Explaining Dynamic Graph Neural Networks via Relevance Back-propagation
This work addresses the need for interpretability in dynamic GNNs, a domain-specific problem for users in fields like network analysis, but it is incremental as it adapts existing explanation techniques to dynamic graphs.
The paper tackles the problem of explaining dynamic Graph Neural Networks (GNNs), which have time-varying graph structures, by proposing DGExplainer, a method that redistributes activation scores to identify important nodes, and demonstrates its effectiveness through experiments on real-world datasets for tasks like link prediction and node regression.
Graph Neural Networks (GNNs) have shown remarkable effectiveness in capturing abundant information in graph-structured data. However, the black-box nature of GNNs hinders users from understanding and trusting the models, thus leading to difficulties in their applications. While recent years witness the prosperity of the studies on explaining GNNs, most of them focus on static graphs, leaving the explanation of dynamic GNNs nearly unexplored. It is challenging to explain dynamic GNNs, due to their unique characteristic of time-varying graph structures. Directly using existing models designed for static graphs on dynamic graphs is not feasible because they ignore temporal dependencies among the snapshots. In this work, we propose DGExplainer to provide reliable explanation on dynamic GNNs. DGExplainer redistributes the output activation score of a dynamic GNN to the relevances of the neurons of its previous layer, which iterates until the relevance scores of the input neuron are obtained. We conduct quantitative and qualitative experiments on real-world datasets to demonstrate the effectiveness of the proposed framework for identifying important nodes for link prediction and node regression for dynamic GNNs.