用概念子空间让图学习模型自动解释决策过程。
Exploring Concept Subspace for Self-explainable Text-Attributed Graph Learning
- 将图映射到由有意义短语构成的概念子空间进行预测。
- 在保持精度的同时实现可解释性，且对数据扰动更鲁棒。
- 适合需要透明决策的场景，如医疗或金融图分析。
我们提出图概念瓶颈（GCB）作为自解释文本属性图学习的新范式。GCB将图映射到一个概念瓶颈子空间，其中每个概念是具有意义的短语，预测基于这些概念的激活程度做出。不同于现有方法主要依赖子图作为解释，概念瓶颈提供了新的解释形式。为优化概念空间，我们应用信息瓶颈原理，聚焦最相关概念，不仅使解释更简洁、忠实，还显式引导模型“思考”至正确决策。实验表明，GCB在保持与黑箱图神经网络相当精度的同时实现内在可解释性；在分布偏移和数据扰动下表现更优，得益于概念引导的预测机制，展现出更强的鲁棒性和泛化能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。