InteractiveGNNExplainer: A Visual Analytics Framework for Multi-Faceted Understanding and Probing of Graph Neural Network Predictions

TL;DR

InteractiveGNNExplainer is a visual analytics framework that enhances understanding and probing of GNN predictions through interactive visualization, explanation techniques, and graph editing for better transparency and trust.

Contribution

It introduces an integrated system combining multiple explanation methods with interactive visualization and editing for comprehensive GNN interpretability.

Findings

Enables in-depth diagnosis of misclassifications.

Facilitates comparison between GCN and GAT models.

Supports probing of model sensitivity through interactive perturbations.

Abstract

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.