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

Prior works on formalizing explanations of a graph neural network (GNN) focuson a single use case - to preserve the prediction results through identifyingimportant edges and nodes. In this paper, we develop a multi-purposeinterpretation framework by acquiring a mask that indicates topologyperturbations of the input graphs. We pack the framework into an interactivevisualization system (GNNViz) which can fulfill multiple purposes:Preserve,Promote, or Attack GNN's predictions. We illustrate our approach'snovelty and effectiveness with three case studies: First, GNNViz can assist nonexpert users to easily explore the relationship between graph topology andGNN's decision (Preserve), or to manipulate the prediction (Promote or Attack)for an image classification task on MS-COCO; Second, on the Pokec socialnetwork dataset, our framework can uncover unfairness and demographic biases;Lastly, it compares with state-of-the-art GNN explainer baseline on a syntheticdataset.

Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation