基于深度对抗网络的动态图生成模型研究  

Research on dynamic graph generation model based on deep adversarial network

作　　者：张梦圆 端阳 王彬彬 张蕾 吴裔 刘畅 郭乃网 程大伟 ZHANG Mengyuan;DUAN Yang;WANG Binbin;ZHANG Lei;WU Yi;LIU Chang;GUO Naiwang;CHENG Dawei(State Grid Shanghai Municipal Electric Power Company,Shanghai 200122;School of Computer Science and Technology,Tongji University,Shanghai 201804,China)

机构地区：[1]国网上海市电力公司,上海200122 [2]同济大学计算机科学与技术学院,上海201804

出　　处：《计算机工程与科学》2025年第4期728-739,共12页Computer Engineering & Science

基　　金：国家电网有限公司科技项目(52094024001D)。

摘　　要：近年来,图生成问题受到了广泛关注。通过学习真实图的分布,图生成技术能够生成与其具有相似特征的合成图,广泛应用于电子商务、电力网络等各个领域。在实际应用中,大多数图是动态变化的,图的拓扑结构会随着时间的推移发生改变。然而,现有的图生成器主要针对静态图进行设计,忽略了图的时序特征,而且现有的动态图生成模型普遍存在训练时间长的问题,难以处理规模庞大的动态图。为了解决这些问题,提出了一种新的基于深度对抗网络的动态图生成模型DGGAN。模型编码器利用图自注意力机制实现并行计算,从而提升模型的训练效率,并使用门控机制来控制信息流动,帮助模型更有效地学习和记忆关键信息。在6个动态图数据集上对DGGAN和具有代表性的图生成模型进行全面的实验评估,实验结果表明,DGGAN在生成图的质量和效率上优于现有模型。In recent years,the problem of graph generation has received widespread attention.By learning the distribution of real graphs,graph generation techniques can generate synthetic graphs with similar characteristics,which are widely used in various fields such as e-commerce and power networks.In practical applications,most graphs are dynamic,with their topological structures changing over time.However,existing graph generators are primarily designed for static graphs,neglecting the temporal characteristics of graphs.Additionally,current dynamic graph generation models generally suffer from long training times,making it difficult to handle large-scale dynamic graphs.To address these issues,a novel GAN-based model,called dynamic graph generative adversarial network(DGGAN),is proposed.The model's encoder employs a graph self-attention mechanism for parallel computation,thereby enhancing model training efficiency.A gating mechanism is used to control information flow,helping the model learn and memorize key information more effectively.Comprehensive experimental evaluations of DGGAN and representative graph generation methods were conducted on six dynamic graph datasets.The experimental results demonstrate that DGGAN outperforms existing models in terms of generated graphs quality and efficiency.

关 键 词：图生成 动态图 生成对抗网络 图自注意力机制 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]