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

Digraph Representation Learning (DRL) aims to learn representations fordirected homogeneous graphs (digraphs). Prior work in DRL is largelyconstrained (e.g., limited to directed acyclic graphs), or has poorgeneralizability across tasks (e.g., evaluated solely on one task). Most GraphNeural Networks (GNNs) exhibit poor performance on digraphs due to the neglectof modeling neighborhoods and preserving asymmetry. In this paper, we addressthese notable challenges by leveraging hyperbolic collaborative learning frommulti-ordered and partitioned neighborhoods, and regularizers inspired bysocio-psychological factors. Our resulting formalism, Digraph HyperbolicNetworks (D-HYPR) - albeit conceptually simple - generalizes to digraphs wherecycles and non-transitive relations are common, and is applicable to multipledownstream tasks including node classification, link presence prediction, andlink property prediction. In order to assess the effectiveness of D-HYPR,extensive evaluations were performed across 8 real-world digraph datasetsinvolving 21 prior techniques. D-HYPR statistically significantly outperformsthe current state of the art. We release our code athttps://github.com/hongluzhou/dhypr

D-HYPR: Harnessing Neighborhood Modeling and Asymmetry Preservation for Digraph Representation Learning