[1]张玉瑶,程学林,尹天鹤.基于深度学习和矩阵分解的推荐算法[J].计算机技术与发展,2021,31(07):21-27.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 004]
　ZHANG Yu-yao,CHENG Xue-lin,YIN Tian-he.A Recommendation Algorithm Based on Deep Learning and Matrix Factorization[J].,2021,31(07):21-27.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 004]
点击复制

基于深度学习和矩阵分解的推荐算法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
31
期数:
2021年07期
页码:
21-27
栏目:
大数据分析与挖掘
出版日期:
2021-07-10

文章信息/Info

Title:
A Recommendation Algorithm Based on Deep Learning and Matrix Factorization
文章编号:
1673-629X(2021)07-0021-07
作者:
张玉瑶; 程学林; 尹天鹤
浙江大学 软件学院,浙江 杭州 310058
Author(s):
ZHANG Yu-yao; CHENG Xue-lin; YIN Tian-he
School of Software,Zhejiang University,Hangzhou 310058,China
关键词:
深度学习; 矩阵分解; 电影推荐; 多层感知机; 长短期记忆网络
Keywords:
deep learning; matrix factorization; movie recommendation; multilayer perceptron; long short-term memory
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2021. 07. 004
摘要:
推荐系统可以有效地缓解信息过载,帮助用户从海量数据中筛选其偏好的内容。 目前应用最普遍的推荐算法,如协同过滤,普遍存在着数据稀疏、冷启动、特征提取不充分等问题。 把电影推荐作为研究对象,提出了融合深度学习和矩阵分解的 LM-SVD 推荐算法。 以多层感知机 MLP 和长短期记忆网络 LSTM 的组合模型学习用户、电影属性数据及文本数据,获取用户和电影的深层特征表示。 接着以 BiasSVD 矩阵分解模型学习用户电影评分数据,获取用户和电影的潜在隐特征向量,并与深度学习阶段获得的深层特征向量相融合。 改进矩阵分解的预测评分和损失函数计算方式,缓解评分矩阵的稀疏性,使得特征提取更充分。 在两个 MovieLens 数据集上进行的算法对比实验表明,LM-SVD 算法有效提升了电影评分预测准确度,使得推荐性能提高。
Abstract:
Recommendation systems can effectively alleviate information overload and help users filter their preferred content from vast amounts of data. At present,the most common recommendation algorithms,such as collaborative filtering,generally have some problems,such as sparse data,cold starting and insufficient feature extraction. Taking movie recommendation as the research object,the LM-SVD recommendation algorithm is proposed by integrating deep learning and matrix factorization. The combined model of MLP and LSTM is used to learn user,movie attribute data and text data,so as to obtain the deep feature representation of user and movie. Then the Bias SVD matrix decomposition model is used to learn the user’s movie rating data,to obtain the latent implicit vectors of the user and the movie,and to integrate with the deep feature vectors obtained in the deep learning stage. The prediction scoring and loss function calculation methods of matrix decomposition are improved to alleviate the sparsity of scoring matrix and make feature extraction more sufficient. Algorithm comparison experiments on two Movie Lens data sets show that the LM-SVD algorithm effectively improves the prediction accuracy of movie scores and improves the recommendation performance.

相似文献/References:

[1]陈强锐,谢世朋.基于深度学习的肺部肿瘤检测方法[J].计算机技术与发展,2018,28(04):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
　CHEN Qiang-rui,XIE Shi-peng.Lung Cancer Detection Method Based on Deep Learning[J].,2018,28(07):201.[doi:10.3969/ j. issn.1673-629X.2018.04.043]
[2]施泽浩,赵启军.基于全卷积网络的目标检测算法[J].计算机技术与发展,2018,28(05):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
　SHI Ze-hao,ZHAO Qi-jun.Object Detection Algorithm Based on Fully Convolutional Neural Network[J].,2018,28(07):55.[doi:10.3969/j.issn.1673－629X.2018.05.013]
[3]黄法秀,张世杰,吴志红,等.数据增广下的人脸识别研究[J].计算机技术与发展,2020,30(03):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
　HUANG Fa-xiu,ZHANG Shi-jie,WU Zhi-hong,et al.Research on Face Recognition Based on Data Augmentation[J].,2020,30(07):67.[doi:10. 3969 / j. issn. 1673-629X. 2020. 03. 013]
[4]陈浩翔,蔡建明,刘铿然,等. 手写数字深度特征学习与识别[J].计算机技术与发展,2016,26(07):19.
　CHEN Hao-xiang,CAI Jian-ming,LIU Keng-ran,et al. Deep Learning and Recognition of Handwritten Numeral Features[J].,2016,26(07):19.
[5]高翔,陈志,岳文静,等.基于视频场景深度学习的人物语义识别模型[J].计算机技术与发展,2018,28(06):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
　GAO Xiang,CHEN Zhi,YUE Wen-jing,et al.Human Semantic Recognition Model Based on Video Scene Deep Learning[J].,2018,28(07):53.[doi:10.3969/ j. issn.1673-629X.2018.06.012]
[6]贺飞翔,赵启军. 基于深度学习的头部姿态估计[J].计算机技术与发展,2016,26(11):1.
　HE Fei-xiang,ZHAO Qi-jun. Head Pose Estimation Based on Deep Learning[J].,2016,26(07):1.
[7]徐 融,邱晓晖.一种改进的 YOLO V3 目标检测方法[J].计算机技术与发展,2020,30(07):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
　XU Rong,QIU Xiao-hui.An Improved YOLO V3 Object Detection[J].,2020,30(07):30.[doi:10. 3969 / j. issn. 1673-629X. 2020. 07. 007]
[8]曾志平[] [],萧海东[],张新鹏[]. 基于DBN的金融时序数据建模与决策[J].计算机技术与发展,2017,27(04):1.
　ZENG Zhi-ping[] [],XIAO Hai-dong[],ZHANG Xin-peng[]. Modeling and Decision-making of Financial Time Series Data with DBN[J].,2017,27(07):1.
[9]李全兵,文 钊*,田艳梅*,等.基于 WGAN 的音频关键词识别研究[J].计算机技术与发展,2021,31(08):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
　LI Quan-bing,WEN Zhao *,TIAN Yan-mei *,et al.Research on Audio Keywords Recognition Based on WassersteinGenerative Adversarial Network[J].,2021,31(07):26.[doi:10. 3969 / j. issn. 1673-629X. 2021. 08. 005]
[10]李宏林. 分析式纹理合成技术及其在深度学习的应用[J].计算机技术与发展,2017,27(11):7.
　LI Hong-lin. Analyzed Texture-synthesis Techniques and Their Applications in Deep Learning[J].,2017,27(07):7.

更新日期/Last Update: 2021-07-10