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

While graph neural networks (GNNs) have shown a great potential in varioustasks on graph, the lack of transparency has hindered understanding how GNNsarrived at its predictions. Although few explainers for GNNs are explored, theconsideration of local fidelity, indicating how the model behaves around aninstance should be predicted, is neglected. In this paper, we first propose anovel post-hoc framework based on local fidelity for any trained GNNs - TraP2,which can generate a high-fidelity explanation. Considering that both relevantgraph structure and important features inside each node need to be highlighted,a three-layer architecture in TraP2 is designed: i) interpretation domain aredefined by Translation layer in advance; ii) local predictive behavior of GNNsbeing explained are probed and monitored by Perturbation layer, in whichmultiple perturbations for graph structure and feature-level are conducted ininterpretation domain; iii) high faithful explanations are generated by fittingthe local decision boundary through Paraphrase layer. Finally, TraP2 isevaluated on six benchmark datasets based on five desired attributions:accuracy, fidelity, decisiveness, insight and inspiration, which achieves$10.2\%$ higher explanation accuracy than the state-of-the-art methods.

Perturb More, Trap More: Understanding Behaviors of Graph Neural Networks