Step2Vec: 面向动力学传播的网络表示学习方法

陈奇,焦鹏飞,王震,鲍青

PDF(16119 KB)
PDF(16119 KB)
中文信息学报 ›› 2025, Vol. 39 ›› Issue (2) : 100-110.
情感分析与社会计算

Step2Vec: 面向动力学传播的网络表示学习方法

  • 陈奇,焦鹏飞,王震,鲍青
作者信息 +

Step2Vec:A Network Representation for Dynamic Transmission

  • CHEN Qi, JIAO Pengfei, WANG Zhen, BAO Qing
Author information +
History +

摘要

网络表示学习是对节点的网络结构的一种分布式表示方案,目前被广泛应用于节点分类、社团发现和边关系预测等任务中。然而网络表示学习对网络传播过程中节点状态的估计仍是一个开放性的问题。经典的网络表示学习方法在对该问题上的应用效果不佳,因此该文提出了基于动力学传播的采样方法,称为Step2Vec逐步采样方法。Step2Vec通过结合网络传播过程,对节点的网络结构信息进行提取并训练。该文分别将Step2Vec与其他的网络分析方法及网络表示学习方法在多个引文网络和真实传播网络上进行了节点状态估计和边关系预测的实验。实验结果表明,Step2Vec算法估计网络传播中的节点状态准确率达85.6%,且对边关系预测的准确率也具有一定提升,相较于随机游走算法平均提高了5.9%。

Abstract

The network representation learning is a distributed representation scheme for the nodes and the network structure, which is widely used in node classification, community detection and link prediction. It is still an open issue for network representation learning to estimate node state during network transmission. This paper proposes a sampling method based on dynamic transmission, called Step2Vec step-by-step sampling method. Step2Vec extracts and trains the network structure features of nodes by combining the network transmission process. Evaluated by node state estimate task and link prediction task, Step2Vec algorithm achieves 85.6% in estimating the node state in network transmission, and outperforms the random walk algorithm by 5.9%.

关键词

网络传播 / 网络表示学习方法 / 状态估计

Key words

network transmission / network representation algorithms / state estimation

引用本文

导出引用
陈奇,焦鹏飞,王震,鲍青. Step2Vec: 面向动力学传播的网络表示学习方法. 中文信息学报. 2025, 39(2): 100-110
CHEN Qi, JIAO Pengfei, WANG Zhen, BAO Qing. Step2Vec:A Network Representation for Dynamic Transmission. Journal of Chinese Information Processing. 2025, 39(2): 100-110

参考文献

[1] GROVER A, LESKOVEC J. Node2vec: Scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016: 855-864.
[2] TANG J, QU M, WANG M, et al. LINE: Large-scale information network embedding[C]//Proceedings of the 24th International Conference on World Wide Web, 2015: 1067-1077.
[3] DU N, SONG L, GOMEZ RODRIGUEZ M, et al. Scalable influence estimation in continuous-time diffusion networks[J]. Advances in Neural Information Processing Systems, 2013: 26-37.
[4] FUNK S, GILAD E, WATKINS C, et al. The spread of awareness and its impact on epidemic outbreaks[J]. Proceedings of the National Academy of Sciences, 2009, 106(16): 6872-6877.
[5] WANG Z, BAUCH C T, BHATTACHARYYA S, et al. Statistical physics of vaccination[J]. Physics Reports, 2016, 664: 1-113.
[6] SUN M, TAO Y, FU X. Asymmetrical dynamics of epidemic propagation and awareness diffusion in multiplex networks[J]. Chaos: An Interdisciplinary Journal of Nonlinear Science, 2021, 31(9): 093134.
[7] HUANG H, CHEN Y, YAN Z. Impacts of social distancing on the spread of infectious diseases with asymptomatic infection: A mathematical model[J]. Applied Mathematics and Computation,2021,398: 125983.
[8] MENG X, CAI Z, SI S, et al. Analysis of epidemic vaccination strategies on heterogeneous networks: Based on SEIRV model and evolutionary game[J]. Applied Mathematics and Computation, 2021,403: 126172.
[9] WANG Z, XIA C, CHEN Z, et al. Epidemic propagation with positive and negative preventive information in multiplex networks[J]. IEEE Transactions on Cybernetics, 2020, 51(3): 1454-1462.
[10] SATORRAS P R, VESPIGNANI A. Epidemic spreading in scale-free networks[J]. Physical Review Letters, 2001, 86(14): 3200.
[11] KEMPE D, KLEINBERG J, TARDOS . Maximizing the spread of influence through a social network[C]//Proceedings of the 9th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2003: 137-146.
[12] KITSAK M, GALLOS L K, HAVLIN S, et al. Identification of influential spreaders in complex networks[J]. Nature Physics, 2010, 6(11): 888-893.
[13] SHAH D, ZAMAN T. Rumors in a network: Whos the culprit?[J]. IEEE Transactions on Information Theory, 2011, 57(8): 5163-5181.
[14] SHAH D, ZAMAN T. Detecting sources of computer viruses in networks: Theory and experiment[C]//Proceedings of the ACM SIGMETRICS International Conference on Measurement and Modeling of Computer Systems, 2010: 203-214.
[15] LUO W, TAY W P. Estimating infection sources in a network with incomplete observations[C]//Proceedings of the IEEE Global Conference on Signal and Information Processing, 2013: 301-304.
[16] ZHU K, YING L. Information source detection in the SIR model: A sample-path-based approach[J]. IEEE/ACM Transactions on Networking, 2014, 24(1): 408-421.
[17] HAMMOND D K, VANDERGHEYNST P, GRIBONVAL R. Wavelets on graphs via spectral graph theory[J]. Applied and Computational Harmonic Analysis, 2011, 30(2): 129-150.
[18] GRADY L, FUNKALEA G. Multi-label image segmentation for medical applications based on graph-theoretic electrical potentials[C]//Proceedings of the Computer Vision and Mathematical Methods in Medical and Biomedical Image Analysis, 2004: 230-245.
[19] PEROZZI B, ALRFOU R, SKIENA S. DeepWalk: Online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2014: 701-710.
[20] ZHAN X X, LI Z, MASUDA N, et al. Susceptible-infected-spreading-based network embedding in static and temporal networks[J]. EPJ Data Science, 2020, 9(1): 30-31.

陈奇(1998—),硕士研究生,主要研究领域为网络科学。
E-mail: chenqi@hdu.edu.cn焦鹏飞(1990—),通信作者,博士,教授,主要研究领域为复杂网络科学及其应用。
E-mail: pjiao@hdu.edu.cn王震(1984—),博士,副教授,主要研究领域为人工智能安全、数据驱动安全、博弈论、多智能体系统和网络科学等。
E-mail wangzhen@hdu.edu.cn

基金

国家自然科学基金(61902278);浙江省属高校基本科研业务费专项(GK229909299001-008)
PDF(16119 KB)

Accesses

Citation

Detail

段落导航
相关文章

/