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

Trust evaluation assesses trust relationships between entities andfacilitates decision-making. Machine Learning (ML) shows great potential fortrust evaluation owing to its learning capabilities. In recent years, GraphNeural Networks (GNNs), as a new ML paradigm, have demonstrated superiority indealing with graph data. This has motivated researchers to explore their use intrust evaluation, as trust relationships among entities can be modeled as agraph. However, current trust evaluation methods that employ GNNs fail to fullysatisfy the dynamic nature of trust, overlook the adverse effects oftrust-related attacks, and cannot provide convincing explanations on evaluationresults. To address these problems, we propose TrustGuard, a GNN-based accuratetrust evaluation model that supports trust dynamicity, is robust againsttypical attacks, and provides explanations through visualization. Specifically,TrustGuard is designed with a layered architecture that contains a snapshotinput layer, a spatial aggregation layer, a temporal aggregation layer, and aprediction layer. Among them, the spatial aggregation layer adopts a defensemechanism to robustly aggregate local trust, and the temporal aggregation layerapplies an attention mechanism for effective learning of temporal patterns.Extensive experiments on two real-world datasets show that TrustGuardoutperforms state-of-the-art GNN-based trust evaluation models with respect totrust prediction across single-timeslot and multi-timeslot, even in thepresence of attacks. In addition, TrustGuard can explain its evaluation resultsby visualizing both spatial and temporal views.

TrustGuard: GNN-based Robust and Explainable Trust Evaluation with Dynamicity Support