Distill n' Explain: explaining graph neural networks using simple surrogates

arXiv:2303.10139v2 Announce Type: replace
Abstract: Explaining node predictions in graph neural networks (GNNs) often boils down to finding graph substructures that preserve predictions. Finding these structures usually implies back-propagating through the GNN, bonding the complexity (e.g., number of layers) of the GNN to the cost of explaining it. This naturally begs the question: Can we break this bond by explaining a simpler surrogate GNN? To answer the question, we propose Distill n' Explain (DnX). First, DnX learns a surrogate GNN …

abstract arxiv complexity cost cs.ai cs.lg gnn gnns graph graph neural networks networks neural networks node predictions simple through type