期刊文献+

融合元数据及隐式反馈信息的多层次联合学习推荐方法 预览

Combing metadata and implicit feedback to recommendation by multi-level deep joint learning
在线阅读 下载PDF
收藏 分享 导出
摘要 针对隐式数据单纯利用隐反馈信息往往难以获取较好推荐性能的问题,提出一种融合元数据及隐式反馈信息的多层次深度联合学习(multi-level deep joint learning,MDJL)推荐方法。它利用双深度神经网络共同学习,其中一个网络利用隐式反馈学习用户及项目个体个性化关系,另一个网络利用元数据学习高层次群体共性化关系,从而有效地表达用户偏好,使MDJL框架在个体及群体因素间达到平衡。最后,MDJL推荐算法在Movie Lens 100K和MovieLens 1M两个公开数据集上进行实验评估。结果表明,该算法比其他基线方法表现出了更为优越的推荐性能。 Due to the implicit data is difficult to obtain better recommendation performance by using implicit feedback information,this paper proposed a multi-level deep joint learning( MDJL) recommendation method integrating metadata and implicit feedback information. It used double deep neural network learning,one network used implicit feedback learning the relationship between individual and individual user,another network used metadata for learning high level group common relationship,so as to effectively express the user preferences,the MDJL framework to achieve the balance in the individual and group factors. Finally,it evaluated the MDJL recommendation algorithm on two open data sets of MovieLens 100K and MovieLens 1M. The results show that the proposed algorithm performs better recommendation performance than other baseline methods.
作者 张全贵 李志强 蔡丰 王星 Zhang Quangui, Li Zhiqiang, Cai Feng, Wang Xing ( School of Electronics & Information Engineering, kiaoning Technical University, Huludao kiaoning 125105, China)
出处 《计算机应用研究》 CSCD 北大核心 2018年第12期3635-3639,共5页 Application Research of Computers
基金 国家留学基金资助项目(留金法[2015]5104) 国家自然科学基金资助项目(61402212) 辽宁省自然科学基金指导计划资助项目
关键词 元数据 隐式反馈 多层次深度联合学习 个体个性化 群体共性化 metadata implicit feedback muhi-level deep joint learning individual personalized group commonality
作者简介 张全贵(1978-),男,河北秦皇岛人,副教授,博士,主要研究方向为计算机视觉、推荐系统、机器学习、数据挖掘等(zhqgui@126.com);;李志强(1993-),男,辽宁锦州人,硕士,主要研究方向为机器学习、计算机视觉、推荐系统等;;蔡丰(1992-),女,辽宁锦州人,硕士,主要研究方向为计算机视觉、机器学习等;;王星(1983-),男,山东泰安人,副教授,博士,主要研究方向为知识表示、数据挖掘等.
  • 相关文献

参考文献2

二级参考文献21

  • 1Backstrom L,Sun E,Marlow C.Find me if you can:improving geographical prediction with social and spatial proximity[C] //Proc of the 19th International Conference on World Wide Web.New York:ACM Press,2010:61-70. 被引量:1
  • 2Scellato S,Noulas A,Mascolo C.Exploiting place features in link prediction on location-based social networks[C] //Proc of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM Press,2011:1046-1054. 被引量:1
  • 3Monreale A,Pinelli F,Trasarti R,et al.Where next:a location predictor on trajectory pattern mining[C] //Proc of the 15th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM Press,2009:637-646. 被引量:1
  • 4Zheng Yu.Tutorial on location-based social networks[C] //Proc of International Conference on World Wide Web.2012:45-46. 被引量:1
  • 5Bao Jie,Zheng Yu,Wilkie D,et al.A survey on recommendations in location-based social networks[J].GeoInformatica,2014,11:126-155. 被引量:1
  • 6Berjani B,Strufe T.A recommendation system for spots in location-based online social networks[C] //Proc of the 4th Workshop on Social Network Systems.New York:ACM Press,2011:4-20. 被引量:1
  • 7Cho E,Myers S A,Leskovec J.Friendship and mobility:user movement in location-based social networks[C] //Proc of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York:ACM Press,2011:1082-1090. 被引量:1
  • 8Mao Ye,Janowicz K,Muligann C,et al.What you are is when you are:the temporal dimension of feature types in location-based social networks[C] //Proc of the 19th ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems.New York:ACM Press,2011:102-111. 被引量:1
  • 9Mao Ye,Yin Peifeng,Wang C L.Location recommendation for location-based social networks[C] //Proc of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems.New York:ACM Press,2010:458-461. 被引量:1
  • 10Vincent W Z,Cao Bin,Zheng Yu,et al.Collaborative filtering meets mobile recommendation:a user-centered approach[C] //Proc of the 24th AAAI Conference on Artificial Intelligence.2010:64-78. 被引量:1

共引文献6

投稿分析

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈