Rsc: accelerate graph neural networks training via randomized sparse computations
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 …
based operations are hard to be accelerated by community hardware. Prior art successfully …
Efficient sharpness-aware minimization for molecular graph transformer models
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 …
since it can effectively eliminate the sharp local minima from the training trajectory and …
Data Visualization Analysis Based on Explainable Artificial Intelligence: A Survey
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 …
bottleneck of intelligent analysis of massive data has changed from" how to deal with …
NCART: Neural Classification and Regression Tree for tabular data
J Luo, S Xu - Pattern Recognition, 2024 - Elsevier
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 …
the limitations of decision trees and enable valuable applications like semi-supervised …
Graph Neural Networks for Tabular Data Learning: A Survey with Taxonomy and Directions
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 …
(GNNs), a domain where deep learning-based approaches have increasingly shown …
TabGSL: Graph structure learning for tabular data prediction
JC Liao, CT Li - arXiv preprint arXiv:2305.15843, 2023 - arxiv.org
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 …
learning and graph neural networks. Despite the prevalence of tabular data in real-world …
Interpretable Graph Neural Networks for Tabular Data
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 …
Networks (GNNs) have recently been extended to effectively handle such data, allowing …
GCondNet: A Novel Method for Improving Neural Networks on Small High-Dimensional Tabular Data
Neural network models often struggle with high-dimensional but small sample-size tabular
datasets. One reason is that current weight initialisation methods assume independence …
datasets. One reason is that current weight initialisation methods assume independence …
Investigating latent representations and generalization in deep neural networks for tabular data
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 …
feature level and process multiple latent representations simultaneously, typically one per …
GraphFADE: Field-aware Decorrelation Neural Network for Graphs with Tabular Features
J Wan, Y Fu, J Yu, W Jiang, S Pu, R Yang - Proceedings of the 32nd …, 2023 - dl.acm.org
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 …
remarkable ability to extract effective representations from both node features and graph …