提出首个能提取子图与图级概念的GNN，提升模型可解释性。
Subgraph Concept Networks: Concept Levels in Graph Classification
- 通过节点概念嵌入的软聚类，挖掘子图与图级语义概念。
- 在保持竞争力准确率的同时，发现多层级有意义的概念。
- 适合关注图神经网络可解释性的研究人员使用。
图神经网络的推理过程复杂且难以理解，限制了对其预测结果的信任。现有基于概念的解释方法虽能从节点嵌入聚类中提取概念，但仅限于节点层，且在图分类任务中因池化操作而被掩盖。为解决此问题，本文提出子图概念网络（Subgraph Concept Network），这是首个能够提炼子图与图级概念的GNN架构。该方法通过对节点概念嵌入进行软聚类，生成跨层级的概念表示。实验表明，该模型在保持与主流方法相当的分类准确率的同时，能够有效发现网络中不同层次的有意义概念，实现更深层的理解。
原文摘要 · Abstract (English)
The reasoning process of Graph Neural Networks is complex and considered opaque, limiting trust in their predictions. To alleviate this issue, prior work has proposed concept-based explanations, extracted from clusters in the model's node embeddings. However, a limitation of concept-based explanations is that they only explain the node embedding space and are obscured by pooling in graph classification. To mitigate this issue and provide a deeper level of understanding, we propose the Subgraph Concept Network. The Subgraph Concept Network is the first graph neural network architecture that distils subgraph and graph-level concepts. It achieves this by performing soft clustering on node concept embeddings to derive subgraph and graph-level concepts. Our results show that the Subgraph Concept Network allows to obtain competitive model accuracy, while discovering meaningful concepts at different levels of the network.
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。