电子学报 ›› 2020, Vol. 48 ›› Issue (8): 1615-1622.DOI: 10.3969/j.issn.0372-2112.2020.08.021

• 学术论文 • 上一篇    下一篇

融合内容表示的度量排序学习推荐模型

李琳, 唐守廉   

  1. 北京邮电大学经济管理学院, 北京 100876
  • 收稿日期:2019-08-19 修回日期:2020-03-05 出版日期:2020-08-25 发布日期:2020-08-25
  • 通讯作者: 李琳
  • 作者简介:唐守廉 男,1952年出生于上海,北京邮电大学经济管理学院教授、博士生导师,主要研究为政府电信管制政策研究,企业发展战略研究,企业市场营销策划. E-mail:tangshoulian@263.net
  • 基金资助:
    浙江省基础公益研究计划(No.LGG18F020010)

Metric Ranking Learning Recommendation Model Based on Content Representation

LI Lin, TANG Shou-lian   

  1. School of Economics and Management, Beijing University of Posts and Telecommunications, Beijing 100876, China
  • Received:2019-08-19 Revised:2020-03-05 Online:2020-08-25 Published:2020-08-25

摘要: 融合内容语义信息的推荐模型可以有效缓解音乐推荐系统中的数据稀疏性和冷启动问题.然而,这些模型是通过最小化预测评分误差学习用户与音乐的全局关系,忽略了用户和音乐隐式特征的细粒度差异.此外,内容语义特征是以推荐任务无关的无监督学习方式提取的,从而导致不精确推荐.为此,本文提出了融合内容表示的度量排序学习推荐模型,该模型是以个性化排序最优化为目标的概率图模型,利用度量学习从全局和细粒度层面挖掘用户音乐偏好.为了解决冷启动推荐问题,本文建立了与推荐任务相关的监督学习策略训练内容语义特征提取模型.在KKBOX和MIGU数据集上的实验结果表明,提出的模型显著提升了冷启动音乐推荐的效果,在不同稀疏度数据集上的鲁棒性得到了显著增强.

关键词: 内容表示, 度量学习, 排序学习, 音乐推荐

Abstract: A model that incorporates semantic information can alleviate the sparse data and cold start problems in a music recommendation system.Current models learn the global relations between users and music by minimizing prediction score error.However,they ignore the fine-grained differences between the implicit features of users and music.Current models also extract semantic features by unsupervised learning that is irrelevant to recommending,leading to inaccurate recommendations.We propose a metric-ranking-learning recommendation model that incorporates content representation (CAMRL).This model is a probabilistic graphical model that optimizes a personalized ranking and explores user music preferences through metric learning at both global and fine-grained levels.To solve the cold start recommendation problem,a supervised learning strategy in relation to the recommendation task is proposed to train the model of content semantic feature exaction.The results of trials using the KKBOX and MIGU datasets show that the proposed model significantly improves cold start music recommendations when compared with other algorithms; it is also more robust when using sparse datasets.

Key words: content representation, metric learning, ranking learning, music recommendation

中图分类号: