用于个性化推荐的条件卷积隐因子模型

doi:10.19678/j.issn.1000-3428.0054209

计算机工程 ›› 2020, Vol. 46 ›› Issue (4): 85-90,96. doi: 10.19678/j.issn.1000-3428.0054209

用于个性化推荐的条件卷积隐因子模型

李南星^1,2, 盛益强^1,2, 倪宏^1,2

1. 中国科学院声学研究所国家网络新媒体工程技术研究中心, 北京 100190;
2. 中国科学院大学电子电气与通信工程学院, 北京 100049

收稿日期:2019-03-13 修回日期:2019-04-15 出版日期:2020-04-15 发布日期:2019-05-16
作者简介:李南星(1991-),男,博士研究生,主研方向为人工智能、深度学习、数据挖掘;盛益强,博士;倪宏,研究员。
基金资助:
中国科学院先导专项课题"SEANET技术标准化研究与系统研制"（XDC02010801）。

Conditional Convolution Implicit Factor Model for Personalized Recommendation

LI Nanxing^1,2, SHENG Yiqiang^1,2, NI Hong^1,2

1. National Network New Media Engineering Research Center, Institute of Acoustics, Chinese Academy of Sciences, Beijing 100190, China;
2. School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing 100049, China

Received:2019-03-13 Revised:2019-04-15 Online:2020-04-15 Published:2019-05-16

摘要/Abstract

摘要： 在推荐系统中，传统的矩阵分解无法提取用户和物品特征，而神经协同过滤（NCF）在分解模型中增加多层感知器，但不能有效利用用户和物品ID之外的辅助信息。为此，提出一种新的条件卷积方法。通过将物品特征作为输入，将用户特征作为卷积核，达到权值不共享的目的，使得条件卷积具有更强的特征提取和组合能力以及不增加参数量的特性。在此基础上，条件卷积能够融入多种辅助信息进行个性化推荐。实验结果表明，与NCF模型相比，该方法在隐性反馈数据中推荐命中率提升3.11%，在显性反馈数据中评分预测误差降低2.47%。

Abstract: In the recommendation system,the traditional Matrix Factorization(MF) cannot extract the features of users and items.The Neural Collaborative Filtering(NCF) adds a multi-layer perceptron to the model for this reason,but still cannot effectively make use of the auxiliary information other than the user and item ID.Therefore,this paper proposes a new conditional convolution method.In this method,the item features are used as input and the user features as convolutional kernels,so as to achieve the purpose of unshared weights,thus making the conditional convolution has stronger feature extraction and combination abilities while maintaining the features of parameters.On this basis,the conditional convolution can incorporate a variety of auxiliary information for personalized recommendation.Experimental results show that compared with the NCF model,the proposed method can increase the recommendation hit rate by 3.11% in the implicit feedback data and reduce the scoring prediction error by 2.47% in the explicit feedback data.

Key words: recommendation system, Deep Neural Networks(DNN), Neural Collaborative Filtering(NCF), conditional convolution, Matrix Factorization(MF)

中图分类号:

TP18

李南星, 盛益强, 倪宏. 用于个性化推荐的条件卷积隐因子模型[J]. 计算机工程, 2020, 46(4): 85-90,96.

LI Nanxing, SHENG Yiqiang, NI Hong. Conditional Convolution Implicit Factor Model for Personalized Recommendation[J]. Computer Engineering, 2020, 46(4): 85-90,96.

http://www.ecice06.com/CN/Y2020/V46/I4/85

图/表 10

20200414124033

20200414124037

20200414124041

20200414124045

20200414124049

20200414124052

20200414124056

20200414124100

20200414124103

20200414124107

参考文献 22

[1]	SARWAR B M,KARYPIS G,KONSTAN J A,et al.Item-based collaborative filtering recommendation algorithms[C]//Proceedings of the 10th International World Wide Web Conference.Hong Kong,China:[s.n.],2001:285-295.
[2]	HERLOCKER J,KONSTAN J A,RIEDL J.An empirical analysis of design choices in neighborhood-based collaborative filtering algorithms[J].Information Retrieval,2002,5(4):287-310.
[3]	HERLOCKER J,KONSTAN J,BORCHERS A,et al.An algorithmic framework for performing collaborative filtering[C]//Proceedings of the 22nd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval.Berkeley,USA:[s.n.],1999:230-237.
[4]	HU Y,KOREN Y,VOLINSKY C.Collaborative filtering for implicit feedback datasets[C]//Proceedings of the 8th IEEE International Conference on Data Mining.Pisa,Italy:[s.n.],2008:263-272.
[5]	KOREN Y.Factorization meets the neighborhood:a multifaceted collaborative filtering model[C]//Proceedings of the 14th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Las Vegas,USA:[s.n.],2008:426-434.
[6]	WANG C,BLEI D M.Collaborative topic modeling for recommending scientific articles[C]//Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.San Diego,USA:[s.n.],2011:448-456.
[7]	WANG H,WANG N,YEUNG D.Collaborative deep learning for recommender systems[C]//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.Sydney,Australia:[s.n.],2015:1235-1244.
[8]	WU Ke,ZHAN Yinwei,LI Ying.Recommendation algorithm of latent factor model fused with user attribute[J].Computer Engineering,2016,42(12):171-175.(in Chinese) 巫可,战荫伟,李鹰.融合用户属性的隐语义模型推荐算法[J].计算机工程,2016,42(12):171-175.
[9]	COLLOBERT R,WESTON J.A unified architecture for natural language processing:deep neural networks with multitask learning[C]//Proceedings of IC’08.Helsinki,Finland:[s.n.],2008:160-167.
[10]	HE Kaiming,ZHANG Xiangyu,REN Shaoqing,et al.Deep residual learning for image recognition[C]//Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition.Las Vegas,USA:[s.n.],2016:770-778.
[11]	HORNIK K,STINCHCOMBE M B,WHITE H.Multilayer feedforward networks are universal approximators[J].Neural Networks,1989,2(5):359-366.
[12]	ZHANG F,YUAN N J,LIAN D,et al.Collaborative knowledge base embedding for recommender systems[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.San Francisco,USA:[s.n.],2016:353-362.
[13]	WANG Xingkai,DENG Haojiag,ZHAO Zhenyu,et al.Design of video recommendation system with extended attributes of Chinese semantic feature[J].Journal of Network New Media,2018,7(3):51-55.(in Chinese) 王星凯,邓浩江,赵震宇,等.中文语义特征属性扩展的视频推荐系统设计[J].网络新媒体技术,2018,7(3):51-55.
[14]	LIAN Jianxun,ZHANG Fuzheng,XIE Xing,et al.A content-boosted collaborative filtering neural network for cross domain recommender systems[C]//Proceedings of the 26th International Conference on World Wide Web Companion.Geneva,Switzerland:[s.n.],2017:817-818.
[15]	HE Xiangnan,LIAO Lizi,ZHANG Hanwang,et al.Neural collaborative filtering[EB/OL].[2019-02-20].http://arxiv.org/abs/1708.05031.
[16]	WANG Xiang,HE Xiangnan,NIE Liqing,et al.Item silk road:recommending items from information domains to social users[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval.New York,USA:ACM Press,2017:185-194.
[17]	GUO Jingfeng,ZHANG Jilong,ZHANG Debin,et al.Enhancing trust networks using asymmetric similarity for recommendation[J].Journal of Chinese Computer Systems,2015,36(9):1943-1947.(in Chinese)郭景峰,张济龙,章德斌,等.一种利用非对称相似度强化信任用户关系的推荐算法[J].小型微型计算机系统,2015,36(9):1943-1947.
[18]	TAIGMAN Y,YANG M,RANZATO M,et al.Deepface:closing the gap to human-level performance in face verification[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C.,USA:IEEE Press,2014:1701-1708.
[19]	SARWAR B.Item-based collaborative filtering recommendation algorithms[EB/OL].[2019-02-20].https://ci.nii.ac.jp/naid/10012086326/en/.
[20]	RENDLE S,FREUDENTHALER C,GANTNER Z,et al.BPR:bayesian personalized ranking from implicit feedback[C]//Proceedings of the 25th Conference on Uncertainty in Artificial Intelligence.Arlington,USA:AUAI Press,2009:452-461.
[21]	HE X,ZHANG H,KAN M Y,et al.Fast matrix factorization for online recommendation with implicit feedback[C]//Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval.New York,USA:ACM Press,2016:549-558.
[22]	ZHANG Shuai,YAO Lina,SUN Aixin,et al.Deep learning based recommender system:a survey and new perspectives[EB/OL].[2019-02-20].https://arxiv.org/abs/1707.07435v3.

选择文件类型/文献管理软件名称

选择包含的内容

用于个性化推荐的条件卷积隐因子模型

Conditional Convolution Implicit Factor Model for Personalized Recommendation

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 22

相关文章 15

编辑推荐

Metrics

本文评价

[1]	陈君航, 杨祖元, 刘名扬, 李陵江. 基于正交约束的广义可分离非负矩阵分解算法[J]. 计算机工程, 2023, 49(8): 46-53.
[2]	靳雁霞, 史志儒, 杨晶, 刘亚变, 乔星宇, 张翎. 布料与精细建模物体间的碰撞检测算法研究[J]. 计算机工程, 2023, 49(7): 269-277.
[3]	唐彦, 卢镘旭. 基于知识图谱与深度涟漪网络的推荐系统[J]. 计算机工程, 2023, 49(5): 63-72,80.
[4]	陈锐, 孙羽菲, 郭强, 隋轶丞, 周振辉, 石昌青, 张玉志. OclDNN:一种可应用于TensorFlow的通用DNN库[J]. 计算机工程, 2023, 49(4): 138-148.
[5]	石磊, 张吉涛, 高宇飞, 卫琳, 陶永才. 基于Transformer与BiLSTM的网络流量入侵检测[J]. 计算机工程, 2023, 49(3): 29-36,57.
[6]	李盼, 解庆, 李琳, 刘永坚. 知识增强的图神经网络序列推荐模型[J]. 计算机工程, 2023, 49(2): 70-80.
[7]	王春东, 孙嘉琪, 杨文军. 基于矫正理解的中文文本对抗样本生成方法[J]. 计算机工程, 2023, 49(2): 37-45.
[8]	刘杭, 殷歆, 陈杰, 罗恒. 基于混合网络模型的多维时间序列预测[J]. 计算机工程, 2023, 49(1): 121-129.
[9]	刘金硕, 詹岱依, 邓娟, 王丽娜. 基于深度神经网络和联邦学习的网络入侵检测[J]. 计算机工程, 2023, 49(1): 15-21,30.
[10]	董卫宇, 李海涛, 王瑞敏, 任化娟, 孙雪凯. 基于堆叠卷积注意力的网络流量异常检测模型[J]. 计算机工程, 2022, 48(9): 12-19.
[11]	范林歌, 武欣嵘, 童玮, 曾维军. 基于概率矩阵分解的不完整数据集特征选择方法[J]. 计算机工程, 2022, 48(6): 57-64.
[12]	冉懿, 王润年, 潘红伟, 俞海猛, 袁培森. 面向停电分类预测的因子分解机模型[J]. 计算机工程, 2022, 48(5): 98-103,111.
[13]	张恒, 陈晓红, 蓝宇翔, 李舜酩. 基于深度学习的监督型典型相关分析[J]. 计算机工程, 2022, 48(5): 222-228.
[14]	路东生, 张玉金, 党良慧. 面向图像篡改取证的多特征融合U形深度网络[J]. 计算机工程, 2022, 48(4): 213-222.
[15]	杨文雪, 吴非, 郭桐, 肖利民. 基于噪声溶解的对抗样本防御方法[J]. 计算机工程, 2022, 48(4): 158-164.

模态框（Modal）标题

选择文件类型/文献管理软件名称

选择包含的内容

用于个性化推荐的条件卷积隐因子模型

Conditional Convolution Implicit Factor Model for Personalized Recommendation

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 10

参考文献 22

相关文章 15

编辑推荐

Metrics

本文评价