Improving Variational Graph Autoencoders With Multi-Order Graph Convolutions

Variational Graph Autoencoders (VAGE) emerged as powerful graph representation learning methods with promising performance on graph analysis tasks. However, existing methods typically rely on Graph Convolutional Networks (GCN) to encode the attributes and topology of the original graph. This strateg...

詳細記述

書誌詳細

主要な著者:	Lining Yuan, Ping Jiang, Zhu Wen, Jionghui Li
フォーマット:	Artigo
言語:	Inglês
出版事項:	IEEE 2024-01-01
シリーズ:	IEEE Access
主題:	Variational graph autoencoders graph convolutional networks multi-order neighborhood high-order information graph representation learning
オンライン･アクセス:	https://ieeexplore.ieee.org/document/10477408/
タグ:	タグ追加 タグなし, このレコードへの初めてのタグを付けませんか!