《计算机应用研究》|Application Research of Computers

基于FG_DRFwFm模型的深度推荐

Depth recommendation based on FG_DRFwFm model

免费全文下载 (已被下载 次)  
获取PDF全文
作者 王杉文,欧鸥,张伟劲,欧阳飞
机构 成都理工大学 信息科学与技术学院(网络安全学院),成都 610051
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2021)10-025-3030-05
DOI 10.19734/j.issn.1001-3695.2021.02.0048
摘要 近年来随着深度学习在多个领域取得了不错的效果,深度学习也开始应用在推荐系统,例如利用深度学习技术来捕捉高阶特征交互的NFM模型和DeepFM模型等。然而考虑到外部环境和内部感知的变化,用户的兴趣也应该随着时间动态的变化,且基于原始特征进行组合不一定能学到有效特征交互。为此尝试构建一种新的模型FG_DRFwFm,该模型能学习多特征域低阶与高阶特征交互与处理用户长期兴趣变化,并且训练特征是根据原始特征构建出新特征并拼接后组成的,能更好地学习有效特征交互。最后该模型在MovieLens数据集上与多个先进的CTR算法进行推荐效果对比验证,实验结果证明提出的模型取得了更好的效果。
关键词 推荐算法; 深度学习; 特征拼接; 域加权因子分解机; CTR预测
基金项目 国家重点研发计划资助项目(2018YFF01013304)
贵州地质灾害预警平台调查评价系统(80303-AHG069)
本文URL http://www.arocmag.com/article/01-2021-10-025.html
英文标题 Depth recommendation based on FG_DRFwFm model
作者英文名 Wang Shanwen, Ou Ou, Zhang Weijin, Ou Yangfei
机构英文名 College of Information Science & Technology(College of Internet Security),Chengdu University of Technology,Chengdu 610051,China
英文摘要 In recent years, as deep learning has achieved good results in many fields, deep learning has also begun to be applied to recommendation systems, such as NFM models and DeepFM models that use deep learning technology to capture high-level feature interactions. However, considering the changes in the external environment and internal perception, the user's interest should also change dynamically over time, and the combination based on the original features may not necessarily learn effective feature interaction. This paper attempted to build a new model FG_DRFwFm, which could learn the interaction of low-level and high-level features of multiple feature domains and dealt with long-term changes in user interest. It constructed the training features by constructing new features based on the original features and splicing them together, which could better learn effective feature interaction. Finally, the proposed model compared the recommendation effect with multiple advanced CTR algorithms on the MovieLens data set. The experimental results show that the proposed model achieves better results.
英文关键词 recommendation algorithm; deep learning; feature splicing; field-weighted factorization machines; CTR prediction
参考文献 查看稿件参考文献
 
收稿日期 2021/2/26
修回日期 2021/4/17
页码 3030-3034
中图分类号 TP301.6
文献标志码 A