English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Recently, maximizing mutual information has emerged as a powerful method forunsupervised graph representation learning. The existing methods are typicallyeffective to capture information from the topology view but ignore the featureview. To circumvent this issue, we propose a novel approach by exploitingmutual information maximization across feature and topology views.Specifically, we first utilize a multi-view representation learning module tobetter capture both local and global information content across feature andtopology views on graphs. To model the information shared by the feature andtopology spaces, we then develop a common representation learning module usingmutual information maximization and reconstruction loss minimization. Toexplicitly encourage diversity between graph representations from the sameview, we also introduce a disagreement regularization to enlarge the distancebetween representations from the same view. Experiments on synthetic andreal-world datasets demonstrate the effectiveness of integrating feature andtopology views. In particular, compared with the previous supervised methods,our proposed method can achieve comparable or even better performance under theunsupervised representation and linear evaluation protocol.

Maximizing Mutual Information Across Feature and Topology Views for Learning Graph Representations