Graph Neural Networks for Tabular Data Learning

• Published in: 2023 IEEE 39th International Conference on Data Engineering (ICDE) pp. 3589 - 3592
• Main Authors: Li, Cheng-Te, Tsai, Yu-Che, Liao, Jay Chiehen
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.04.2023
• Subjects: Correlation; Data engineering; Graph neural networks; Graph Representation Learning; Graph Structure Learning; Representation learning; Self-supervised Learning; Tabular Data Learning; Taxonomy; Training; Tutorials
• ISSN: 2375-026X
• DOI: 10.1109/ICDE55515.2023.00275

Deep learning-based approaches to Tabular Data Learning (TDL) have shown promising performance compared to their conventional counterparts. However, these methods often fail to account for the latent correlation among data instances and feature values. Recently, graph neural networks (GNNs) have gained attention across various application domains, including TDL, for their ability to model relations and interactions between different data entities. By creating appropriate graph structures from the input tabular data and employing GNNs for learning, the performance of TDL can be improved significantly. In this tutorial, we systematically introduce the methodologies of designing and applying GNNs to TDL. Our discussion covers the foundations and overview of GNN-based TDL methods, with a focus on formulating TDL as different graph structures. We also provide a comprehensive taxonomy of constructing graph structures and representation learning in GNN-based TDL methods. We describe the TDL model training framework, which includes different auxiliary tasks and supports open-world learning. Additionally, we discuss how to apply GNNs to various TDL application scenarios and tasks. Finally, we outline the limitations of current research and future directions for this field.