基于二分图划分联合聚类的协同过滤推荐算法

计算机工程与科学

基于二分图划分联合聚类的协同过滤推荐算法

黄乐乐1，马慧芳1,2，李宁3，余丽1

（1.西北师范大学计算机科学与工程学院，甘肃兰州 730070;

2.桂林电子科技大学广西可信软件重点实验室,广西桂林 541004;3.中国科学院信息工程研究所，北京 100093）

收稿日期:2018-09-03 修回日期:2019-04-08 出版日期:2019-11-25 发布日期:2019-11-25
基金资助:
国家自然科学基金(61762078,61363058,61802404,61762079,U1711263,U1811264);广西可信软件重点实验室研究课题(kx201910)

A collaborative filtering recommendation algorithm

based on bipartite graph partitioning co-clustering

HUANG Le-le1，MA Hui-fang1,2，LI Ning3，YU Li1

（1.College of Computer Science and Engineering,Northwest Normal University,Lanzhou 730070;

2.Guangxi Key Laboratory of Trusted Software,Guilin University of Electronic Technology,Guilin 541004;

3.Institute of Information Engineering,Chinese Academy of Sciences,Beijing 100093,China）

Received:2018-09-03 Revised:2019-04-08 Online:2019-11-25 Published:2019-11-25

摘要/Abstract

摘要：

准确而积极地向用户提供他们可能感兴趣的信息或服务是推荐系统的主要任务。协同过滤是采用得最广泛的推荐算法之一，而数据稀疏的问题往往严重影响推荐质量。为了解决这个问题，提出了基于二分图划分联合聚类的协同过滤推荐算法。首先将用户与项目构建成二分图进行联合聚类，从而映射到低维潜在特征空间；其次根据聚类结果改进2种相似性计算策略：簇偏好相似性和评分相似性，并将二者相结合。基于结合的相似性，分别采用基于用户和项目的方法来获得对未知目标评分的预测。最后，将这些预测结果进行融合。实验结果表明，所提算法比最新的联合聚类协同过滤推荐算法具有更好的性能。

关键词: 推荐系统, 协同过滤, 二分图划分联合聚类, 簇偏好相似性

Abstract:

To accurately and actively provide users with potentially interested information or services is the main task of a recommender system. Collaborative filtering is one of the most widely used recommendation algorithms, whereas it is suffering the issue of data sparsity that severely degrades recommendation quality. To address this issue, we propose a collaborative filtering recommendation algorithm based on bipartite graph partitioning co-clustering, called BPCF. Firstly, users and items are constructed into a bipartite graph for co-clustering, which is then mapped to the low-dimensional feature space. Then, the proposed algorithm computes the two types of improved similarities (cluster preference similarity and rating similarity) according to the clustering results and combines them. Based on the combined similarity, the user-based approach and item-based approach are adopted, respectively, to predict for an unknown target rating and these prediction results are fused. Experimental results show that the proposed method outperforms the state-of-the-art co-clustering collaborative filtering recommendation algorithms.

Key words: recommender system, collaborative filtering, bipartite graph partitioning co-clustering, cluster preference similarity

黄乐乐1，马慧芳1,2，李宁3，余丽1. 基于二分图划分联合聚类的协同过滤推荐算法[J]. 计算机工程与科学.

HUANG Le-le1，MA Hui-fang1,2，LI Ning3，YU Li1.

A collaborative filtering recommendation algorithm

based on bipartite graph partitioning co-clustering

[J]. Computer Engineering & Science.

参考文献［14］

［1］	Bhagavatula C,Feldman S,Power R,et al.Content-based citation recommendation［C］∥Proc of NAACL-HLT,2018:238-251.
［2］	Chen J, Zhang H,He X,et al.Attentive collaborative filtering:Multimedia recommendation with item-and component-level attention［C］∥Proc of International ACM SIGIR Conference on Research and Development in Information Retrieval,2017:335-344.
［3］	Alshammari G,Kapetanakis S,Alshammari A,et al.A hybrid feature combination method that improves recommendations［C］∥Proc of International Conference on Computational Collective Intelligence,2018:209-218.
［4］	Wei Su-yun,Xiao Jing-jing,Ye Ning.Collaborative filtering algorithm based on co-clustering smoothing［J］.Journal of Computer Research and Development,2013,50(s2):163-169.(in Chinese)
［5］	Xiong L,Chen X,Huang T K,et al.Temporal collaborative filtering with Bayesian probabilistic tensor factorization［C］∥Proc of SIAM Data Mining,2010:211-222.
［6］	Gong S.An efficient collaborative recommendation algorithm based on item clustering［C］∥Proc of Advances in Wireless Networks and Information Systems,2010:381-387.
［7］	Honda K, Oh C H,Matsumoto Y,et al.Exclusive partition in fcm-type co-clustering and its application to collaborative filtering［J］.International Journal of Computer Science and Network Security,2012,12(12):52-58.
［8］	Alqadah F,Reddy C,Hu J,et al.Biclustering neighborhood-based collaborative filtering method for top-n recommender systems［J］.Knowledge and Information Systems,2015,44(2):475-491.
［9］	Wei Hui-juan,Dai Mu-hong,Ning Yong-yu.Collaborative filtering recommendation algorithm based on nearest neighbor clustering［J］.Journal of University of Science & Technology of China,2016,46(9):736-742.(in Chinese)
［10］	Dhillon I.Co-clustering documents and words using bipartite spectral graph partitioning［C］∥Proc of the 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2001:269-274.
［11］	Liang C,Leng Y.Collaborative filtering based on information theoretic co-clustering［J］.International Journal of Systems Science,2014,45(3):589-597.
［12］	Liu Hua-feng,Jing Li-ping,Yu Jian.Survey of matrix factorization based recommendation methods by integrating
	social information［J］.Journal of Software,2018,29(2):340-362.(in Chinese)
［13］	Zhang Z, Kudo Y,Murai T.Neighbor selection for user-based collaborative filtering using covering-based rough sets［J］.Annals of Operations Research,2017,256(2):359-374.
［14］	Cheng Fei,Jia Cai-yan.An improved collaborative filtering algorithm based on user similarity［J］.Computer Engineering & Science,2013,35(5):161-165.(in Chinese)
	附中文参考文献：
［4］	韦素云,肖静静,业宁.基于联合聚类平滑的协同过滤算法［J］.计算机研究与发展,2013,50(s2):163-169.
［9］	魏慧娟,戴牡红,宁勇余.基于最近邻居聚类的协同过滤推荐算法［J］.中国科学技术大学学报,2016,46(9):736-742.
［12］	刘华锋,景丽萍,于剑.融合社交信息的矩阵分解推荐方法研究综述［J］.软件学报,2018,29(2):340-362.
［14］	程飞,贾彩燕.一种基于用户相似性的协同过滤推荐算法［J］.计算机工程与科学,2013,35(5):161-165.

[1]	高玮蔚, 刘杨, 马慧芳, 唐月晨. 基于增强偏好影响力的图注意力网络推荐算法[J]. 计算机工程与科学, 2023, 45(07): 1300-1307.
[2]	王玫申, 张鹏, 薛乐洋, . 基于二分网络的长期推荐[J]. 计算机工程与科学, 2023, 45(04): 691-700.
[3]	罗可劲, 刘广聪, 杨文浩. 基于多任务学习的图神经网络推荐模型研究[J]. 计算机工程与科学, 2023, 45(04): 726-733.
[4]	张若一, 金柳, 马慧芳, 王亦可, 李清风. 融合相似用户影响效应的知识图谱推荐模型[J]. 计算机工程与科学, 2023, 45(03): 520-527.
[5]	邹程辉, 李卫疆, . 融合知识图谱和评论文本的个性化推荐模型[J]. 计算机工程与科学, 2023, 45(01): 181-190.
[6]	贾俊杰, 姚叶旺, 陈旺虎. 基于非负矩阵分解的群组推荐算法[J]. 计算机工程与科学, 2022, 44(05): 933-943.
[7]	贾俊杰, 段超强. 基于评分离散度的托攻击检测算法[J]. 计算机工程与科学, 2022, 44(03): 554-562.
[8]	阎红灿, 王子茹, 李伟芳, 谷建涛. 伴随时间的模糊聚类协同过滤推荐算法[J]. 计算机工程与科学, 2021, 43(11): 2084-2090.
[9]	陈海龙, 闫五岳, 孙海娇, 程苗. 标签扩展的协同过滤推荐算法[J]. 计算机工程与科学, 2021, 43(10): 1826-1832.
[10]	顾军华, 佘士耀, 樊帅, 张素琪. 基于用户长短期兴趣与知识图卷积网络的推荐[J]. 计算机工程与科学, 2021, 43(03): 511-517.
[11]	陈海涵, 吴国栋, 李景霞, 王静雅, 陶鸿. 基于注意力机制的深度学习推荐研究进展[J]. 计算机工程与科学, 2021, 43(02): 370-380.
[12]	杨丰瑞, 李前洋, 罗思烦, . 一种基于降噪自编码器的隐式反馈推荐算法[J]. 计算机工程与科学, 2020, 42(08): 1500-1505.
[13]	张瑞典，钱晓东. 用余弦相似度修正评分的协同过滤推荐算法[J]. 计算机工程与科学, 2020, 42(06): 1096-1105.
[14]	杨丰瑞, 李前洋, 罗思烦, . 基于降噪自编码器的社会化推荐算法[J]. 计算机工程与科学, 2020, 42(05): 944-950.
[15]	袁泉1,2,3,成振华1,2,江洋1,2. 基于知识图谱和协同过滤的电影推荐算法研究[J]. 计算机工程与科学, 2020, 42(04): 714-721.