首页 | 本学科首页   官方微博 | 高级检索  
     

基于注意力机制的规范化矩阵分解推荐算法
引用本文:张青博,王斌,崔宁宁,宋晓旭,秦婧.基于注意力机制的规范化矩阵分解推荐算法[J].软件学报,2020,31(3):778-793.
作者姓名:张青博  王斌  崔宁宁  宋晓旭  秦婧
作者单位:东北大学计算机科学与工程学院,辽宁沈阳 110189;东北大学计算机科学与工程学院,辽宁沈阳 110189;东北大学计算机科学与工程学院,辽宁沈阳 110189;东北大学计算机科学与工程学院,辽宁沈阳 110189;东北大学计算机科学与工程学院,辽宁沈阳 110189
基金项目:国家重点研发计划(2018YFB1700404);国家自然科学基金项资金(N171602003)
摘    要:近年来,矩阵分解(MF)技术因其有效性和简便性在推荐系统中得到广泛应用.但是,数据稀疏和冷启动问题导致MF学习到的用户特征向量不能准确地代表用户的偏好以及反映用户间的相似关系,影响了模型的性能.为了解决该问题,规范化矩阵分解(RMF)技术引起了研究者的关注.挖掘用户间可靠的相似关系,是RMF需要解决的问题.此外,MF将目标用户特征向量和目标项目特征向量的内积作为目标用户对目标项目的评分,这种简单的线性关系忽略了用户对项目各个属性特征不同的关注度.如何分析用户对项目属性特征的关注度,获取用户更准确的偏好,仍然是一个挑战.针对上述问题,提出了基于注意力机制的规范化矩阵分解模型(ARMF).具体地,为了获取用户间可靠的相似关系解决数据稀疏和冷启动问题,该模型同时依据用户信任网络和评分记录构建用户-项目异构网络,并基于该异构网络挖掘用户间的相似关系;为了进一步提升模型性能,通过在MF中引入注意力机制,分析用户对项目各个属性特征不同的关注度来获取用户更准确的偏好.最后,在两个真实数据集上对比ARMF与现有工作,实验结果证明,ARMF有更好的准确性和健壮性.

关 键 词:推荐系统  矩阵分解  数据稀疏  冷启动  社交网络  注意力机制
收稿时间:2019/8/13 0:00:00
修稿时间:2019/9/10 0:00:00

Attention-based Regularized Matrix Factorization for Recommendation
ZHANG Qing-Bo,WANG Bin,CUI Ning-Ning,SONG Xiao-Xu and QIN Jing.Attention-based Regularized Matrix Factorization for Recommendation[J].Journal of Software,2020,31(3):778-793.
Authors:ZHANG Qing-Bo  WANG Bin  CUI Ning-Ning  SONG Xiao-Xu and QIN Jing
Affiliation:School of Computer Science and Engineering, Northeastern University, Shenyang 110189, China,School of Computer Science and Engineering, Northeastern University, Shenyang 110189, China,School of Computer Science and Engineering, Northeastern University, Shenyang 110189, China,School of Computer Science and Engineering, Northeastern University, Shenyang 110189, China and School of Computer Science and Engineering, Northeastern University, Shenyang 110189, China
Abstract:In recent years, matrix factorization (MF) has been exploited commonly in recommender system because of its capability and simplification. However, data sparsity and cold-start problems make the latent feature of users learned by MF cannot represent the users'' preferences and the similarity relation among users exactly, which limits the performance of MF. To remedy it, the regularized matrix factorization (RMF) draws researchers'' attention. And the problem demanding prompt solution in RMF is capturing the reliable similarity relation among users. Besides, MF simply regards the inner product between the latent features of both target user and target item as the score the target user may rate the target item, ignoring the user''s different attentions on various features of the item. How to analyze the user''s attention on item''s features and capture more accurate preference of the user is still a challenge. To address these issues, we put forward a model named Attention-Based Regularized Matrix Factorization, abbreviated as ARMF. Specifically, to settle the problems of data sparsity and cold-start and obtain reliable similar relationships among users, the model builds a user-item heterogeneous network according to the social network and the rating record, and the similarities among users can be obtained basing on it. Incorporating attention mechanism into MF allows us to analyze the attention of users on different item''s features and capture moreaccurate preferences of users, which improves the precision of MF further. At last, we compare our proposed model with the state-of-the-art models on two real-world datasets and the result demonstrates the better precision and robustness of ARMF.
Keywords:recommender system  matrix factorization  data sparsity  cold-start  social network  attention mechanism
本文献已被 维普 万方数据 等数据库收录!
点击此处可从《软件学报》浏览原始摘要信息
点击此处可从《软件学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号