计算机应用 ›› 2018, Vol. 38 ›› Issue (7): 1866-1871.DOI: 10.11772/j.issn.1001-9081.2017123060

• 人工智能 • 上一篇    下一篇

基于堆栈降噪自编码器改进的混合推荐算法

杨帅1, 王鹃2   

  1. 1. 国家多媒体软件工程技术研究中心(武汉大学 计算机学院), 武汉 430072;
    2. 空天信息安全与可信计算教育部重点实验室(武汉大学 计算机学院), 武汉 430072
  • 收稿日期:2017-12-29 修回日期:2018-02-26 出版日期:2018-07-10 发布日期:2018-07-12
  • 通讯作者: 杨帅
  • 作者简介:杨帅(1993-),男,山东枣庄人,硕士研究生,主要研究方向:通信与信息系统、模式识别;王鹃(1980-),女,湖北武汉人,副教授,博士,主要研究方向:系统与网络安全、访问控制、可信计算、云计算、SDN安全。
  • 基金资助:
    国家自然科学基金资助项目(61402342)。

Improved hybrid recommendation algorithm based on stacked denoising autoencoder

YANG Shuai1, WANG Juan2   

  1. 1. National Engineering Research Center for Multimedia Software(School of Computer Science, Wuhan University), Wuhan Hubei 430072, China;
    2. Key Laboratory of Aerospace Information Security and Trusted Computing, Ministry of Education(School of Computer Science, Wuhan University), Wuhan Hubei 430072, China
  • Received:2017-12-29 Revised:2018-02-26 Online:2018-07-10 Published:2018-07-12
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61402342).

摘要: 针对传统协同过滤算法仅利用评分信息作为推荐依据,没有利用用户评论和标签信息,无法准确反映用户对项目特征的偏好,推荐精确度低且容易过拟合等问题,提出一种基于堆栈降噪自编码(SDAE)改进的混合推荐(SDHR)算法。首先利用深度学习模型SDAE从用户自由文本标签中抽取项目的显式特征信息;然后,改进隐因子模型(LFM)算法,使用显式项目特征信息替换LFM中的抽象特征,进行矩阵分解训练;最后通过用户-项目偏好矩阵为用户提供推荐。在公开数据集MovieLens上的实验测试,与三组推荐模型(基于标签权重及协同过滤、基于SDAE和极限学习机、基于循环神经网络)比较,该算法推荐精确度分别提高了45.2%、38.4%和16.1%。实验结果表明,所提算法可以充分利用项目自由文本标签信息提高推荐性能。

关键词: 推荐系统, 协同过滤, 深度学习, 堆栈降噪自编码器, 隐因子模型

Abstract: Concerning the problem that traditional collaborative filtering algorithm just utilizes users' ratings on items when generating recommendation, without considering users' labels or comments, which can not reflect users' real preference on different items and the prediction accuracy is not high and easily overfits, a Stacked Denoising AutoEncoder (SDAE)-based improved Hybrid Recommendation (SDHR) algorithm was proposed. Firstly, SDAE was used to extract items' explicit features from users' free-text labels. Then, Latent Factor Model (LFM) algorithm was improved, the LFM's abstract item features were replaced with extracted explicit ones to train matrix decomposition model. Finally, the user-item preference matrix was used to generate recommendations. Experimental tests on the dataset MovieLens showed that the accuracy of the proposed algorithm was improved by 38.4%, 16.1% and 45.2% respectively compared to the three recommendation models (including the model based on label-based weights with collaborative filtering, the model based on SDAE and extreme learning machine, and the model based on recurrent neural networks). The experimental results show that the proposed algorithm can make full use of items' free-text label information to improve recommendation performance.

Key words: recommendation system, collaborative filtering, deep learning, Stacked Denoising AutoEncoder (SDAE), Latent Factor Model (LFM)

中图分类号: