Saved in:
Bibliographic Details
Main Authors: Tanis, James H., Giannella, Chris, Mariano, Adrian V., Meerzaman, Daoud
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.19419
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917553815683072
author Tanis, James H.
Giannella, Chris
Mariano, Adrian V.
Meerzaman, Daoud
author_facet Tanis, James H.
Giannella, Chris
Mariano, Adrian V.
Meerzaman, Daoud
contents Graph neural networks are deep neural networks designed for graphs with attributes attached to nodes or edges. The number of research papers in the literature concerning these models is growing rapidly due to their impressive performance on a broad range of tasks. This survey introduces graph neural networks through the encoder-decoder framework and provides examples of decoders for a range of graph analytic tasks. It uses theory and numerous experiments on homogeneous graphs to illustrate the behavior of graph neural networks under different training sizes and degrees of graph complexity, with an emphasis on oversmoothing and oversquashing.
format Preprint
id arxiv_https___arxiv_org_abs_2412_19419
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Introduction to Graph Neural Networks for Machine Learning Engineers
Tanis, James H.
Giannella, Chris
Mariano, Adrian V.
Meerzaman, Daoud
Machine Learning
Artificial Intelligence
Graph neural networks are deep neural networks designed for graphs with attributes attached to nodes or edges. The number of research papers in the literature concerning these models is growing rapidly due to their impressive performance on a broad range of tasks. This survey introduces graph neural networks through the encoder-decoder framework and provides examples of decoders for a range of graph analytic tasks. It uses theory and numerous experiments on homogeneous graphs to illustrate the behavior of graph neural networks under different training sizes and degrees of graph complexity, with an emphasis on oversmoothing and oversquashing.
title Introduction to Graph Neural Networks for Machine Learning Engineers
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2412.19419