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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Unsupervised graph representation learning is a non-trivial topic for graphdata. The success of contrastive learning and self-supervised learning in theunsupervised representation learning of structured data inspires similarattempts on the graph. The current unsupervised graph representation learningand pre-training using the contrastive loss are mainly based on the contrastbetween handcrafted augmented graph data. However, the graph data augmentationis still not well-explored due to the unpredictable invariance. In this paper,we propose a novel collaborative graph neural networks contrastive learningframework (CGCL), which uses multiple graph encoders to observe the graph.Features observed from different views act as the graph augmentation forcontrastive learning between graph encoders, avoiding any perturbation toguarantee the invariance. CGCL is capable of handling both graph-level andnode-level representation learning. Extensive experiments demonstrate theadvantages of CGCL in unsupervised graph representation learning and thenon-necessity of handcrafted data augmentation composition for graphrepresentation learning.

Collaborative Graph Contrastive Learning: Data Augmentation Composition May Not be Necessary for Graph Representation Learning