CIExplainer++: Generating Causal and Interpretable Explanations for Graph Neural Networks
For users of GNNs who need trustworthy explanations, this work provides a causally grounded method for identifying influential subgraphs and generating human-readable explanations.
CIExplainer++ introduces a perturbation-based method using causal inference to identify subgraphs with the highest causal effect on GNN predictions, and a method to convert these subgraphs into natural language explanations. The approach is evaluated on multiple GNN architectures and datasets.
Explainable Artificial Intelligence aims to make black-box models more trustworthy by presenting, in a human-understandable manner, the elements that lead to the model's output. This involves both (i) identifying components and connections with genuine causal influence on outputs and (ii) translating such structures into an interpretable representation. For the former, we introduce CIExplainer, a novel perturbation-based method grounded in causal inference for explaining Graph Neural Networks (GNNs). CIExplainer identifies the subgraph with the highest causal effects on GNN predictions using the Potential Outcome Framework. We evaluate and compare CIExplainer on various GNN architectures (GCN, GraphSAGE, GAT, GIN) and datasets. To bridge subgraph explanations with human interpretability, we further propose G2TeXplainer, a method that transforms causal subgraphs into natural language explanations that capture both feature-level and relational information.