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

基于注意力机制的音乐深度推荐算法

Music recommendation algorithm based on attention mechanism

免费全文下载 (已被下载 次)  
获取PDF全文
作者 张全贵,张新新,李志强
机构 辽宁工程技术大学 电子与信息工程学院,辽宁 葫芦岛 125105
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2019)08-012-2297-03
DOI 10.19734/j.issn.1001-3695.2018.01.0075
摘要 在海量音乐中,如何根据用户的历史收听记录分析用户需求以实现歌曲推荐是音乐推荐领域具有挑战性课题之一。现有的音乐推荐方法仅简单地将用户听过的所有音乐均作为音乐推荐的上下文,导致不同类型音乐学习到的上下文权重分配相同,其严重影响了音乐推荐精度。针对此问题,提出了一种基于注意力机制的音乐深度推荐方法,针对不同用户的历史收听音乐动态分配不同的注意力,即学习出不同的上下文权重,使推荐结果更符合用户的实际偏好。通过在公开音乐数据集million song dateset上的测试,所提方法的推荐准确率有很大的提升。
关键词 深度学习; 注意力机制; 音乐推荐
基金项目 国家留学基金资助项目(留金法[2015]5104)
辽宁省自然科学基金资助项目(20180550995)
本文URL http://www.arocmag.com/article/01-2019-08-012.html
英文标题 Music recommendation algorithm based on attention mechanism
作者英文名 Zhang Quangui, Zhang Xinxin, Li Zhiqiang
机构英文名 School of Electronic & Information Engineering,Liaoning Technical University,Huludao Liaoning 125105,China
英文摘要 In the mass music, how to analyze the user's needs according to the user's history listening record to implement song recommendation is one of the challenging topics in the music recommendation field. The existing music recommendation method simply uses all the music the user has heard as the context of the music recommendation, which results in the same weight distribution of contexts learned by different types of music, which seriously affects the accuracy of the music recommendation. In response to this problem, this paper proposed a music recommendation method based on attention mechanism, which dynamically allocated different attentions to different users' historical listening music, that was learns different contextual weights so as to make the recommendation result more in line with the user's actual preference. And through the test on public music dataset named million song dataset, the recommended accuracy of the method proposed has greatly improved.
英文关键词 deep learning(DL); attention mechanism; music recommendation(MR)
参考文献 查看稿件参考文献
 
收稿日期 2018/1/30
修回日期 2018/3/28
页码 2297-2299,2304
中图分类号 TP391
文献标志码 A