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

Graphs are a powerful representation tool in machine learning applications,with link prediction being a key task in graph learning. Temporal linkprediction in dynamic networks is of particular interest due to its potentialfor solving complex scientific and real-world problems. Traditional approachesto temporal link prediction have focused on finding the aggregation of dynamicsof the network as a unified output. In this study, we propose a novelperspective on temporal link prediction by defining nodes as Newtonian objectsand incorporating the concept of velocity to predict network dynamics. Bycomputing more specific dynamics of each node, rather than overall dynamics, weimprove both accuracy and explainability in predicting future connections. Wedemonstrate the effectiveness of our approach using two datasets, including 17years of co-authorship data from PubMed. Experimental results show that ourtemporal graph embedding dynamics approach improves downstream classificationmodels' ability to predict future collaboration efficacy in co-authorshipnetworks by 17.34% (AUROC improvement relative to the baseline model).Furthermore, our approach offers an interpretable layer over traditionalapproaches to address the temporal link prediction problem.

Temporal Link Prediction Using Graph Embedding Dynamics