基于知识图谱与邻域感知注意力机制的推荐算法研究  

Study on Recommendation Algorithms Based on Knowledge Graph and Neighbor Perception Attention Mechanism

作　　者：陈珊珊[1] 姚苏滨 CHEN Shanshan;YAO Subin(School of Computer Science,Nanjing University of Posts and Telecommunications,Nanjing 210003,China)

机构地区：[1]南京邮电大学计算机学院/软件学院/网络空间安全学院,南京210003

出　　处：《计算机科学》2024年第8期313-323,共11页Computer Science

摘　　要：为解决传统推荐算法在面对数据稀疏的推荐任务时产生的冷启动问题,本研究将知识图谱引入推荐算法,结合一种新的邻域感知注意力机制代替传统图注意力机制来挖掘实体间的高阶连通信息,提出了基于知识图谱和邻域感知注意力机制的推荐模型KGNPAN。得益于知识图谱可使推荐具有精准、多样和可解释的特点,该模型能够很好地缓解数据稀疏与冷启动问题。首先利用基于自对抗负采样的图嵌入方法RotatE对原有物品和用户表征的语义信息进行扩充,将实体和关系向量映射成低维嵌入向量;其次,根据协同邻居的不同类型分别应用邻域感知注意力机制聚合邻居节点信息,丰富目标节点语义,并以卷积形式递归挖掘高阶连通信息;最后对用户与项目向量应用内积操作计算交互概率,得到推荐结果。在Amazon-book和Last-FM两个公共基准数据集上进行实验,结果表明,在与CKE,BPRMF,RippleNet,KGAT,KGCN和CAKN 6个基准模型的对比中,KGNPAN相较于基准模型中结果最优的CAKN模型,在召回率(Recall)上分别提升了1.30%和1.37%,在归一化折损累计增益上(NDCG)分别提升了1.26%和1.14%,充分验证了其有效性和可解释性。In order to solve the cold start problem caused by traditional recommendation algorithms when they face the recommendation task with sparse data,this paper introduces the knowledge graph into the recommendation algorithm,combing a new neighbor perception attention mechanism to replace the traditional graph attention mechanism to mine the higher-order connected information between entities,and proposes a recommendation model KGNPAN based on the knowledge graph and neighbor perce-ption attention mechanism.Thanks to the knowledge graph,recommendations can be accurate,diverse and interpretable.This model can effectively alleviate issues of data sparsity and cold start.Firstly,this model utilizes the graph embedding method RotatE based on self adversarial negative sampling to expand the semantic information of the original item and user representations,mapping entity and relationship vectors into low dimensional embedding vectors.Secondly,based on the different types of collaborative neighbors,neighbor perception attention mechanisms are applied to aggregate neighbor node information,enrich the semantics of target nodes,and recursively mine high-order connected information in convolutional form.Finally,the inner product operation is applied to calculate the interaction probability between the user and the project vector,and the recommendation result is obtained.Experiments are conducted on two common benchmark datasets,Amazon-book and Last-FM,and compared with six benchmark models,namely CKE,BPRMF,RippleNet,KGAT,KGCN,and CAKN,KGNPAN.The results show that KGNPAN improves the recall rate by 1.30%and 1.37%,and normalized discounted cumulative gain(NDCG)increases by 1.26%and 1.14%,respectively,compared with CAKN model,which has the best performance in the benchmark modes,verifying the effectiveness and interpretability of the model.

关 键 词：推荐算法 邻域感知注意力机制 知识图谱 图神经网络 冷启动 

分 类 号：TP181[自动化与计算机技术—控制理论与控制工程]