基于网络表示学习与深度学习的推荐算法研究

doi:10.19678/j.issn.1000-3428.0058631

计算机工程 ›› 2021, Vol. 47 ›› Issue (8): 54-61. doi: 10.19678/j.issn.1000-3428.0058631

基于网络表示学习与深度学习的推荐算法研究

刘峰¹, 王宝亮¹, 潘文采²

1. 天津大学信息与网络中心, 天津 300072;
2. 天津大学电气自动化与信息工程学院, 天津 300072

收稿日期:2020-06-15 修回日期:2020-08-08 发布日期:2020-07-16
作者简介:刘峰(1963-),男,副研究员,主研方向为信号与信息处理;王宝亮,高级工程师;潘文采,硕士研究生。
基金资助:
赛尔网络下一代互联网技术创新项目（NGII20160206）。

Research on Recommendation Algorithm Based on Network Representation Learning and Deep Learning

LIU Feng¹, WANG Baoliang¹, PAN Wencai²

1. Information and Network Center, Tianjin University, Tianjin 300072, China;
2. School of Electrical Automation and Information Engineering, Tianjin University, Tianjin 300072, China

Received:2020-06-15 Revised:2020-08-08 Published:2020-07-16

摘要/Abstract

摘要： 针对传统基于协同过滤的推荐算法信息提取能力有限的问题，提出基于网络表示学习的卷积协同过滤推荐算法。将二分网络分成物品与用户同质网络，在各自的同质网络上使用GraphSAGE模型得到融合网络空间信息和用户与物品属性信息的矩阵。在此基础上，利用外积运算丰富用户和物品特征向量各维度的相关表示，通过卷积神经网络训练物品和用户的交互信息得到算法模型。实验结果验证了该算法的有效性，且相比ConvNCF算法，其在Movielens数据集上HR@5和NDCG@5分别提升了1.89和2.19个百分点，在Last.fm数据集上HR@5和NDCG@5分别提升了1.09和2.32个百分点。

Abstract: The traditional recommendation algorithms based on collaborative filtering information are faced with the bottleneck of the information extraction capability. To address the problem, a recommendation algorithm based on convolution collaborative filtering for network representation learning is proposed. The algorithm decomposes the bipartite network into a homogenous network of users and items, and then uses the GraphSAGE algorithm for the two homogenous networks to obtain feature vectors. On this basis, the outer product operation is performed to enrich the relevant representation of each dimension of the user and item feature vectors. Finally, the convolutional neural network is used to train the interaction information between the item and the user to obtain the algorithm model. The experimental results show that the algorithm is effective, compared with the ConvNCF algorithm, the proposed algorithm improves HR@5 by 1.89 percentage point and NDCG@5 by 2.19 percentage point on the Movielens data set. The improvement of HR@5 is 1.09 percentage point and that of NDCG@5 is 2.32 percentage point on the Last. fm data set.

Key words: recommendation algorithm, Network Representation Learning(NRL), Deep Learning(DL), Convolutional Neural Network(CNN), collaborative filtering

中图分类号:

TP18

刘峰, 王宝亮, 潘文采. 基于网络表示学习与深度学习的推荐算法研究[J]. 计算机工程, 2021, 47(8): 54-61.

LIU Feng, WANG Baoliang, PAN Wencai. Research on Recommendation Algorithm Based on Network Representation Learning and Deep Learning[J]. Computer Engineering, 2021, 47(8): 54-61.

http://www.ecice06.com/CN/Y2021/V47/I8/54

图/表 11

20210819194743

20210819194747

20210819194752

20210819194756

20210819194801

20210819194805

20210819194810

20210819194816

20210819194821

20210819194825

20210819194829

参考文献

[1] TU C, LIU H, LIU Z, et al. CANE:context-aware network embedding for relation modeling[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics.San Diego, USA:Association for Computational Linguistics, 2017, (1): 1722-1731.
[2] HAN Q Y.The study of personalized recommendation algorithm in e-commerce system[J]. International Journal of Education and Economics, 2020, 3(2): 1-6.
[3] HU L M, LI C, SHI C, et al. Graph neural news recommendation with long-term and short-term interest modeling[EB/OL]. [2020-07-05]. https://arxiv.org/abs/1910.14025?context=stat.ML.
[4] ABUL-FOTTOUH D, SONG M Y, GRUZD A.Examining algorithmic biases in YouTube's recommendations of vaccine videos[J]. International Journal of Medical Informatics, 2020, 140:104385.
[5] HAVELIWALA T H.Topic-sensitive pagerank:a context-sensitive ranking algorithm for Web search[J]. IEEE Transactions on Knowledge and Data Engineering, 2003, 15(4): 784-796.
[6] GROVER A, LESKOVEC J.Mode2vec:scalable feature learning for networks[C]//Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York, USA:ACM Press, 2016:855-864.
[7] SUN X F, GUO J, DING X, et al. A general framework for content-enhanced network representation learning[EB/OL]. [2020-07-03]. https://arxiv.org/abs/1610.02906.
[8] TENENBAUM J B, DE SILVA V, LANGFORD J C.A global geometric framework for nonlinear dimensionality reduction[J]. Science, 2000, 290(5500): 2319-2323.
[9] BELKIN M, NIYOGI P.Laplacian eigenmaps and spectral techniques for embedding and clustering[C]//Proceedings of Advances in Neural Information Processing Systems.Cambridge, USA:MIT Press.2002:585-591.
[10] HAMILTON W, YING Z, LESKOVEC J.Inductive representation learning on large graphs[C]//Proceedings of Advances in Neural Information Processing Systems.Cambridge, USA:MIT Press.2017:1024-1034.
[11] HOCHREITER S, SCHMIDHUBER J.Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
[12] TAS O, KIYANI F.A survey automatic text summarization[C]//Proceedings of the 2nd World Conference on Technology, Innovation and Entrepreneurship.Istanbul, Turkey:Press Academia Procedia, 2007, 5(1): 205-213.
[13] BLEI D M, NG A Y, JORDAN M I.Latent dirichlet allocation[J]. Journal of Machine Learning Research, 2003, 3(1): 993-1022.
[14] KINGMA D P, BA J.Adam:a method for stochastic optimization[EB/OL]. [2020-07-06]. https://arxiv.org/pdf/1412.6980.pdf.
[15] KRIZHEVSKY A, SUTSKEVER I, HINTON G E.Imagenet classification with deep convolutional neural networks[C]//Proceedings of Advances in Neural Information Processing Systems.Cambridge, USA:MIT Press, 2012:1097-1105.
[16] SARWAR B, KARYPIS G, KONSTAN J, et al. Item-based collaborative filtering recommendation algorithms[C]//Proceedings of the 10th International Conference on World Wide Web.Berlin, Germany:Springer, 2001:285-295.
[17] RENDLE S, FREUDENTHALER C, GANTNER Z, et al. BPR:Bayesian personalized ranking from implicit feedback[C]//Proceedings of the 25th International Conference on Uncertainty in Artificial Intelligence.Washington D.C., USA:IEEE Press, 2009:452-461.
[18] KOREN Y, BELL R, VOLINSKY C.Matrix factorization techniques for recommender systems[J]. Computer, 2009, 42(8): 30-37.
[19] HE X, LIAO L, ZHANG H, et al. Neural collaborative filtering[C]//Proceedings of the International Conference on World Wide Web.Berlin, Germany:Springer, 2017:173-182.
[20] HE X N, DU X Y, WANG X, et al. Outer product-based neural collaborative filtering[EB/OL]. [2020-07-04]. https://arxiv.org/pdf/1808.03912.pdf.

选择文件类型/文献管理软件名称

选择包含的内容

基于网络表示学习与深度学习的推荐算法研究

Research on Recommendation Algorithm Based on Network Representation Learning and Deep Learning

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献

相关文章 15

编辑推荐

Metrics

本文评价

[1]	江雨燕, 陶承凤, 李平. 数据增强和自适应自步学习的深度子空间聚类算法[J]. 计算机工程, 2023, 49(8): 96-103, 110.
[2]	李泽水, 冀俊忠, 杨翠翠. 基于边权重信息深度网络嵌入的PPIN功能模块检测[J]. 计算机工程, 2023, 49(8): 69-76.
[3]	王可铮, 徐玉芬, 周尚波. 结合对比感知损失和融合注意力的图像去雾模型[J]. 计算机工程, 2023, 49(8): 207-214.
[4]	刘俊豪, 王美林, 谢兴, 宋烨兴, 许莉花. 基于改进YOLOv5的皮革瑕疵检测算法[J]. 计算机工程, 2023, 49(8): 240-249.
[5]	曹坪, 杨怀志, 薄一军, 尤嘉, 张淳杰, 李丹勇. 面向低质量裂缝图像的多知识蒸馏分类[J]. 计算机工程, 2023, 49(7): 204-213.
[6]	白明昌. 基于折叠路径聚合的属性网络节点嵌入方法[J]. 计算机工程, 2023, 49(7): 76-84.
[7]	闫兴亚, 匡娅茜, 白光睿, 李月. 基于深度学习的学生课堂行为识别方法[J]. 计算机工程, 2023, 49(7): 251-258.
[8]	李军侠, 王星驰, 殷梓, 石德硕. 边缘深度挖掘的弱监督显著性目标检测[J]. 计算机工程, 2023, 49(7): 169-178.
[9]	吴珊, 周凤. 基于改进SSD算法的小目标检测[J]. 计算机工程, 2023, 49(7): 179-188.
[10]	席建锐, 唐红梅, 梁春阳, 刘鑫. 基于改进隐函数的点云物体重建[J]. 计算机工程, 2023, 49(7): 214-222.
[11]	齐咏生, 杜晓旭, 朱俊峰, 高胜利, 刘利强. 基于增强型轻量深度网络的牧区牲畜高效检测[J]. 计算机工程, 2023, 49(7): 278-287.
[12]	谌雨章, 黄逸姿, 张钧涵. 基于多速率空洞卷积的多尺度水下小目标检测[J]. 计算机工程, 2023, 49(6): 257-264.
[13]	张博旭, 蒲智, 程曦. 基于提示学习的维吾尔语文本分类研究[J]. 计算机工程, 2023, 49(6): 292-299,313.
[14]	于海洋, 景鹏, 张文涛, 谢赛飞, 滑志华, 宋草原. 基于残差与注意力机制的道路裂缝检测U-Net改进模型[J]. 计算机工程, 2023, 49(6): 265-273.
[15]	代祖华, 刘园园, 狄世龙. 语义增强的图神经网络方面级文本情感分析[J]. 计算机工程, 2023, 49(6): 71-80.

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

基于网络表示学习与深度学习的推荐算法研究

Research on Recommendation Algorithm Based on Network Representation Learning and Deep Learning

RichHTML

PDF

可视化

被引次数

摘要/Abstract

引用本文

使用本文

图/表 11

参考文献

相关文章 15

编辑推荐

Metrics

本文评价