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

The task of inductive link prediction in (discrete) attributed multigraphsinfers missing attributed links (relations) between nodes in new testmultigraphs. Traditional relational learning methods face the challenge oflimited generalization to test multigraphs containing both novel nodes andnovel relation types not seen in training. Recently, under the only assumptionthat all relation types share the same structural predictive patterns (singletask), Gao et al. (2023) proposed a link prediction method using thetheoretical concept of double equivariance (equivariance for nodes & relationtypes), in contrast to the (single) equivariance (only for nodes) used todesign Graph Neural Networks (GNNs). In this work we further extend the doubleequivariance concept to multi-task double equivariance, where we define linkprediction in attributed multigraphs that can have distinct and potentiallyconflicting predictive patterns for different sets of relation types (multipletasks). Our empirical results on real-world datasets demonstrate that ourapproach can effectively generalize to test graphs with multi-task structureswithout access to additional information.

A Multi-Task Perspective for Link Prediction with New Relation Types and Nodes