基于二分图卷积表示的推荐算法  

Recommendation Algorithm Based on Bipartite Graph Convolution Representation

作　　者：熊旭东 杜圣东[1,2,3] 夏琬钧 李天瑞 XIONG Xu-dong;DU Sheng-dong;XIA Wan-jun;LI Tian-rui(School of Information Science and Technology,Southwest Jiaotong University,Chengdu 611756,China;Institute of Artificial Intelligence,Southwest Jiaotong University,Chengdu 611756,China;National Engineering Laboratory of Integrated Transportation Big Data Application Technology,Chengdu 611756,China)

机构地区：[1]西南交通大学信息科学与技术学院,成都611756 [2]西南交通大学人工智能研究院,成都611756 [3]综合交通大数据应用技术国家工程实验室,成都611756

出　　处：《计算机科学》2021年第4期78-84,共7页Computer Science

基　　金：国家重点研发计划(2017YFB1401400)。

摘　　要：随着数据驱动智能技术的快速发展,个性化推荐算法及相关应用成为了研究热点。推荐可视为将用户与物品进行匹配的问题,但用户与物品之间存在的语义差距不便于两者之间的直接匹配。现有的许多基于深度学习的推荐算法采用的思路都是将不同空间中的实体映射到统一潜在语义空间,利用其嵌入表示来进行匹配度计算。随着网络表示学习方法的出现,由于用户和物品的交互可构成二分图,用户和物品的嵌入表示可被视作二分图节点表示,许多基于二分图节点表示的推荐算法被提出,但现有算法仍难以对高阶交互信息进行有效提取。针对这一问题,文中提出了一种基于二分图卷积表示学习的推荐算法BGCRRA(Bipartite Graph Convolution Representation-based Recommendation Algorithm)。该算法首先将用户和物品交互视作二分图,然后通过实现自适应融合多阶、多层次的图卷积模型来对节点进行嵌入表示,最后计算用户和物品的匹配度,并实现推荐。文中在3个公开的数据集上进行对比实验,通过将该算法与当前表现优异的算法进行HR和NDCG(Normalized Discounted Cumulative Gain)指标的比较分析,验证了所提推荐算法的有效性。With the rapid development of data-driven intelligent technology,personalized intelligent recommendation algorithms and related applications become research hotspots.Recommendation can be regarded as a matching problem between users and items.As the semantic gap between users and items,it’s inconvenient to match them directly.Many existing recommendation methods based on deep learning use the idea of mapping entities from different spaces into a unified semantic space to calculate the matching degree by embedding representation.With the emergence of network representation learning,the bipartite graph can be formed between users and items and the embedding representation in the recommendation algorithm can also be regarded as nodes representation in bipartite graph.Many recommendation algorithms based on bipartite graph nodes representation have been proposed.However,existing algorithms are still hard to extract high-order interactive information effectively.To solve this problem,a bipartite graph convolution representation-based recommendation algorithm(BGCRRA)is developed in this paper.Interactions between users and items are regarded as a bipartite graph at first,nodes are represented by adaptively fusing multi-order and multi-level graphs secondly,and finally the matching degree of users and items is calculated and the recommendation is realized.Comparative experiments are carried out on 3 open datasets and the effectiveness of the proposed algorithm is verified by comparing HR and NDCG(Normalized Discounted Cumulative Gain)indexes of our algorithm and the state-of-the-art algorithms.

关 键 词：推荐算法 嵌入方法 图卷积 二分图 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]