Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning
This work addresses the need for interpretable graph learning by offering a novel concept-based explanation method that maintains performance, benefiting researchers and practitioners requiring trustworthy models.
GCB introduces a new paradigm for self-explainable text-attributed graph learning by mapping graphs into a concept bottleneck subspace, achieving accuracy comparable to black-box GNNs while providing intrinsic interpretability and improved robustness under distribution shifts.
We introduce Graph Concept Bottleneck (GCB) as a new paradigm for self-explainable text-attributed graph learning. GCB maps graphs into a subspace, concept bottleneck, where each concept is a meaningful phrase, and predictions are made based on the activation of these concepts. Unlike existing interpretable graph learning methods that primarily rely on subgraphs as explanations, the concept bottleneck provides a new form of interpretation. To refine the concept space, we apply the information bottleneck principle to focus on the most relevant concepts. This not only yields more concise and faithful explanations but also explicitly guides the model to "think" toward the correct decision. We empirically show that GCB achieves intrinsic interpretability with accuracy on par with black-box Graph Neural Networks. Moreover, it delivers better performance under distribution shifts and data perturbations, showing improved robustness and generalizability, benefitting from concept-guided prediction.