Graph Clustering via Variational Graph Embedding
作者：
Highlights：
• GC-VGE exploits GCN and applies it to the proposed graph variational auto-encoder.
• A joint generative model is constructed for acquiring an embedding space with high information content.
• GC-VGE takes advantage of the topological structure and node features of the graph.
• GC-VGE simultaneously performs graph embedding and optimizes graph nodes clustering.
• GC-VGE utilizes a self-supervised mechanism.
摘要
•GC-VGE exploits GCN and applies it to the proposed graph variational auto-encoder.•A joint generative model is constructed for acquiring an embedding space with high information content.•GC-VGE takes advantage of the topological structure and node features of the graph.•GC-VGE simultaneously performs graph embedding and optimizes graph nodes clustering.•GC-VGE utilizes a self-supervised mechanism.
论文关键词：Graph convolution neural network,Variational graph embedding,Graph clustering,Variational graph auto-encoder
论文评审过程：Received 22 December 2020, Revised 2 August 2021, Accepted 17 September 2021, Available online 22 September 2021, Version of Record 5 October 2021.
论文官网地址：https://doi.org/10.1016/j.patcog.2021.108334
