利用结构先验知识精准评估图神经网络中子图的重要性。
Estimating Subgraph Importance with Structural Prior Domain Knowledge
- 基于嵌入空间的线性分组Lasso回归，融合图结构先验知识。
- 无需真实标签即可估计子图重要性，在多个真实数据集上优于基线。
- 可扩展至识别关键节点，适用于无监督图分析场景。
我们提出一种针对预训练图神经网络在图级别任务中的子图重要性估计方法，该方法在嵌入空间中表述为线性分组Lasso回归问题。该方法有效利用了图子结构的先验领域知识，且不依赖于GNN架构中特定的输出层或读出函数形式，也无需访问真实目标标签。在真实世界图数据集上的实验表明，该方法在子图重要性估计上始终优于现有基线。此外，我们将方法扩展至识别图中重要节点。
原文摘要 · Abstract (English)
We propose a subgraph importance estimation method for pretrained Graph Neural Networks (GNNs) on graph-level tasks, formulated as a linear Group Lasso regression problem in the embedding space. Our method effectively leverages prior domain knowledge of graph substructures, while remaining independent of the specific form of the output layer or readout function used in the GNN architecture, and it does not require access to ground-truth target labels. Experiments on real-world graph datasets demonstrate that our method consistently outperforms existing baselines in subgraph importance estimation. Furthermore, we extend our method to identify important nodes within the graph.
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。