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

Link prediction on graphs is a fundamental problem. Subgraph representationlearning approaches (SGRLs), by transforming link prediction to graphclassification on the subgraphs around the links, have achievedstate-of-the-art performance in link prediction. However, SGRLs arecomputationally expensive, and not scalable to large-scale graphs due toexpensive subgraph-level operations. To unlock the scalability of SGRLs, wepropose a new class of SGRLs, that we call Scalable Simplified SGRL (S3GRL).Aimed at faster training and inference, S3GRL simplifies the message passingand aggregation operations in each link's subgraph. S3GRL, as a scalabilityframework, accommodates various subgraph sampling strategies and diffusionoperators to emulate computationally-expensive SGRLs. We propose multipleinstances of S3GRL and empirically study them on small to large-scale graphs.Our extensive experiments demonstrate that the proposed S3GRL models scale upSGRLs without significant performance compromise (even with considerable gainsin some cases), while offering substantially lower computational footprints(e.g., multi-fold inference and training speedup).

Simplifying Subgraph Representation Learning for Scalable Link Prediction