Information-Enhanced Graph Neural Network for Transcending Homophily Barriers

Information-Enhanced Graph Neural Network for Transcending Homophily Barriers

Homophily and heterophily are intrinsic properties of graphs that describe whether linked nodes share similar properties. While Message Passing Neural Networks (MPNNs) have shown remarkable success in node classification tasks, their performance often deteriorates within specific homophily ranges, w...

Full description

Bibliographic Details
Main Authors: Xiao Liu, Lijun Zhang, Hui Guan
Format: Article
Language:English
Published: IEEE 2024-01-01
Series:IEEE Access
Subjects:
Graph neural networks (GNNs)
graph homophily
graph node classification
Online Access:https://ieeexplore.ieee.org/document/10810421/

Internet

https://ieeexplore.ieee.org/document/10810421/

Similar Items