基于GT模型的多编码下一个兴趣点推荐模型  

Multi-coding next point of interest recommendation model based on GT model

作　　者：王永贵[1] 张小锐 Wang Yonggui;Zhang Xiaorui(College of Electronics&Information Engineering,Liaoning Technical University,Huludao Liaoning 125105,China)

机构地区：[1]辽宁工程技术大学电子与信息工程学院,辽宁葫芦岛125105

出　　处：《计算机应用研究》2024年第11期3382-3388,共7页Application Research of Computers

基　　金：国家自然科学基金面上项目(61772249);辽宁省教育厅科学研究经费资助项目(LJKZ0355)。

摘　　要：下一个兴趣点推荐是推荐算法领域的热点,旨在为用户推荐适合的下一地点。较新的研究通过图和序列方法模拟用户与POI的交互以及POI之间转换关系,性能得到显著提升。然而,现有模型仍然存在需要解决的问题。针对现有的下一个兴趣点推荐模型的局限性,特别是如何充分捕捉User-POI交互图上全局和局部信息,以及缓解图神经网络的过平滑特性导致图上信息丢失的问题,提出了基于graph Transformer的多编码模型(multi-coding network based on GT model)对下一个兴趣点进行推荐。首先,从位置和结构的视角上联合对user-POI交互图上进行全局、局部以及相对信息进行编码;然后,将编码后生成的图嵌入通过graph Transformer网络层更新图上节点与边信息;最后通过MLP网络层生成预测;最终,MCGT在Gowalla和TKY两个公开数据集进行对比实验。结果表明,在Gowalla数据集上recall和NDCG指标至少有3.79%的提升,在TKY数据集上recall和NDCG指标至少有2.5%的提升,证明了MCGT设计的合理性与有效性。Next point of interest(POI)recommendation is a hot topic in the field of recommendation algorithms,which aims at recommending the suitable next locations for users.Recent research has significantly improved performance by simulating user interactions with POIs and the transitions between POIs using graph and sequence methods.However,existing models still have issues that need to be addressed.In response to the limitations of current next POI recommendation models,particularly in how to fully capture both global and local information on the user-POI interaction graph,and in alleviating the oversmoothing characteristics of graph neural networks that lead to information loss on the graph,this paper proposed a multi-coding network based on the graph Transformer model for recommending the next POI.Firstly,it jointly encoded global,local,and relative information on the user-POI interaction graph from the perspectives of position and structure.Then,the graph embeddings produced by this encoding were updated through graph Transformer network layers,which refreshed the information of nodes and edges on the graph.Finally,predictions were generated through MLP network layers.The MCGT model was empirically tested on two public datasets,Gowalla and TKY.The results show that at least a 3.79%improvement in recall and NDCG metrics on the Gowalla dataset and at least a 2.5%improvement on the TKY dataset,thus proving the reasonableness and effectiveness of MCGT.

关 键 词：下一个兴趣点推荐 多编码 全局信息 局部信息 相对信息 图Transformer 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]