发表机构
Center for Nonlinear and Complex Systems, Università degli Studi dell’Insubria; Data Science Institute, Hasselt University（非线性与复杂系统中心，因苏布利亚大学; 哈塞尔特大学数据科学研究所）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
研究用图神经网络近似介数和接近中心性，将其作为节点排序问题，以精确中心性值监督，用肯德尔tau秩相关评估。通过混合分布训练等方法，在不同图拓扑上取得较好结果，证明其可提高结构转移能力，同时指出接近中心性对拓扑敏感这一挑战。
AI 中文摘要
图神经网络（GNN）为近似精确计算成本高昂的图数量提供了基于学习的框架。本文研究GNN用于介数和接近中心性的可扩展近似，将其公式化为节点排序问题。使用精确中心性值作为监督，并用肯德尔tau秩相关评估排序质量。研究消息传递GNN能否学习跨不同图拓扑的可转移结构表示。在未见过的Erdos renyi图上，模型介数tau = 0.851，接近中心性tau = 0.894。大规模介数模型在N = 5000节点的图上训练得tau = 0.938。混合分布训练改善了跨图族的介数转移，接近中心性对社区结构图更敏感。GNN推理比精确计算快97.7倍。结果表明混合分布训练可改善基于GNN的中心性近似中的结构转移，同时指出接近中心性对拓扑的敏感性是一个开放挑战。
英文摘要
Graph Neural Networks (GNNs) provide a learning-based framework for approximating graph quantities that are expensive to compute exactly. This paper investigates GNNs for scalable approximation of betweenness and closeness centrality, formulated as a node-ranking problem. Exact centrality values are used as supervision, and ranking quality is evaluated using Kendall's tau rank correlation. We study whether message-passing GNNs can learn transferable structural representations across different graph topologies rather than only fitting the distribution used during training. On unseen Erdos renyi graphs, the proposed models achieve tau = 0.851 for betweenness and tau = 0.894 for closeness. A large-scale betweenness model trained on graphs with N = 5,000 nodes achieves tau = 0.938, demonstrating scalability. Mixed-distribution training on Erdos renyi, Barabasi-Albert, and Gaussian Random Partition graphs improves betweenness transfer across graph families. In contrast, closeness centrality remains more sensitive to community-structured graphs and shows reduced transfer to real-world topologies. Finally, GNN inference achieves up to a 97.7x speedup over exact computation. These results show that mixed-distribution training can improve structural transfer in GNN-based centrality approximation, while identifying closeness centrality's sensitivity to topology as an open challenge.
Comments22 pages, 5 figures
