ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2017, Vol. 54 ›› Issue (8): 1853-1863.doi: 10.7544/issn1000-1239.2017.20170344

所属专题: 2017人工智能前沿进展专题

• 人工智能 • 上一篇    



  1. 1(南京邮电大学计算机学院 南京 210023);2(江苏省无线传感网高技术研究重点实验室 南京 210003);3(江苏省大数据安全与智能处理重点实验室 南京 210023) (
  • 出版日期: 2017-08-01
  • 基金资助: 

Latent Group Recommendation Based on Dynamic Probabilistic Matrix Factorization Model Integrated with CNN

Wang Haiyan1,2,3, Dong Maowei1   

  1. 1(School of Computer Science, Nanjing University of Posts and Telecommunications, Nanjing 210023);2(Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks, Nanjing 210003);3(Jiangsu Key Laboratory of Big Data Security & Intelligence Processing, Nanjing 210023)
  • Online: 2017-08-01

摘要: 近年来,群组推荐由于其良好的实用价值得到了广泛关注.然而,已有的群组推荐方法大多都是根据分析用户对服务的评分矩阵直接将个体用户的推荐结果或个体用户偏好进行聚合,没有综合地考虑用户-群组-服务这三者间的联系,导致群组推荐效果欠佳.受潜在因子模型与状态空间模型启发,结合评分矩阵、服务描述文档以及时间因素,共同分析用户-群组-服务间的联系,提出了一种基于动态卷积概率矩阵分解的群组推荐方法.该方法首先利用基于卷积神经网络的文本表示方法获取服务潜在特征模型的先验分布;然后,将状态空间模型与概率矩阵分解模型相结合,获得用户潜在偏好向量与服务特征向量;之后,对用户偏好向量运用聚类算法来发现潜在的群组;最终,对群组中的用户偏好采取均值策略融合成群组偏好向量,并与服务特征向量共同生成群组对服务的评分,实现群组推荐.通过在MovieLens数据集上与同类方法进行对比实验,发现所提方法的推荐有效性与精确性上更具有优势.

关键词: 卷积神经网络, 概率矩阵分解, 状态空间模型, 聚类算法, 群组推荐

Abstract: Group recommendation has recently received great attention in the academic sector due to its significant utility in real applications. However, the available group recommendation methods mainly aggregate individual recommendation results or personal preferences directly based on an analysis of rating matrix. The relationship among users, groups, and services has not been taken into comprehensive consideration during group recommendation, which will interfere with the accuracy of recommendation results. Inspired by latent factor model and state space model, we propose a latent group recommendation (LGR) based on dynamic probabilistic matrix factorization model integrated with convolutional neural network (DPMFM-CNN), which comprehensively investigates rating matrix, service description documents and time factor and makes a joint analysis of the relationship among those three entities. The proposed LGR method firstly obtains a prior distribution for service latent factor model with the employment of text representation method based on convolutional neural network (CNN). Secondly, it integrates state space model with probabilistic matrix factorization model and draws user latent vector together with service latent vector. Thirdly, latent groups are detected through the use of multiple clustering algorithms on user latent vectors. Finally, group latent vectors are aggregated with average strategy and group rating can be generated. In addition, simulation on MovieLens is performed and comparison results demonstrate that LGR has better performance in efficiency and accuracy for group recommendation.

Key words: convolutional neural network, probabilistic matrix factorization, state space model, clustering algorithms, group recommendation