Multiview Deep Graph Infomax to Achieve Unsupervised Graph Embedding | IEEE Journals & Magazine | IEEE Xplore

Multiview Deep Graph Infomax to Achieve Unsupervised Graph Embedding


Abstract:

Unsupervised graph embedding aims to extract highly discriminative node representations that facilitate the subsequent analysis. Converging evidence shows that a multivie...Show More

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.
Published in: IEEE Transactions on Cybernetics ( Volume: 53, Issue: 10, October 2023)
Page(s): 6329 - 6339
Date of Publication: 15 April 2022

ISSN Information:

PubMed ID: 35427229

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.