摘要
动态网络链路预测是理解和分析动态网络的核心问题之一。针对链路预测面临的捕获复杂网络结构和真实演化规律等困难的问题,提出了一种融合图神经网络和神经常微分方程的自适应网络动力学建模方法——双层活跃度约束神经常微分方程模型DANOM。DANOM融合节点的重要性和相对位置信息,增强了网络结构的表征;通过节点活跃度约束下的神经常微分方程单元强化了演化规律的学习过程;并在节点活跃度和节点表示的重构损失优化下,挖掘到网络的有效信息。DANOM在多个真实数据集上的多种下游任务中均达到了最优效果,其中在单步链路预测任务中AUC与AP最高分别提升14%和9.7%,在快照缺失情况下的链路预测任务中AUC与AP分别平均仅降低0.43%和0.03%,在用户缝合实验中AUC与AP最高分别提升20.6%和24.4%。
Dynamic network link prediction is one of the core issues in understanding and analyzing dynamic networks.In response to the challenges of capturing complex network structures and real evolution patterns faced by link prediction,this paper proposes a method integrating the graph neural network and neural ordinary differential equation to adaptive model various network dynamics:double-layer activity-constrained neural ordinary differential equation model(DANOM).DANOM integrates the importance and relative positional information of nodes to enhance the representation of network structures,strengthens the learning process of evolution patterns through neural ordinary differential equation units constrained by node activity,and mines effective information of the network under the reconstruction loss of node activity and node representation.DANOM achieves optimal results in various down-stream tasks on multiple real-world datasets.It achieves the highest improvements of 14%and 9.7%in terms of AUC and AP,respectively,in the single-step link prediction task.In cases of snapshot missingness,the average AUC and AP of link prediction are only reduced by 0.43%and 0.03%,respectively.In the user stitching experiments,DANOM achieves the highest improvements of 20.6%and 24.4%in terms of AUC and AP,respectively.
作者
郭翾
侯锦霖
王文俊
焦鹏飞
GUO Xuan;HOU Jinlin;WANG Wenjun;JIAO Pengfei(College of Intelligence and Computing,Tianjin University,Tianjin 300350,China;College of Cyberspace Security,Hangzhou Dianzi University,Hangzhou 310018,China)
出处
《计算机科学》
北大核心
2025年第6期118-128,共11页
Computer Science
基金
海南省重点研发项目(ZDYF2024SHFZ051)
国家自然科学基金(62372146)
浙江省自然科学基金(LDT23F01015F01)
新奥集团合作项目(2023GKF-1220)。
关键词
图表示学习
动态网络
链路预测
神经常微分方程
网络动力学
Graph representation learning
Dynamic network
Link prediction
Neural ordinary differential equation
Network dynamics
