Multiview Deep Graph Infomax to Achieve Unsupervised Graph Embedding
- 15 April 2022
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Cybernetics
- Vol. 53 (10) , 6329-6339
Abstract
Unsupervised graph embedding aims to extract highly discriminative node representations that facilitate the subsequent analysis. Converging evidence shows that a multiview graph provides a more comprehensive relationship between nodes than a single-view graph to capture the intrinsic topology. However, little attention has been paid to excavating discriminative representations of each node from multiview heterogeneous networks in an unsupervised manner. To that end, we propose a novel unsupervised multiview graph embedding method, called multiview deep graph infomax (MVDGI). The backbone of our proposed model sought to maximize the mutual information between the view-dependent node representations and the fused unified representation via contrastive learning. Specifically, the MVDGI first uses an encoder to extract view-dependent node representations from each single-view graph. Next, an aggregator is applied to fuse the view-dependent node representations into the view-independent node representations. Finally, a discriminator is adopted to extract highly discriminative representations via contrastive learning. Extensive experiments demonstrate that the MVDGI achieves better performance than the benchmark methods on five real-world datasets, indicating that the obtained node representations by our proposed approach are more discriminative than by its competitors for classification and clustering tasks.Keywords
Funding Information
- National Natural Science Foundation of China (U21A20520, 62102153, 62172112)
- Fundamental Research Fund for the Central Universities (x2jsD2200720)
- Key-Area Research and Development of Guangdong Province (2020B1111190001)
- China Postdoctoral Science Foundation (2021M691062)
- National Key Research and Development Program of China (2019YFB2102102)
This publication has 28 references indexed in Scilit:
- Predicting multicellular function through multi-layer tissue networksBioinformatics, 2017
- node2vec2016
- Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classification2015
- LINE2015
- DeepWalk2014
- Glove: Global Vectors for Word Representation2014
- Deep Learning via Semi-supervised Embedding2012
- Combining link and content for community detection2009
- Link-based Classification2006
- An efficient k-means clustering algorithm: analysis and implementationIEEE Transactions on Pattern Analysis and Machine Intelligence, 2002