通过稀疏约束提升图预测的可解释性与精度
Exact Subgraph Isomorphism Network with Mixed $L_{0,2}$ Norm Constraint for Predictive Graph Mining
- 结合精确子图枚举与神经网络，增强对子图结构的判别力
- 利用混合$L_{0,2}$正则化，在保持性能前提下减少计算量
- 能识别关键子图，适合需要可解释性的图预测任务
在图级预测任务中，输入图中的子图信息起关键作用。本文提出精确子图同构网络（EIN），融合精确子图枚举、神经网络与混合$L_{0,2}$范数正则化。该方法在保证高判别能力的同时，提升了模型可解释性。混合正则化实现了两个优势：一是设计有效剪枝策略，缓解枚举带来的计算负担，同时维持预测性能；二是识别出对预测贡献显著的关键子图。实验表明，EIN在预测性能上优于标准图神经网络模型，并展示了基于选定子图的后验分析案例。
原文摘要 · Abstract (English)
In the graph-level prediction task (predict a label for a given graph), the information contained in subgraphs of the input graph plays a key role. In this paper, we propose Exact subgraph Isomorphism Network (EIN), which combines the exact subgraph enumeration, a neural network, and a sparse regularization by the mixed $L_{0,2}$ norm constraint. In general, building a graph-level prediction model achieving high discriminative ability along with interpretability is still a challenging problem. Our combination of the subgraph enumeration and neural network contributes to high discriminative ability about the subgraph structure of the input graph. Further, the sparse regularization in EIN enables us 1) to derive an effective pruning strategy that mitigates computational difficulty of the enumeration while maintaining the prediction performance, and 2) to identify important subgraphs that contributes to high interpretability. We empirically show that EIN has sufficiently high prediction performance compared with standard graph neural network models, and also, we show examples of post-hoc analysis based on the selected subgraphs.
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。