Training graph neural networks (GNNs) is extremely time consuming because sparse graph-
based operations are hard to be accelerated by community hardware. Prior art successfully …

Sharpness-aware minimization (SAM) has received increasing attention in computer vision
since it can effectively eliminate the sharp local minima from the training trajectory and …

With the rapid development of computer hardware and big data processing technology, the
bottleneck of intelligent analysis of massive data has changed from" how to deal with …

Deep learning models have become popular in the analysis of tabular data, as they address
the limitations of decision trees and enable valuable applications like semi-supervised …

In this survey, we dive into Tabular Data Learning (TDL) using Graph Neural Networks
(GNNs), a domain where deep learning-based approaches have increasingly shown …

This work presents a novel approach to tabular data prediction leveraging graph structure
learning and graph neural networks. Despite the prevalence of tabular data in real-world …

Data in tabular format is frequently occurring in real-world applications. Graph Neural
Networks (GNNs) have recently been extended to effectively handle such data, allowing …

Neural network models often struggle with high-dimensional but small sample-size tabular
datasets. One reason is that current weight initialisation methods assume independence …

Recent deep neural network architectures that are tailored to tabular data operate at the
feature level and process multiple latent representations simultaneously, typically one per …

Graph Neural Networks (GNNs) have achieved great success in recent years for their
remarkable ability to extract effective representations from both node features and graph …