基于时序生成对抗网络的机会网络链路预测  

Opportunistic Network Link Prediction Based on Temporal Generative Adversarial Networks

作　　者：舒坚[1] 王鹏涛 李睿瑞 SHU Jian;WANG Pengtao;LI Ruirui(School of Software,Nanchang Hangkong University,Nanchang 330063,China)

机构地区：[1]南昌航空大学软件学院,南昌330063

出　　处：《北京邮电大学学报》2025年第1期39-45,共7页Journal of Beijing University of Posts and Telecommunications

基　　金：国家自然科学基金项目(62362052,62062050);江西省研究生创新专项资金项目(YC2023-S707)。

摘　　要：机会网络节点频繁移动的特点导致其链路预测极具挑战。为更好地反映其拓扑结构随时间变化的情况,提出基于时序生成对抗网络的机会网络链路预测方法。定义网络波动率,计算网络分割时长,将机会网络分割为细粒度的网络切片;从网络切片中提取信息矩阵,从空间和时间两个维度进行信息融合;利用图嵌入方法提取网络特征向量矩阵;结合门控循环单元和生成对抗网络,构建了时序生成对抗网络模型,学习网络拓扑结构在时间序列上的演变特征,实现网络未来时刻的链路预测。在3个真实数据集上的实验结果表明,所提方法的预测性能优于基线方法。The frequent node mobility of opportunistic networks poses significant challenges for link prediction.To better reflect the temporal evolution of the topology,an opportunistic network link prediction method based on temporal generative adversarial networks is proposed.A network volatility is defined for calculating the network segmentation duration so that an opportunistic network is sliced into fine-grained snapshots.Information matrices are extracted from these network slices which integrate spatial and temporal dimensional information,and network feature vector matrices are constructed by graph embedding methods.Combining gated recurrent units and generative adversarial network,a temporal generative adversarial network model is developed.It learns the evolutionary features of network topology,so as to achieve link prediction in networks for the future.The experimental results on three real datasets demonstrate that the predictive performance of the proposed method is superior to that of the baseline method.

关 键 词：机会网络 链路预测 生成对抗网络 门控循环单元 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]