Rankings
Publications
Search Publications
Cited-by Search
Sources
Publishers
Scholars
Scholars
Top Cited Scholars
Organizations
About
Scilit
About Us
Advisory Board
Data Sources
Career
Support / Contact
User Guide
Publisher User
Search Function
Rankings Function
API Resource
Scilit Knowledge
Metrics
Scilit Recognitions
Publications Classification
Media
News
Blog
Login
Register
Home
Publications
On Addressing the Limitations of Graph Neural Networks
Home
Publications
On Addressing the Limitations of Graph Neural Networks
On Addressing the Limitations of Graph Neural Networks
Author:
SL
Sitao Luan
Sitao Luan
Article Alert
Citation Alert
Add to Library
Cite
Download
Share
Download
Download PDF
Download
Preprint
Publisher website
Google Scholar
4 July 2023
preprint
Published by
MDPI AG
in
Preprints.org
DOI:
10.20944/preprints202307.0118.v1
Abstract
This report gives a comprehensive summary of two problems about graph convolutional networks (GCNs): over-smoothing and heterophily challenges, and outlines future directions to explore.
Keywords
GRAPH NEURAL NETWORKS
REINFORCEMENT LEARNING
OVER-SMOOTHING
HETEROPHILY
All Related Versions
Version 1, 2023-07-04, Preprints
Version 1, 2023-06-22, ArXiv (Unconfirmed version)
Version 2, 2023-07-02, ArXiv (Unconfirmed version)
Related articles
Cited
Cited by 5 articles
Scroll to top