基于全局图扩散和时空感知的解缠绕会话推荐方法  

Session recommendation method based on global graph diffusion andspatio-temporal awareness disentanglement

作　　者：高榕 周浩 邵雄凯[1] 吴歆韵 Gao Rong;Zhou Hao;Shao Xiongkai;Wu Xinyun(School of Computer Science,Hubei University of Technology,Wuhan 430068,China;State Key Laboratory of New Computer Software Technology,Nanjing University,Nanjing 210093,China)

机构地区：[1]湖北工业大学计算机学院,武汉430068 [2]南京大学计算机软件新技术国家重点实验室,南京210093

出　　处：《计算机应用研究》2023年第11期3294-3302,共9页Application Research of Computers

基　　金：国家自然科学基金资助项目(61902116);南京大学计算机软件新技术国家重点实验室开放课题(KFKT2021B12);湖北省高层次人才基金资助项目(GCRC2020011);湖北工业大学博士科研启动基金资助项目(BSQD2019026,BSQD2019022)。

摘　　要：针对会话推荐中存在的推荐性能不足的问题,提出了一种采用全局图扩散和时空感知的解缠绕图神经网络模型(GDST-GNN)。具体来说,该模型首先基于所有会话从全局视角下构建全局协同图,然后采用图扩散作为项目的全局表示学习的消息传播范式,以捕获超越当前会话外的全局信息。对于当前会话的表示学习,设计了一种解缠绕时空门控网络建模会话中项目的复杂转换模式和时序依赖模式,然后将学习到的全局表征和局部表征逐因素融合。此外,还采用了一个自监督任务实现模型的性能增强。最后,通过注意力网络生成会话表示,实现了项目的准确推荐。在四个真实世界中的数据集进行广泛的实验验证了所提出模型的有效性。To address the problem of insufficient recommendation performance in session recommendation,this paper proposed a disentangled graph neural network model(GDST-GNN)using global graph diffusion and spatio-temporal awareness.Specifically,the model firstly constructed a global collaborative graph based on all sessions from a global perspective,and then employed graph diffusion as the message propagation paradigm for global representation learning of items to capture global information beyond the current session.For the representation learning of the current session,this paper designed a disentangled spatio-temporal gated network modeling the complex transition pattern and temporal dependency pattern of items in the session,and then fused the learned global and local representations factor by factor.In addition,this paper employed a self-supervised task to achieve performance enhancement of the model.Finally,it generated session representations through attention networks to achieve accurate recommendation of items.Extensive experiments on four real-world datasets validate the effectiveness of the proposed model.

关 键 词：推荐系统 深度学习 图神经网络 时序模式 用户意图 

分 类 号：TP391.3[自动化与计算机技术—计算机应用技术]