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 various practical applications, such asdrug discovery, recommendation engines, and chip design. However, GNNs lacktransparency as they cannot provide understandable explanations for theirpredictions. To address this issue, counterfactual reasoning is used. The maingoal is to make minimal changes to the input graph of a GNN in order to alterits prediction. While several algorithms have been proposed for counterfactualexplanations of GNNs, most of them have two main drawbacks. Firstly, they onlyconsider edge deletions as perturbations. Secondly, the counterfactualexplanation models are transductive, meaning they do not generalize to unseendata. In this study, we introduce an inductive algorithm called INDUCE, whichovercomes these limitations. By conducting extensive experiments on severaldatasets, we demonstrate that incorporating edge additions leads to bettercounterfactual results compared to the existing methods. Moreover, theinductive modeling approach allows INDUCE to directly predict counterfactualperturbations without requiring instance-specific training. This results insignificant computational speed improvements compared to baseline methods andenables scalable counterfactual analysis for GNNs.

Empowering Counterfactual Reasoning over Graph Neural Networks through Inductivity