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

There is a fast-growing body of research on predicting future links indynamic networks, with many new algorithms. Some benchmark data exists, andperformance evaluations commonly rely on comparing the scores of observednetwork events (positives) with those of randomly generated ones (negatives).These evaluation measures depend on both the predictive ability of the modeland, crucially, the type of negative samples used. Besides, as generally thecase with temporal data, prediction quality may vary over time. This creates acomplex evaluation space. In this work, we catalog the possibilities fornegative sampling and introduce novel visualization methods that can yieldinsight into prediction performance and the dynamics of temporal networks. Weleverage these visualization tools to investigate the effect of negativesampling on the predictive performance, at the node and edge level. We validateempirically, on datasets extracted from recent benchmarks that the error istypically not evenly distributed across different data segments. Finally, weargue that such visualization tools can serve as powerful guides to evaluatedynamic link prediction methods at different levels.

New Perspectives on the Evaluation of Link Prediction Algorithms for Dynamic Graphs