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

This study presents a novel approach that synergizes community detectionalgorithms with various Graph Neural Network (GNN) models to bolster linkprediction in scientific literature networks. By integrating the Louvaincommunity detection algorithm into our GNN frameworks, we consistently enhanceperformance across all models tested. For example, integrating Louvain with theGAT model resulted in an AUC score increase from 0.777 to 0.823, exemplifyingthe typical improvements observed. Similar gains are noted when Louvain ispaired with other GNN architectures, confirming the robustness andeffectiveness of incorporating community-level insights. This consistent upliftin performance reflected in our extensive experimentation on bipartite graphsof scientific collaborations and citations highlights the synergistic potentialof combining community detection with GNNs to overcome common link predictionchallenges such as scalability and resolution limits. Our findings advocate forthe integration of community structures as a significant step forward in thepredictive accuracy of network science models, offering a comprehensiveunderstanding of scientific collaboration patterns through the lens of advancedmachine learning techniques.

A Community Detection and Graph Neural Network Based Link Prediction Approach for Scientific Literature