频谱效率中心性：一种用于识别时序网络中关键节点的高效频谱方法
Spectral Efficiency Centrality: An Efficient Spectral Approach for Influential Node Identification in Temporal Networks
浏览论文内容
中文总结 AI 辅助
针对现有频谱节点移除方法仅适用于静态网络的问题，提出时序频谱中心性框架 SEC 及高效近似方法 ASEC，经多组真实数据集实验验证，二者在三类扩散模型下识别时序网络关键节点的性能优于基线指标。
中文摘要 AI 辅助
中心性指标在识别演化网络中的关键节点方面发挥着至关重要的作用。现有时序中心性指标主要依赖于局部结构属性或时序路径，而频谱节点移除方法大多局限于静态网络。为填补这一空白，我们提出了频谱效率中心性（Spectral Efficiency Centrality, SEC），这是一种时序频谱中心性框架，通过评估节点移除在各个时序快照中引起的谱半径变化来量化节点重要性。SEC 能够捕捉节点在整个网络演化过程中的全局结构影响，识别出对维持时序网络的结构连通性和效率至关重要的节点。为提高计算可扩展性，我们进一步基于 Perron-Frobenius 理论和一阶特征值扰动开发了高效近似方法 ASEC。ASEC 仅需主导特征对，避免了重复特征分解，适用于大型时序网络。在多个真实世界时序数据集上进行的大量实验表明，SEC 和 ASEC 在 SI、SIS 和 IC 扩散模型下识别关键节点的性能优于现有的基线中心性指标。统计显著性和鲁棒性分析进一步证实了它们的有效性，而 ASEC 为大型时序网络提供了一种计算高效的解决方案。
英文摘要
Centrality measures play a vital role in identifying influential nodes in evolving networks. While existing temporal centrality measures primarily rely on local structural properties or temporal paths, spectral node-removal approaches have been largely limited to static networks. To bridge this gap, we propose Spectral Efficiency Centrality (SEC), a temporal spectral centrality framework that quantifies node importance by evaluating the change in spectral radius caused by node removal across temporal snapshots. By capturing the global structural influence of nodes throughout network evolution, SEC identifies nodes that are critical for preserving the structural connectivity and efficiency of temporal networks. To improve computational scalability, we further develop an efficient approximation, ASEC, based on Perron-Frobenius theory and first-order eigenvalue perturbation. ASEC requires only the leading eigenpair and avoids repeated eigendecomposition, making it suitable for large temporal networks. Extensive experiments on multiple real-world temporal datasets demonstrate that SEC and ASEC outperform existing baseline centrality measures in identifying influential nodes under SI, SIS, and IC diffusion models. Statistical significance and robustness analyses further confirm their effectiveness, while ASEC offers a computationally efficient solution for large-scale temporal networks.
