Journal of Computer Applications ›› 2016, Vol. 36 ›› Issue (6): 1594-1598.DOI: 10.11772/j.issn.1001-9081.2016.06.1594

Previous Articles     Next Articles

Co-clustering recommendation algorithm based on parallel factorization decomposition

DING Xiaohuan, PENG Furong, WANG Qiong, LU Jianfeng   

  1. School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing Jiangsu 210094, China
  • Received:2015-12-11 Revised:2016-02-26 Online:2016-06-10 Published:2016-06-08
  • Supported by:
    This work is partially supported by the Construction Project of Dominate Subjects in Colleges and Universities in Jiangsu, the Jiangsu "Six Talent Peaks" High Level Talent Project.

基于平行因子分解的协同聚类推荐算法

丁小焕, 彭甫镕, 王琼, 陆建峰   

  1. 南京理工大学 计算机科学与工程学院, 南京 210094
  • 通讯作者: 丁小焕
  • 作者简介:丁小焕(1991-),女,浙江衢州人,硕士研究生,主要研究方向:数据挖掘;彭甫镕(1987-),男,贵州遵义人,博士研究生,主要研究方向:数据挖掘、推荐系统;王琼(1981-),女,江苏南京人,副教授,博士,主要研究方向:模式识别、智能系统;陆建峰(1969-),男,江苏淮安人,教授,博士,主要研究方向:智能系统、数据挖掘。
  • 基金资助:
    江苏高校优势学科建设工程资助项目;江苏省"六大人才高峰" 高层次人才项目。

Abstract: Aiming at the complexity of triple data's inner relation, a co-clustering recommendation model based on the PARAllel FACtorization (PARAFAC) decomposition was proposed. The PARAFAC was used for tensor decomposition to mine the relevant relations and potential topics between the entities of multidimensional data. Firstly, triple tensor data was clustered by using the PARAFAC decomposition algorithm. Secondly, three recommendation models for different schemes were proposed based on collaborative clustering algorithm, and compared for obtaining the optimal recommendation model through the experiment. Finally, the proposed co-clustering recommendation model was compared with Higher Order Singular Value Decomposition (HOSVD) model. Compared to the HOSVD tensor decomposition algorithm, the PARAFAC collaborative clustering algorithm increased the recall rate and precision by 9.8 percentage points and 3.7 percentage points on average on the last.fm data set, and increased the recall rate and precision by 11.6 percentage points and 3.9 percentage points on average on the delicious data set. The experimental results show that the proposed algorithm can effectively dig out tensor potential information and internal relations, and achieve recommendation with high accuracy and high recall rate.

Key words: tag, tensor decomposition, collaborative clustering, recommendation system, PARAllel FACtorization(PARAFAC) decomposition

摘要: 针对三元组数据内在关联性复杂的特点,提出了基于平行因子分解(PARAFAC)的协同聚类推荐算法。该算法利用PARAFAC算法对张量进行分解,挖掘多维数据实体之间的相关联系和潜在主题。首先,利用PARAFAC分解算法对三元组张量数据进行聚类;然后,基于协同聚类算法提出了三种不同方案的推荐模型,并通过实验对三种方案进行了比较,得到了最优的推荐模型;最后,将提出的协同聚类模型与基于高阶奇异值分解(HOSVD)的推荐模型进行比较。在last.fm数据集上,PARAFAC协同聚类算法比HOSVD张量分解算法在召回率和精确度上平均提高了9.8个百分点和3.7个百分点,在delicious数据集上平均提高了11.6个百分点和3.9个百分点。实验结果表明所提算法能更有效地挖掘出张量中的潜在信息和内在联系,实现高准确率和高召回率的推荐。

关键词: 标签, 张量分解, 协同聚类, 推荐系统, 平行因子分解

CLC Number: