计算机科学 ›› 2020, Vol. 47 ›› Issue (6A): 540-545.doi: 10.11896/JsJkx.191000172

• 数据库 & 大数据 & 数据科学 • 上一篇    下一篇

基于卷积神经网络与约束概率矩阵分解的推荐算法

马海江   

  1. 华侨大学计算机科学与技术学院 厦门 361021
  • 发布日期:2020-07-07
  • 通讯作者: 马海江(751219377@qq.com)
  • 基金资助:
    国家社会科学基金资助项目(19BXW110);福建省社会科学规划项目(FJ2017B073);华侨大学科研启动项目(600005-Z16Y0005)

Recommendation Algorithm Based on Convolutional Neural Network and Constrained Probability Matrix Factorization

MA Hai-Jiang   

  1. School of Computer Science and Technology Huaqiao University,Xiamen 361021,China
  • Published:2020-07-07
  • About author:LEE D D, SEUNG H S.Algorithms for non-negative matrix factorization//Advances in Neural Information Processing Systems.2001:556-562.
    MA Hai-Jiang, born in 1989, postgradua-te.His main research interests include Intelligent data processing and analysis.
  • Supported by:
    This work was supported by the ProJect National Social Science Foundation (19BXW110),Social Science Planning ProJect of FuJian Province (FJ2017B073) and Huaqiao University Research Startup ProJect (600005-Z16Y0005).

摘要: 用户评分数据的稀疏性和上下文的信息缺失,往往导致基于矩阵分解(Matrix Factorization,MF)的推荐算法在准确性方面有所欠缺。针对此问题,文中提出了一种基于卷积神经网络(Convolutional Neural Networks,CNN)与约束概率矩阵分解(Constrained Probabilistic Matrix Factorization,CPMF)的推荐算法。首先,构建卷积神经网络模型,对用户上下文辅助信息进行识别,获得文本潜在向量,并叠加高斯噪声,初始化项目特征矩阵;然后,根据用户评分信息,利用约束矩阵来约束用户特征,并叠加补偿矩阵,初始化用户特征矩阵;接着,利用初始化的用户特征矩阵和项目特征矩阵拟合评分矩阵,对评分矩阵进行矩阵分解,并利用坐标下降算法更新参数;最后,预测用户对项目的评分,实现项目推荐。在Movielens和Amazon数据集上的实验结果表明,该推荐算法显著优于传统的推荐模型,有效地提高了推荐结果的准确率。

关键词: 矩阵分解, 卷积神经网络, 上下文信息, 推荐算法

Abstract: Due to the sparsity of user rating data and the lack of context information,the recommendation algorithm based on matrix factorization is often lacking in accuracy.To solve this problem,a recommendation algorithm based on convolutional neural network and constrained probability matrix factorization is proposed.Firstly,a convolutional neural network model is constructed to identify the contextual auxiliary information of users,obtain the text potential vector,superimpose gaussian noise,and initialize the proJect characteristic matrix.Then,according to the user rating information,the user characteristics are constrained by the constraint matrix,and the user characteristic matrix is initialized by superimposing the compensation matrix.Then,the initialized user characteristic matrix and proJect characteristic matrix are used to fit the rating matrix,the rating matrix is decomposed by matrix,and the coordinate descent algorithm is used to update the parameters.Finally,predict the user’s score on the proJect and implement the proJect recommendation.Experimental results on Movielens and Amazon data sets show that this recommendation algorithm is significantly superior to the traditional recommendation model and effectively improves the accuracy of recommendation results.

Key words: Contextual information, Convolutional neural networks, Matrix factorization, Recommendation algorithm

中图分类号: 

  • TP391
[1] ZHANG Z W.Summary of research on personalized recommendation algorithm .Information and Computer (Theoretical Edition),2018(17):27-29.
[2] ZHANG M,DING B Y,MA W Z,et al.Hybrid recommendation method based on deep learning reinforcement.Journal of Tsinghua University (Natural Science Edition),2017,57(10):1014-1021.
[3] LI F,XU G,CAO L.Coupled item-based matrix factorization//International Conference on Web Information Systems Engineering.Cham:Springer,2014:1-14.
[4] WANG H,WANG N,YEUNG D Y.Collaborative deep learning for recommender systems//Proceedings of the 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2015:1235-1244.
[5] GAO Q L,GAO L,YANG J F,et al.Preference acquisition method based on user cognitive behavior in context-aware re-commendation system .Acta Computerica Sinica,2015,38(9):1767-1776.
[6] PENG Y,ZHU W,ZHAO Y,et al.Cross-media analysis and
[7] reasoning:advances and directions.Frontiers of Information Technology &Electronic Engineering,2017,18(1):44-57.
[8] WER J,HE J,CHEN K,et al.Collaborative filtering and deep learning based recommendation system for cold start items.Expert Systems with Applications,2016,69(10):1339-1351.
[9] CHEN P H,ZHU Y.A recommendation algorithm for fusion knowledge graph representation and matrix decomposition.Computer engineering and design,2018,39(10):145-150.
[10] OKURA S,TAGAMI Y,ONO S,et al.Embedding-based news recommendation for millions of users//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.ACM,2017:1933-1942.
[11] VANDEN O A,DIELEMAN S,SCHRAUWEN B.Deep content-based music recommendation//Advances in Neural Information Processing Systems.2013:2643-2651.
[12] CHENG H T,KOC L,HARMSEN J,et al.Wide & deep learning for recommender systems//Proceedings of the 1st Workshop on Deep Learning for Recommender Systems.ACM,2016:7-10.
[13] ZHENG L,NOROOZI V,YU P S.Joint deep modeling of users and items using reviewsfor recommendation//Proceedings of the Tenth ACM International Conference on Web Search and Data Mining.ACM,2017:425-434.
[14] RENDEL S.Factorization machines with libfm.ACM Transactions on Intelligent Systems and Technology (TIST),2012,3(3):57.
[15] WANG H,ZHANG F,XIE X,et al.DKN:Deep knowledgeaware network for news recommendation//Proceedings of the 2018 World Wide Web Conference on World Wide Web.International World Wide Web Conferences Steering Committee,2018:1835-1844.
[16] MNIH A,SALAKHUTDINOV R R.Probabilistic matrix factorization//Advances in Neural Information Processing Systems.2008:1257-1264.
[17] KIMD,PARK C,OH J,et al.Convolutional Matrix Factorization for Document Context-Aware Recommendation//Acm Conference on Recommender Systems.ACM,2016:233-240.
[18] HARPER F M,KONSTAN J A.The movielens datasets:History and context.Acm Transactions on Interactive Intelligent Systems (tiis),2016,5(4):19.
[19] DESHPANDEM,KARYPIS G.Item-based top- N recommendation algorithms.ACM Transactions on Information Systems,2004,22(1):143-177.
[1] 周乐员, 张剑华, 袁甜甜, 陈胜勇.
多层注意力机制融合的序列到序列中国连续手语识别和翻译
Sequence-to-Sequence Chinese Continuous Sign Language Recognition and Translation with Multi- layer Attention Mechanism Fusion
计算机科学, 2022, 49(9): 155-161. https://doi.org/10.11896/jsjkx.210800026
[2] 李宗民, 张玉鹏, 刘玉杰, 李华.
基于可变形图卷积的点云表征学习
Deformable Graph Convolutional Networks Based Point Cloud Representation Learning
计算机科学, 2022, 49(8): 273-278. https://doi.org/10.11896/jsjkx.210900023
[3] 陈泳全, 姜瑛.
基于卷积神经网络的APP用户行为分析方法
Analysis Method of APP User Behavior Based on Convolutional Neural Network
计算机科学, 2022, 49(8): 78-85. https://doi.org/10.11896/jsjkx.210700121
[4] 朱承璋, 黄嘉儿, 肖亚龙, 王晗, 邹北骥.
基于注意力机制的医学影像深度哈希检索算法
Deep Hash Retrieval Algorithm for Medical Images Based on Attention Mechanism
计算机科学, 2022, 49(8): 113-119. https://doi.org/10.11896/jsjkx.210700153
[5] 檀莹莹, 王俊丽, 张超波.
基于图卷积神经网络的文本分类方法研究综述
Review of Text Classification Methods Based on Graph Convolutional Network
计算机科学, 2022, 49(8): 205-216. https://doi.org/10.11896/jsjkx.210800064
[6] 金方焱, 王秀利.
融合RACNN和BiLSTM的金融领域事件隐式因果关系抽取
Implicit Causality Extraction of Financial Events Integrating RACNN and BiLSTM
计算机科学, 2022, 49(7): 179-186. https://doi.org/10.11896/jsjkx.210500190
[7] 张颖涛, 张杰, 张睿, 张文强.
全局信息引导的真实图像风格迁移
Photorealistic Style Transfer Guided by Global Information
计算机科学, 2022, 49(7): 100-105. https://doi.org/10.11896/jsjkx.210600036
[8] 戴朝霞, 李锦欣, 张向东, 徐旭, 梅林, 张亮.
基于DNGAN的磁共振图像超分辨率重建算法
Super-resolution Reconstruction of MRI Based on DNGAN
计算机科学, 2022, 49(7): 113-119. https://doi.org/10.11896/jsjkx.210600105
[9] 刘月红, 牛少华, 神显豪.
基于卷积神经网络的虚拟现实视频帧内预测编码
Virtual Reality Video Intraframe Prediction Coding Based on Convolutional Neural Network
计算机科学, 2022, 49(7): 127-131. https://doi.org/10.11896/jsjkx.211100179
[10] 徐鸣珂, 张帆.
Head Fusion:一种提高语音情绪识别的准确性和鲁棒性的方法
Head Fusion:A Method to Improve Accuracy and Robustness of Speech Emotion Recognition
计算机科学, 2022, 49(7): 132-141. https://doi.org/10.11896/jsjkx.210100085
[11] 孙福权, 崔志清, 邹彭, 张琨.
基于多尺度特征的脑肿瘤分割算法
Brain Tumor Segmentation Algorithm Based on Multi-scale Features
计算机科学, 2022, 49(6A): 12-16. https://doi.org/10.11896/jsjkx.210700217
[12] 黄少滨, 孙雪薇, 李熔盛.
基于跨句上下文信息的神经网络关系分类方法
Relation Classification Method Based on Cross-sentence Contextual Information for Neural Network
计算机科学, 2022, 49(6A): 119-124. https://doi.org/10.11896/jsjkx.210600150
[13] 吴子斌, 闫巧.
基于动量的映射式梯度下降算法
Projected Gradient Descent Algorithm with Momentum
计算机科学, 2022, 49(6A): 178-183. https://doi.org/10.11896/jsjkx.210500039
[14] 杨涵, 万游, 蔡洁萱, 方铭宇, 吴卓超, 金扬, 钱伟行.
基于步态分类辅助的虚拟IMU的行人导航方法
Pedestrian Navigation Method Based on Virtual Inertial Measurement Unit Assisted by GaitClassification
计算机科学, 2022, 49(6A): 759-763. https://doi.org/10.11896/jsjkx.211200148
[15] 何亦琛, 毛宜军, 谢贤芬, 古万荣.
基于点割集图分割的矩阵变换与分解的推荐算法
Matrix Transformation and Factorization Based on Graph Partitioning by Vertex Separator for Recommendation
计算机科学, 2022, 49(6A): 272-279. https://doi.org/10.11896/jsjkx.210600159
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!