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

Explaining the foundations for predictions obtained from graph neuralnetworks (GNNs) is critical for credible use of GNN models for real-worldproblems. Owing to the rapid growth of GNN applications, recent progress inexplaining predictions from GNNs, such as sensitivity analysis, perturbationmethods, and attribution methods, showed great opportunities and possibilitiesfor explaining GNN predictions. In this study, we propose a method to improvethe explanation quality of node classification tasks that can be applied in apost hoc manner through aggregation of auxiliary explanations from importantneighboring nodes, named SEEN. Applying SEEN does not require modification of agraph and can be used with diverse explainability techniques due to itsindependent mechanism. Experiments on matching motif-participating nodes from agiven graph show great improvement in explanation accuracy of up to 12.71% anddemonstrate the correlation between the auxiliary explanations and the enhancedexplanation accuracy through leveraging their contributions. SEEN provides asimple but effective method to enhance the explanation quality of GNN modeloutputs, and this method is applicable in combination with most explainabilitytechniques.

SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods