基于自注意力机制的局部与全局特征融合的评分预测算法  

Rating prediction algorithm based on self-attention mechanism and fusion of local&global features

作　　者：伊磊 纪淑娟[1] Yi Lei;Ji Shujuan(Shandong Provincial Key Laboratory of Wisdom Mine Information Technology,Shandong University of Science&Technology,Qingdao Shandong 266590,China;Dept.of Personnel,Shandong Jianzhu University,Jinan 250101,China)

机构地区：[1]山东科技大学山东省智慧矿山信息技术重点实验室,山东青岛266590 [2]山东建筑大学人事处,济南250101

出　　处：《计算机应用研究》2022年第5期1337-1342,共6页Application Research of Computers

基　　金：国家自然科学基金资助项目(71772107)。

摘　　要：为了完全挖掘异质信息网络中节点的特征并且更好地融合这些特征,提高推荐算法的性能,提出一种基于自注意力机制的局部与全局特征融合的评分预测算法(rating prediction algorithm based on self-attention mechanism and fusion of local&global features,AMFL&GRec)。首先基于LeaderRank算法提取目标节点的全局序列,基于元路径带偏置的随机游走算法提取节点的局部序列,通过skip-gram模型分别学习节点的全局特征与局部特征;通过自注意力机制学习目标节点对局部与全局特征的偏好,从而得到在单一元路径下节点的特征表示;再通过自注意力机制融合不同元路径下同一节点的表示,从而得到节点在不同元路径下的最终特征表示;最后基于多层感知器实现评分预测任务。在两个真实数据集进行了大量实验,实验结果验证了AMFL&GRec算法不仅能够捕获具有密集连通节点的微观(局部)结构,而且还能够捕获该节点在网络中的全局结构,从而使其得到的节点特征得以体现节点的整体(局部+全局)特征。同时,实验结果也证明了AMFL&GRec算法评分预测性能优于对比算法,从而证明利用自注意力机制考虑异质信息网络中节点对于局部、全局特征以及元路径的偏好能够提高评分预测的准确性。In order to fully mine nodes’features and better integrate these features simultaneously in the heterogeneous information network,this paper proposed a AMFL&GRec.Firstly,AMFL&GRec used the LeaderRank algorithm to extract the target node’global sequence,and used a meta-path-based heterogeneous information network embedding model to extract the node’local sequence,and used the skip-gram model to learn the node’global and local features.And then it used the self-attention mechanism to learn the preference of the target nodes’local and global features to obtain the feature representation of the target node in a single meta-path.Secondly,it used the self-attention mechanism to fuse the representation of the same node under different meta-paths to obtain the final feature representation.Finally,it utilized a multi-layer perceptron to achieve the task of rating prediction.This paper conducted a large number of experiments on two real datasets.The experimental results verify that the AMFL&GRec algorithm can not only capture the micro(local)structure of densely connected nodes,but also capture the global structure of the node in the network,and finally obtain nodes’overall(local+global)characteristics.At the same time,the experimental results also prove that the AMFL&GRec’s rating prediction performance is better than the baselines.It proves that in the heterogeneous information network utilizing the self-attention mechanism to consider the nodes’preferences for local and global features and meta-paths can improve the accuracy of rating prediction.

关 键 词：异质信息网络 网络表示学习 注意力机制 评分预测 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]