.png){kind=icon}
返回
Graph Community Infomax
.png){kind=icon}
PRE
AI
DOI：10.1145/3480244.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph representation learning aims at learning low-dimension representations for nodes in graphs, and has been proven very useful in several downstream tasks. In this article, we propose a new model, Graph Community Infomax (GCI), that can adversarial learn representations for nodes in attributed networks. Different from other adversarial network embedding models, which would assume that the data follow some prior distributions and generate fake examples, GCI utilizes the community information of networks, using nodes as positive(or real) examples and negative(or fake) examples at the same time. An autoencoder is applied to learn the embedding vectors for nodes and reconstruct the adjacency matrix, and a discriminator is used to maximize the mutual information between nodes and communities. Experiments on several real-world and synthetic networks have shown that GCI outperforms various network embedding methods on community detection tasks.
Keyword:
Mutual information
attributed network
community detecton
representation learning
期刊
IF:
4.8
论文数:
1.3K
被引数:
4.4K
机构
引用论文
Presynaptic K-channel blockade counteracts the depressant effect of adenosine in olfactory cortex.png)
Neuroscience
NeuroscienceIF0
PREAI
分享收藏What are the perceptions about running and knee joint health among the public and healthcare practitioners in Canada?PLOS ONE
OAAI
PLOS ONEIF0
OAAI分享收藏Insurance activity and economic performance: Fresh evidence from asymmetric panel causality testsOAAI
OAAI分享收藏Passive signal propagation and membrane properties in median photoreceptors of the giant barnacleOAAI
OAAI分享收藏
查看更多内容