Empowering Counterfactual Reasoning over Graph Neural Networks through Inductivity
This addresses the problem of providing scalable and generalizable explanations for GNN predictions in applications like drug discovery and recommendation systems, representing an incremental improvement over prior work.
The paper tackled the lack of transparency in Graph Neural Networks (GNNs) by proposing an inductive algorithm called INDUCE for counterfactual explanations, which incorporates edge additions and achieves better results and significant computational speed improvements compared to existing methods.
Graph neural networks (GNNs) have various practical applications, such as drug discovery, recommendation engines, and chip design. However, GNNs lack transparency as they cannot provide understandable explanations for their predictions. To address this issue, counterfactual reasoning is used. The main goal is to make minimal changes to the input graph of a GNN in order to alter its prediction. While several algorithms have been proposed for counterfactual explanations of GNNs, most of them have two main drawbacks. Firstly, they only consider edge deletions as perturbations. Secondly, the counterfactual explanation models are transductive, meaning they do not generalize to unseen data. In this study, we introduce an inductive algorithm called INDUCE, which overcomes these limitations. By conducting extensive experiments on several datasets, we demonstrate that incorporating edge additions leads to better counterfactual results compared to the existing methods. Moreover, the inductive modeling approach allows INDUCE to directly predict counterfactual perturbations without requiring instance-specific training. This results in significant computational speed improvements compared to baseline methods and enables scalable counterfactual analysis for GNNs.