Journal of Computer Applications ›› 2020, Vol. 40 ›› Issue (12): 3445-3450.DOI: 10.11772/j.issn.1001-9081.2020061023

• 2020 China Conference on Granular Computing and Knowledge Discovery(CGCKD 2020) • Previous Articles     Next Articles

Collaborative filtering recommendation algorithm based on dual most relevant attention network

ZHANG Wenlong1,2, QIAN Fulan1,2, CHEN Jie1,2, ZHAO Shu1,2, ZHANG Yanping1,2   

  1. 1. School of Computer Science and Technology, Anhui University, Hefei Anhui 230601, China;
    2. Key Laboratory of Intelligent Computing&Signal Processing, Ministry of Education(Anhui University), Hefei Anhui 230601, China
  • Received:2020-06-12 Revised:2020-09-16 Online:2020-12-10 Published:2020-10-20
  • Supported by:
    This work is partially supported by the National Natural Science Foundation of China (61702003), the Natural Science Foundation of Anhui Province (1808085MF175).

基于双重最相关注意力网络的协同过滤推荐算法

张文龙1,2, 钱付兰1,2, 陈洁1,2, 赵姝1,2, 张燕平1,2   

  1. 1. 安徽大学 计算机科学与技术学院, 合肥 230601;
    2. 计算智能与信号处理教育部重点实验室(安徽大学), 合肥 230601
  • 通讯作者: 钱付兰(1978-),女,安徽蚌埠人,副教授,博士,主要研究方向:粒计算、社交网络、推荐系统。qianfulan@hotmail.com
  • 作者简介:张文龙(1996-),男,安徽阜阳人,硕士研究生,主要研究方向:深度学习、推荐系统;陈洁(1982-),女,安徽巢湖人,副教授,博士,主要研究方向:智能计算、机器学习、三支决策;赵姝(1979-),女,安徽巢湖人,教授,博士,主要研究方向:粒计算、商空间理论、机器学习;张燕平(1962-),女,安徽合肥人,教授,博士,主要研究方向:智能计算、粒计算、商空间理论
  • 基金资助:
    国家自然科学基金资助项目(61702003);安徽省自然科学基金资助项目(1808085MF175)。

Abstract: Item-based collaborative filtering learns user preferences from the user's historical interaction items and recommends similar new items based on the user's preferences. The existing collaborative filtering methods assume that a set of historical items that user has interacted with have the same impact on user, and all historical interaction items are considered to have the same contribution to the prediction of target item, which limits the accuracy of these recommendation methods. In order to solve the problems, a new collaborative filtering recommendation algorithm based on dual most relevant attention network was proposed, which contained two attention network layers. Firstly, the item-level attention network was used to assign different weights to different historical items in order to capture the most relevant items in the user historical interaction items. Then, the item-interaction-level attention network was used to perceive the correlation degrees of the interactions between the different historical items and the target item. Finally, the fine-grained preferences of users on the historical interaction items and the target item were simultaneously captured through the two attention network layers, so as to make the better recommendations for the next step. The experiments were conducted on two real datasets of MovieLens and Pinterest. Experimental results show that, the proposed algorithm improves the recommendation hit rate by 2.3 percentage points and 1.5 percentage points respectively compared with the benchmark model Deep Item-based Collaborative Filtering (DeepICF) algorithm, which verifies the effectiveness of the proposed algorithm on making personalized recommendations for users.

Key words: recommender system, collaborative filtering, deep learning, implicit feedback, attention mechanism

摘要: 基于项目的协同过滤从用户的历史交互项目中学习用户偏好,根据用户的偏好推荐相似的新项目。现有的协同过滤方法认为用户所交互的一组历史项目对用户的影响是相同的,并且将所有历史交互项目在对目标项目作预测时的贡献看作是相同的,导致这些推荐方法的准确性受限。针对上述问题,提出了一种基于双重最相关注意力网络的协同过滤推荐算法,该算法包含两层注意力网络。首先,使用项目级注意力网络为不同历史项目分配不同的权重来捕获用户历史交互项目中最相关的项目;然后,使用项目交互级注意力网络感知不同历史项目与目标项目之间的交互关联度;最后,通过两层注意力网络的使用来同时捕获用户在历史交互项目上和目标项目上的细粒度偏好,从而更好地进行下一步推荐工作。在MovieLens和Pinterest两个真实数据集上进行实验,实验结果表明,所提算法在推荐命中率上与基准模型基于深度学习的项目协同过滤(DeepICF)算法相比分别提升了2.3个百分点和1.5个百分点,验证了该算法在为用户进行个性化推荐上的有效性。

关键词: 推荐系统, 协同过滤, 深度学习, 隐式反馈, 注意力机制

CLC Number: