.png){kind=icon}
返回
Multi-view contrastive learning for multilayer network embedding
.png){kind=icon}
PRE
AI
DOI：10.1016/j.jocs.2023.101975.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Graph embedding aims to learn low-dimension node representations which can be applied to various downstream tasks, such as node clustering and node classification. When it comes to heterogeneous graphs, things get more challenging as the graph contains richer semantic and structural information. Most existing heterogeneous graph embedding methods usually convert the graph into several homogenous graphs, and then use the manual label information to train the model. However, Graph neural networks (GNNs) mostly require task-dependent labels to learn representations, which is even more costly for heterogeneous graphs. Furthermore, these models treat each converted homogenous graph independently while ignoring the inter-layer informative relational clues among the multi-graphs. Inspired by recent advances of Deep Graph Infomax and multi-view learning in homogeneous graph embedding, we propose an unsupervised graph neural network called CLMNE that adopts multi-view contrastive learning and multilayer information fusion for heterogeneous graph embedding. The proposed model learns rich local and global graph information by maximizing the local-global mutual information from adjacency matrix and diffusion matrix two different views. Moreover, a variant model CL-MNEreg, which provides embedding information of all graph layers, is constructed by addingg a consensus regularization to the CL-MNE. Experiments of node clustering and classification tasks on mainstream datasets demonstrate the effectiveness of the proposed two models.
Keyword:
Heterogeneous graphs
Multilayer network embedding
Mutual information maximization
Multi-view contrastive learning
期刊
IF:
18.3
论文数:
3.1K
被引数:
4.0K
机构
引用论文
Formylglycinamide Ribonucleotide Amidotransferase from Thermotoga maritima: Structural Insights into Complex Formation.png)
Biochemistry
OAAI
BiochemistryIF0
OAAI分享收藏分享收藏Ultrasonographic Assessment of Femoral Cartilage in Individuals With Anterior Cruciate Ligament Reconstruction: A Case-Control Study超声评估前交叉韧带重建患者股骨软骨：一项病例对照研究OAAI
OAAI分享收藏分享收藏分享收藏
查看更多内容