arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2403.04977cs.SIcs.AI
收藏

基于归纳图神经网络的大规模网络节点中心性近似计算

Node Centrality Approximation For Large Networks Based On Inductive Graph Neural Networks

School of Systems Science and Engineering, Sun Yat-sen University(中山大学系统科学与工程学院)

Yiwei Zou, Ting Li, Zong-fu Luo

AI总结:

针对大规模网络中接近中心性与介数中心性计算复杂度高、现有近似方法效率低且鲁棒性差的问题,提出基于归纳图神经网络的编码器-解码器模型CNCA-IGE,在多类网络上实现了性能与计算效率的双重提升。

摘要:

接近中心性(Closeness Centrality, CC)和介数中心性(Betweenness Centrality, BC)是网络分析中的关键指标,为判别复杂网络中节点的重要性提供核心参考,广泛应用于社区检测、网络拆解等关键任务中。但由于时间复杂度较高,在大规模网络中实际计算这类指标的计算开销极大。为缓解这一计算难题,已有诸多近似算法被提出以加速CC和BC的计算,但即便这些近似方法应用于大规模网络时仍需大量处理时间,且其输出对网络结构的微小扰动都十分敏感。\n本研究将CC和BC的节点排序问题重新定义为机器学习问题,提出CNCA-IGE模型——这是一种基于归纳图神经网络的编码器-解码器模型,用于根据指定的CC或BC指标对节点进行排序。在BC排序预测任务中,我们引入MLP-Mixer模型作为解码器,以提升模型的鲁棒性和性能容量。我们在不同规模的多种合成网络与真实网络上对该方法进行了评估,实验结果表明,CNCA-IGE模型性能优于现有最优基线模型,在提升性能的同时大幅缩短了执行时间。

英文摘要:

Closeness Centrality (CC) and Betweenness Centrality (BC) are crucial metrics in network analysis, providing essential reference for discerning the significance of nodes within complex networks. These measures find wide applications in critical tasks, such as community detection and network dismantling. However, their practical implementation on extensive networks remains computationally demanding due to their high time complexity. To mitigate these computational challenges, numerous approximation algorithms have been developed to expedite the computation of CC and BC. Nevertheless, even these approximations still necessitate substantial processing time when applied to large-scale networks. Furthermore, their output proves sensitive to even minor perturbations within the network structure. In this work, We redefine the CC and BC node ranking problem as a machine learning problem and propose the CNCA-IGE model, which is an encoder-decoder model based on inductive graph neural networks designed to rank nodes based on specified CC or BC metrics. We incorporate the MLP-Mixer model as the decoder in the BC ranking prediction task to enhance the model's robustness and capacity. Our approach is evaluated on diverse synthetic and real-world networks of varying scales, and the experimental results demonstrate that the CNCA-IGE model outperforms state-of-the-art baseline models, significantly reducing execution time while improving performance.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑