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

Graph Neural Networks (GNNs) have shown great ability in modelinggraph-structured data for various domains. However, GNNs are known as black-boxmodels that lack interpretability. Without understanding their inner working,we cannot fully trust them, which largely limits their adoption in high-stakescenarios. Though some initial efforts have been taken to interpret thepredictions of GNNs, they mainly focus on providing post-hoc explanations usingan additional explainer, which could misrepresent the true inner workingmechanism of the target GNN. The works on self-explainable GNNs are ratherlimited. Therefore, we study a novel problem of learning prototype-basedself-explainable GNNs that can simultaneously give accurate predictions andprototype-based explanations on predictions. We design a framework which canlearn prototype graphs that capture representative patterns of each class asclass-level explanations. The learned prototypes are also used tosimultaneously make prediction for for a test instance and provideinstance-level explanation. Extensive experiments on real-world and syntheticdatasets show the effectiveness of the proposed framework for both predictionaccuracy and explanation quality.

Towards Prototype-Based Self-Explainable Graph Neural Network