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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

As an intuitive description of complex physical, social, or brain systems,complex networks have fascinated scientists for decades. Recently, to abstracta network's structural and dynamical attributes for utilization, networkrepresentation has been one focus, mapping a network or its substructures (likenodes) into a low-dimensional vector space. Since the current methods aremostly based on machine learning, a black box of an input-output data fittingmechanism, generally the space's dimension is indeterminable and its elementsare not interpreted. Although massive efforts to cope with this issue haveincluded, for example, automated machine learning by computer scientists andcomputational theory by mathematics, the root causes still remain unresolved.Given that, from a physical perspective, this article proposes two determinableand interpretable node representation methods. To evaluate their effectivenessand generalization, this article further proposes Adaptive and InterpretableProbS (AIProbS), a network-based model that can utilize node representationsfor link prediction. Experimental results showed that the AIProbS can reachstate-of-the-art precision beyond baseline models, and by and large it can makea good trade-off with machine learning-based models on precision, determinacy,and interpretability, indicating that physical methods could also play a largerole in the study of network representation.

Determinable and interpretable network representation for link prediction