the enormous amount of unlabeled data. However, the tabular data does not possess an obvious invariant structure, and therefore similar data augmentation methods do not apply to it. To fill this gap, we present a simple yet efficient data augmentation method particular designed for tabular data and apply it to the SSL algorithm: Sdat (Semi-supervised learning with Data Augmentation for Tabular data). We adopt a multi-task learning framework that consists of two components: the data augmentation procedure and the consistency training procedure. The data augmentation procedure which perturbs in latent space employs a variational auto-encoder (Vae) to generate the reconstructed samples as augmented samples. The consistency training procedure constrains the predictions to be invariant between the augmented samples and the corresponding original samples. By sh

Author

Junpeng Fang; Caizhi Tang; Qing Cui; Feng Zhu; Longfei Li; Jun Zhou; Wei Zhu

Publisher

ACM

Published

2022

Language

EN