Graph Autoencoder with Preserving Node Attribute Similarity

Graph Autoencoder with Preserving Node Attribute Similarity

The graph autoencoder (GAE) is a powerful graph representation learning tool in an unsupervised learning manner for graph data. However, most existing GAE-based methods typically focus on preserving the graph topological structure by reconstructing the adjacency matrix while ignoring the preservatio...

Full description

Bibliographic Details
Main Authors: Mugang Lin, Kunhui Wen, Xuanying Zhu, Huihuang Zhao, Xianfang Sun
Format: Article
Language:English
Published: MDPI AG 2023-03-01
Series:Entropy
Subjects:
graph representation learning
graph autoencoder
unsupervised learning
<i>k</i>-nearest neighbor
Online Access:https://www.mdpi.com/1099-4300/25/4/567

Internet

https://www.mdpi.com/1099-4300/25/4/567

Similar Items