GraphNarrator: Generating Textual Explanations for Graph Neural Networks
It addresses the challenge of explainability for users of graph learning models in domains like recommendation systems, but it is incremental as it builds on existing saliency-based and generative methods.
The paper tackles the problem of explainability in Graph Neural Networks by introducing GraphNarrator, a method that generates natural language explanations, resulting in faithful, concise, and human-preferred outputs as demonstrated in experiments.
Graph representation learning has garnered significant attention due to its broad applications in various domains, such as recommendation systems and social network analysis. Despite advancements in graph learning methods, challenges still remain in explainability when graphs are associated with semantic features. In this paper, we present GraphNarrator, the first method designed to generate natural language explanations for Graph Neural Networks. GraphNarrator employs a generative language model that maps input-output pairs to explanations reflecting the model's decision-making process. To address the lack of ground truth explanations to train the model, we propose first generating pseudo-labels that capture the model's decisions from saliency-based explanations, then using Expert Iteration to iteratively train the pseudo-label generator based on training objectives on explanation quality. The high-quality pseudo-labels are finally utilized to train an end-to-end explanation generator model. Extensive experiments are conducted to demonstrate the effectiveness of GraphNarrator in producing faithful, concise, and human-preferred natural language explanations.