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

Graph contrastive learning (GCL) has become a powerful tool for learninggraph data, but its scalability remains a significant challenge. In this work,we propose a simple yet effective training framework called StructuralCompression (StructComp) to address this issue. Inspired by a sparse low-rankapproximation on the diffusion matrix, StructComp trains the encoder with thecompressed nodes. This allows the encoder not to perform any message passingduring the training stage, and significantly reduces the number of sample pairsin the contrastive loss. We theoretically prove that the original GCL loss canbe approximated with the contrastive loss computed by StructComp. Moreover,StructComp can be regarded as an additional regularization term for GCL models,resulting in a more robust encoder. Empirical studies on seven benchmarkdatasets show that StructComp greatly reduces the time and memory consumptionwhile improving model performance compared to the vanilla GCL models andscalable training methods.

StructComp: Substituting propagation with Structural Compression in Training Graph Contrastive Learning