InteractiveGNNExplainer: A Visual Analytics Framework for Multi-Faceted Understanding and Probing of Graph Neural Network Predictions
This addresses the problem of trust and debugging in GNNs for users in critical domains requiring explainability, though it is incremental as it builds on existing explanation methods.
The paper tackles the opacity of Graph Neural Networks (GNNs) by introducing InteractiveGNNExplainer, a visual analytics framework that integrates interactive views and explanation techniques, enabling users to perform 'what-if' analyses through graph editing to diagnose misclassifications and probe model sensitivity on datasets like Cora and CiteSeer.
Graph Neural Networks (GNNs) excel in graph-based learning tasks, but their complex, non-linear operations often render them as opaque "black boxes". This opacity hinders user trust, complicates debugging, bias detection, and adoption in critical domains requiring explainability. This paper introduces InteractiveGNNExplainer, a visual analytics framework to enhance GNN explainability, focusing on node classification. Our system uniquely integrates coordinated interactive views (dynamic graph layouts, embedding projections, feature inspection, neighborhood analysis) with established post-hoc (GNNExplainer) and intrinsic (GAT attention) explanation techniques. Crucially, it incorporates interactive graph editing, allowing users to perform a "what-if" analysis by perturbing graph structures and observing immediate impacts on GNN predictions and explanations. We detail the system architecture and, through case studies on Cora and CiteSeer datasets, demonstrate how InteractiveGNNExplainer facilitates in-depth misclassification diagnosis, comparative analysis of GCN versus GAT behaviors, and rigorous probing of model sensitivity. These capabilities foster a deeper, multifaceted understanding of GNN predictions, contributing to more transparent, trustworthy, and robust graph analysis.