Supervised Learning with Informed Graph Convolution

L. David Aites; David E. Stewart

doi:10.1109/UEMCON62879.2024.10754727

Back

Conference proceeding

Supervised Learning with Informed Graph Convolution

L. David Aites and David E. Stewart

2024 IEEE 15th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), pp.587-592

10/17/2024

DOI: 10.1109/UEMCON62879.2024.10754727

View Online

Abstract

Graph Convolutional Neural Networks (GCNs) have been undergoing improvements in recent years as well as receiving attention due to their usefulness. However the base idea involves computationally expensive mathematics [1]. Some recent advances have shown that modifications can be made that improve the computational efficiency of the concept without any major loss of accuracy. Here we present an improvement to the simplification of GCNs shown by Simple Graph Convolution (SGC) that increased their overall accuracy while maintaining the algorithmic simplicity [8]. We also show that GCNs may be changed from message passing architectures to information gathering to improve their accuracy. This is achieved using the calculations presented in SGC to create new feature vectors using concatenation rather than simply modifying the original feature vectors.

Computer Architecture

Machine Learning

Accuracy

Computational efficiency

Convolution

Convolutional neural networks

Graph Convolutional Neural Networks

Message passing

Mobile communication

Supervised learning

Vectors

Details

Title: Subtitle: Supervised Learning with Informed Graph Convolution
Creators: L. David Aites - University of Iowa
David E. Stewart - University of Iowa
Resource Type: Conference proceeding
Publication Details: 2024 IEEE 15th Annual Ubiquitous Computing, Electronics & Mobile Communication Conference (UEMCON), pp.587-592
Publisher: IEEE
DOI: 10.1109/UEMCON62879.2024.10754727
Language: English
Date published: 10/17/2024
Academic Unit: Mathematics
Record Identifier: 9984751756502771

Metrics

8 Record Views