When Must All Conditions Hold? Identifiable Conjunctive Explanations for Link Prediction with Multiplicative View-Gated Graph Neural Networks
Link predictors that support decisions, such as suggesting a director to a startup, must explain why a link is or is not recommended. We propose the Multiplicative View-Gated GNN (MG-GNN), which scores a pair as the weighted product of gates, each restricted to one view of the evidence: attributes, structural position,...
Angelo Leogrande, Mauro Di Molfetta, Valeria Notarnicola et al.
· Preprints.org · 0 citations