完全图高阶关系驱动的链接预测  

Link Prediction Driven by High-Order Relations in Complete Graph

作　　者：张惠鹃 黄钦阳 胡诗彦 杨青[2] 张敬伟[1] Zhang Huijuan;Huang Qinyang;Hu Shiyan;Yang Qing;Zhang Jingwei(Guangxi Key Laboratory of Trusted Software(Guilin University of Electronic Technology),Guilin,Guangxi 541004;Guangxi Key Laboratory of Automatic Detecting Technology and Instruments(Guilin University of Electronic Technology),Guilin,Guangxi 541004;School of Computer Science and Information Security,Guilin University of Electronic Technology,Guilin,Guangxi 541004)

机构地区：[1]广西可信软件重点实验室(桂林电子科技大学),广西桂林541004 [2]广西自动检测技术与仪器重点实验室(桂林电子科技大学),广西桂林541004 [3]桂林电子科技大学计算机与信息安全学院,广西桂林541004

出　　处：《计算机研究与发展》2024年第7期1825-1835,共11页Journal of Computer Research and Development

基　　金：国家自然科学基金项目(62267002,62167002,61862013);广西重点研发计划项目(桂科AB22080047);广西可信软件重点实验室主任基金重点课题(KX202317);广西自动检测技术与仪器重点实验室主任基金课题(YQ21102)。

摘　　要：图卷积网络(graph convolutional network,GCN)因其在处理图数据方面的独特优势而被广泛应用于推荐系统中,它通过利用图中节点之间的依赖关系传播节点属性信息,极大地提高了节点表示的准确度从而提升推荐性能.然而现有基于GCN的推荐方法仍因过平滑问题而难以进行更深层的建模,从而限制了用户与项目间高阶关系的表达.为此,提出了一种基于项目间关系的完全图高阶关系驱动的链接预测(link prediction driven by high-order relations in complete graph,LinkCG)方法.LinkCG通过用户-项目交互图与项目间隐式关联关系全局图组成的异构图预测用户到项目的链接,跳过了中间的用户节点直接利用完全图建模每个用户历史交互的项目间的局部隐式关联关系,获得项目间的高阶关系从而缓解数据稀疏性问题;此外,不同于基于节点嵌入的推荐方法,LinkCG通过赋予项目间的链接权重来表示项目间关系的紧密程度,并根据紧密程度进行链接预测,优化了模型的训练过程.在3个公开数据集上的实验结果表明,LinkCG作为只包含2个超参数的非深度学习模型,与一些先进的基于深度学习的基线方法相比提供了更好的性能.在社交关系数据上的应用进一步表明LinkCG能够从用户历史交互项目中获取足够丰富的用户偏好信息.Graph convolutional network(GCN)has been widely used in recommendation systems due to its unique advantages in processing graph data.GCN propagates node attribute information by exploiting the dependencies between nodes in the graph,which greatly improves the accuracy of node representation and thus improves recommendation performance.However,existing GCN-based recommendation methods still have difficulty in modeling deeper layers due to the over-smoothing problem,which limits the representation of higher-order relationships between users and items.To this end,we propose a novel link prediction method driven by high-order relations among items in complete graph(short for LinkCG).The LinkCG method utilizes a heterogeneous graph consisting of a user-item interaction graph and a global graph representing implicit item associations to predict useritem links.By directly modeling item associations based on user interactions,LinkCG captures higher-order relationships and mitigates the issue of data sparsity.In addition,unlike node embedding-based methods,LinkCG improves the training process and enhances recommendation accuracy by assigning link weights that represent the degree of item association.Experimental results on three publicly available datasets show that LinkCG method,as a non-deep learning model containing only two hyperparameters,provides better performance compared with the deep learning-based baseline methods.The application on social relationship data further demonstrates LinkCG can capture rich enough information about user preferences from their historical interaction items.

关 键 词：推荐系统 链接预测 完全图 高阶关系 关联关系 

分 类 号：TP274[自动化与计算机技术—检测技术与自动化装置] TP301[自动化与计算机技术—控制科学与工程]