北京邮电大学学报

  • EI核心期刊

北京邮电大学学报 ›› 2017, Vol. 40 ›› Issue (1): 74-78.doi: 10.13190/j.jbupt.2017.01.013

• 研究报告 • 上一篇    下一篇

利用模糊分块改进协同过滤的扩展性和准确性

王晓军, 付超   

  1. 南京邮电大学 信息网络技术研究所, 南京 210003
  • 收稿日期:2016-09-13 出版日期:2017-02-28 发布日期:2017-03-14
  • 作者简介:王晓军(1968-),女,副研究员,E-mail:xjwang@njupt.edu.cn.
  • 基金资助:
    国家自然科学基金项目(61003237)

Enhancing Scalability and Accuracy of Collaborative Filtering Using Fuzzy Blocking

WANG Xiao-jun, FU Chao   

  1. Institute of Information and Network Technology, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
  • Received:2016-09-13 Online:2017-02-28 Published:2017-03-14

摘要: 项目的协同过滤方法利用项目之间相似性预测用户对项目的评分,但相似项的选择面临可扩展性和准确性的问题。为此,提出分布式协同过滤方法,利用模糊分块技术将项目集分成若干块,然后仅在各块内比较项目的相似性。通过裁剪相似关系图进一步改善效率,从图中去除不可能相似的项目之间的边。最后,利用图的分区技术,将相似关系图分割为若干较小的区,在各分区上并行计算项目的相似度。实验结果表明,该方法能改善推荐系统的准确性和可扩展性。

关键词: 推荐系统, 个性化推荐, 协同过滤, 数据分块, 模糊聚类

Abstract: The ratings of items based on the similarities between items are predicted by traditional item-based collaborative filtering methods However, the selections of the similar ones are suffering from limited scalability and accuracy. A distributed collaborative filtering method was proposed. This method clusters items into several blocks using fuzzy blocking, and performs comparisons solely among the items within each block. Additional efficiency enhancements can be achieved through the pruning of the similar relationship graph:edges between items that are not likely to be similar can be removed from the graph. It divides this graph into multiple smaller partitions from each which similarity degrees between items is calculated efficiently in parallel. Experiments show that the proposed method can improve the recommendation scalability and accuracy.

Key words: recommender systems, personalized recommendation, collaborative filtering, data blocking, fuzzy clustering

中图分类号: