Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning

arXiv:2604.11986v1 Announce Type: new Abstract: 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.

Related

• Learning How Much to Think: Difficulty-Aware Dynamic MoEs for Graph Node Classification
• SIGMA: An Efficient Heterophilous Graph Neural Network with Fast Global Aggregation
• Dual Mamba for Node-Specific Representation Learning: Tackling Over-Smoothing with Selective State Space Modeling
• Adversarial Robustness of Graph Transformers
• RoleMAG: Learning Neighbor Roles in Multimodal Graphs

Source: arXiv cs.LG | 2026-04-15