一种基于旁信息增强的协同过滤自动编码器模型

doi:10.12068/j.issn.1005-3026.2019.11.002

东北大学学报:自然科学版 ›› 2019, Vol. 40 ›› Issue (11): 1527-1532.DOI: 10.12068/j.issn.1005-3026.2019.11.002

一种基于旁信息增强的协同过滤自动编码器模型

刘海博^1,2，冯时¹，于戈¹

(1. 东北大学计算机科学与工程学院，辽宁沈阳110169; 2. 河北大学网络空间安全与计算机学院，河北保定071002)

收稿日期:2018-12-20 修回日期:2018-12-20 出版日期:2019-11-15 发布日期:2019-11-05
通讯作者: 刘海博
作者简介:刘海博(1979-)，男，河北保定人，东北大学博士研究生; 于戈(1962-)，男，辽宁沈阳人，东北大学教授，博士生导师.
基金资助:
国家自然科学基金资助项目(61872074); 河北省自然科学基金资助项目(F2015201140，F2017201208) .

Auto-Encoder for Collaborative Filtering Based on Side-Information Enhancement

LIU Hai-bo^1,2， FENG Shi¹， YU Ge¹

1. School of Computer Science & Engineering， Northeastern University， Shenyang 110169， China; 2. School of Cyber Security and Computer， Hebei University， Baoding 071002， China.

Received:2018-12-20 Revised:2018-12-20 Online:2019-11-15 Published:2019-11-05
Contact: LIU Hai-bo
About author:-
Supported by:
-

摘要/Abstract

摘要： 针对用户评分预测不准确的问题，提出了一种基于旁信息(side-information)对用户兴趣进行预测的协同过滤自动编码器推荐模型，给出了模型的设计原理、损失函数以及具体结构.模型使用单隐藏层自动编码器实现，用户评分与旁信息同为模型的输入/输出数据，旁信息也直接参加模型的训练，这种设计不仅降低了模型的规模和复杂度，而且旁信息可以直接对用户兴趣进行修正.同时，通过对训练数据集合的合理划分与扩充，使得训练的网络模型增加了表达能力.在真实数据集上的对比实验表明，本文提出的方法提高了评分预测的准确度，具有一定的实用价值.

关键词: 自动编码器, 协同过滤, 旁信息, 推荐系统, 评分预测

Abstract: In view of inaccurate rating prediction of traditional recommendation model， a model based on side-information enhanced collaborative filtering auto-encoder was proposed， and the design principle， loss function and structure of the model were discussed in detail. The model was implemented by a single hidden layer auto-encoder network with ratings and side-information as input/output data. The model was directly trained by ratings and side-information. The proposed framework not only reduces the scale and complexity of the model， but also amends the user’s interest with side-information. At the same time， the representation ability of the trained model is increased by reasonable division and expansion of training datasets. The comparisons on real datasets show that the proposed model with side-information can effectively ameliorate the user’s interest predicted by the model without side-information， and improve the accuracy of rating prediction， which has a certain practicality.

Key words: auto-encoder, collaborative filtering, side-information, recommender system, rating prediction

中图分类号:

TP301.6

刘海博，冯时，于戈. 一种基于旁信息增强的协同过滤自动编码器模型[J]. 东北大学学报:自然科学版, 2019, 40(11): 1527-1532.

LIU Hai-bo， FENG Shi， YU Ge. Auto-Encoder for Collaborative Filtering Based on Side-Information Enhancement[J]. Journal of Northeastern University Natural Science, 2019, 40(11): 1527-1532.

参考文献

[1]Elhamifar E，Wang Y.High rank matrix completion with side information［C］// AAAI Conference on Artificial Intelligence.New Orleans:AAAI，2018:4252-4259.
[2]Adomavicius G，Tuzhilin A.Toward the next generation of recommender systems:a survey of the state-of-the-art and possible extensions［J］.IEEE Transactions on Knowledge and Data Engineering，2005，17(6):734-749.
[3]Zhang S，Yao L，Sun A，et al.Deep learning based recommender system:a survey and new perspectives［J］.ACM Computing Surveys，2018，1(1):1-35.
[4]He X，Liao L，Zhang H，et al.Neural collaborative filtering［C］//International Conference on World Wide Web.Perth:ACM，2017:173-182.
[5]Wang X，He X，Nie L，et al.Itemsilk road:recommending items from information domains to social users［C］//International ACM SIGIR Conference on Research and Development in Information Retrieval.Tokyo:ACM，2017:185-194.
[6]Lian J，Zhang F，Xie X，et al.CCCF net:a content-boosted collaborative filtering neural network for cross domain recommender systems［C］//International Conference on World Wide Web Companion.Perth:ACM，2017:817-818.
[7]Cheng H T，Koc L，Harmsen J，et al.Wide & deep learning for recommender systems［C］// The Workshop on Deep Learning for Recommender Systems.Boston:ACM，2016:7-10.
[8]Sedhain S，Menon A K，Sanner S，et al.AutoRec:autoencoders meet collaborative filtering［C］// International Conference on World Wide Web.Florence:ACM，2015:111-112.
[9]Strub F，Mary J.Collaborative filtering with stacked denoising autoencoders and sparse inputs［C］// Neural Information Processing Systems.Montreal:NIPS，2015:136-144.
[10]Wu Y，Dubois C，Zheng A X，et al.Collaborative denoising auto-encoders for top-n recommender systems［C］// International Conference on Web Search and Data Mining.San Francisco:ACM，2016:153-162.
[11]Li X，She J.Collaborative variational autoencoder for recommender systems［C］// ACM SIGKDD International Conference.Halifax:ACM，2017:305-314.
[12]Kuchaiev O，Ginsburg B.Training deep autoencoders for collaborative filtering［J］.arXiv:Machine Learning，2017，1(1):1-5.

一种基于旁信息增强的协同过滤自动编码器模型

Auto-Encoder for Collaborative Filtering Based on Side-Information Enhancement

RichHTML

PDF (PC)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

本文评价

[1]	孙艳蕊，陈月. 基于Timed-HITS与协同过滤的混合推荐算法[J]. 东北大学学报:自然科学版, 2019, 40(4): 467-473.
[2]	陈东明，严燕斌，黄新宇，王冬琦. 基于二分网络社团划分的推荐算法[J]. 东北大学学报:自然科学版, 2018, 39(8): 1103-1107.
[3]	张斌，王林，赵秀涛，张长胜. 一种资源与服务性能关系的建模方法[J]. 东北大学学报:自然科学版, 2015, 36(6): 773-776.
[4]	盛国军，温涛，郭权，吴镝. 基于协同过滤的可信Web服务推荐[J]. 东北大学学报(自然科学版), 2013, 34(6): 806-809.
[5]	赵晓煜;黄小原;曹忠鹏;. 基于顾客交易数据的协同过滤推荐方法[J]. 东北大学学报(自然科学版), 2009, 30(12): 1792-1795.