Full Text:   <1984>

Summary:  <1735>

CLC number: TP391

On-line Access: 2017-05-24

Received: 2016-11-22

Revision Accepted: 2017-03-07

Crosschecked: 2017-04-27

Cited: 0

Clicked: 5414

Citations:  Bibtex RefMan EndNote GB/T7714

-   Go to

Article info.
Open peer comments

Frontiers of Information Technology & Electronic Engineering  2017 Vol.18 No.5 P.658-666


A new item-based deep network structure using a restricted Boltzmann machine for collaborative filtering

Author(s):  Yong-ping Du, Chang-qing Yao, Shu-hua Huo, Jing-xuan Liu

Affiliation(s):  Institute of Computer Science, Beijing University of Technology, Beijing 100124, China; more

Corresponding email(s):   ypdu@bjut.edu.cn, yaocq@istic.ac.cn

Key Words:  Restricted Boltzmann machine, Deep network structure, Collaborative filtering, Recommendation system

Yong-ping Du, Chang-qing Yao, Shu-hua Huo, Jing-xuan Liu. A new item-based deep network structure using a restricted Boltzmann machine for collaborative filtering[J]. Frontiers of Information Technology & Electronic Engineering, 2017, 18(5): 658-666.

@article{title="A new item-based deep network structure using a restricted Boltzmann machine for collaborative filtering",
author="Yong-ping Du, Chang-qing Yao, Shu-hua Huo, Jing-xuan Liu",
journal="Frontiers of Information Technology & Electronic Engineering",
publisher="Zhejiang University Press & Springer",

%0 Journal Article
%T A new item-based deep network structure using a restricted Boltzmann machine for collaborative filtering
%A Yong-ping Du
%A Chang-qing Yao
%A Shu-hua Huo
%A Jing-xuan Liu
%J Frontiers of Information Technology & Electronic Engineering
%V 18
%N 5
%P 658-666
%@ 2095-9184
%D 2017
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.1601732

T1 - A new item-based deep network structure using a restricted Boltzmann machine for collaborative filtering
A1 - Yong-ping Du
A1 - Chang-qing Yao
A1 - Shu-hua Huo
A1 - Jing-xuan Liu
J0 - Frontiers of Information Technology & Electronic Engineering
VL - 18
IS - 5
SP - 658
EP - 666
%@ 2095-9184
Y1 - 2017
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.1601732

The collaborative filtering (CF) technique has been widely used recently in recommendation systems. It needs historical data to give predictions. However, the data sparsity problem still exists. We propose a new item-based restricted Boltzmann machine (RBM) approach for CF and use the deep multilayer RBM network structure, which alleviates the data sparsity problem and has excellent ability to extract features. Each item is treated as a single RBM, and different items share the same weights and biases. The parameters are learned layer by layer in the deep network. The batch gradient descent algorithm with minibatch is used to increase the convergence speed. The new feature vector discovered by the multilayer RBM network structure is very effective in predicting a rating and achieves a better result. Experimental results on the data set of MovieLens show that the item-based multi-layer RBM approach achieves the best performance, with a mean absolute error of 0.6424 and a root-mean-square error of 0.7843.


概要:协同过滤推荐算法利用历史数据进行预测推荐,在电子商务领域得到了广泛的应用,同时,数据稀疏问题依然存在。本文提出一种基于项目的受限玻尔兹曼机协同过滤算法,并采用了深度多层网络结构,有效缓解了数据稀疏问题,获取了更加有效的特征。将项目当作单独的受限玻尔兹曼机进行训练,不同的项目具有相同的权重值和偏置,在多层网络结构中,参数逐层被学习,采用带minibatch的批量梯度下降(Batch gradient descent, BGD)算法加快收敛速度,由多层玻尔兹曼机结构的网络学习到的新的特征向量在评分预测中具有更优的能力。在Movielens数据集上的实验结果表明,采用该方法的系统性能显著优于基于用户的受限玻尔兹曼机协同过滤方法,MAE与RMSE最优值分别达到了0.6424和0.7843。


Darkslateblue:Affiliate; Royal Blue:Author; Turquoise:Article


[1]Bell, R., Koren, Y., Volinsky, C., 2007. The BellKor Solution to the Netfix Prize.


[3]Bengio, Y., 2009. Learning deep architectures for AI. Found. Trends Mach. Learn., 2(1):1-127.

[4]Breese, J., Hecherman, D., Kadie, C., 1998. Empirical analysis of predictive algorithms for collaborative filtering. Proc. 14th Conf. on Uncertainty in Artificial Intelligence, p.43-52.

[5]Candès, E.J., Recht, B., 2009. Exact matrix completion via convex optimization. Found. Comput. Math., 9(6):717-772.

[6]Ference, G., Ye, M., Lee, W.C., 2013. Location recommendation for out-of-town users in location-based social networks. Proc. 22nd ACM Int. Conf. on Information & Knowledge Management, p.721-726.

[7]Feuerverger, A., He, Y., Khatri, S., 2012. Statistical significance of the Netflix challenge. Stat. Sci., 27(2):202-231.

[8]Hinton, G.E., 2002. Training products of experts by minimizing contrastive divergence. Neur. Comput., 14(8):1771-1800.

[9]Hinton, G.E., Sejnowski, J., 1983. Optimal perceptual inference. Proc. IEEE Conf. on Computer Vision and Pattern Recognition, p.448-453.

[10]Hinton, G.E., Osindero, S., Teh, Y.W., 2006. A fast learning algorithm for deep belief nets. Neur. Comput., 18(7): 1527-1554.

[11]Koren, Y., Bell, R., Volinsky, C., 2009. Matrix factorization techniques for recommender systems. Computer, 42(8): 30-37.

[12]Li, Y., Yang, M., Zhang, Z.M., 2013. Scientific articles recommendation. Proc. 22nd ACM Int. Conf. on Information & Knowledge Management, p.1147-1156.

[13]Linden, G., Smith, B., York, J., 2003. Amazon.com recommendations: item-to-item collaborative filtering. IEEE Int. Comput., 7(1):76-80.

[14]Luo, H., 2011. Restricted Boltzmann Machines: a Collaborative Filtering Perspective. PhD Thesis, Shanghai Jiao Tong University, Shanghai, China (in Chinese).

[15]Mohamed, A., Dahl, G.E., Hinton, G.E., 2012. Acoustic modeling using deep belief networks. IEEE Trans. Audio Speech Lang. Process., 20(1):14-22.

[16]Nathanson, T., Bitton, E., Goldberg, K., 2007. Eigentaste 5.0: constant-time adaptability in a recommender system using item clustering. Proc. ACM Conf. on Recommender Systems, p.149-152.

[17]Resnick, P., Iacovou, N., Suchak, M., et al., 1994. GroupLens: an open architecture for collaborative filtering of netnews. Proc. ACM Conf. on Computer Supported Cooperative Work, p.175-186.

[18]Salakhutdinov, R., Mnih, A., Hinton, G.E., 2007. Restricted Boltzmann machines for collaborative filtering. Proc. 24th Annual Int. Conf. on Machine Learning, p.791-798.

[19]Sarwar, B., Karypis, G., Konstan, J., et al., 2001. Item-based collaborative filtering recommendation algorithms. Proc. ACM 10th Int. Conf. on World Wide Web, p.285-295.

[20]Schafer, J.B., Konstan, J., Riedl, J., 1999. Recommender systems in E-commerce. Proc. 1st ACM Conf. on Electronic Commerce, p.158-166.

[21]Shi, J., Chen, J., Bao, Z., 2011. An application study on collaborative filtering in e-commerce. Int. Conf. on Service Systems and Service Management, p.1-7.

[22]Smolensky, P., 1986. Information processing in dynamical systems: foundations of harmony theory. In: Rumellhart, D.E., McClelland, J.L. (Eds.), Parallel Distributed Processing: Explorations in the Microstructure of Cognition. Vol. 1: Foundations. MIT Press, Cambridge, MA, USA, p.194-281.

[23]Töscher, A., Jahrer, M., 2008. The BigChaos Solution to the Netfix Prize 2008. http://netflixprize.com/assets/GrandPrize2009_BPC_BigChaos.pdf

[24]Wang, S., Tang, J., Wang, Y., 2015. Exploring implicit hierarchical structures for recommender systems. Proc. 24th Int. Joint Conf. on Artificial Intelligence, p.1813-1819.

[25]Wu, J.L., 2010. Collaborative Filtering on the Netflix Prize Dataset. PHD Thesis, Peking University, Beijing, China (in Chinese).

[26]Zhang, C.X., Ji, N.N., Wang, G.W., 2015. Restricted Boltzman machines. Chin. J. Eng. Math., 32(2):159-173 (in Chinese).

[27]Zhang, M., Tang, J., Zhang, X., et al., 2014. Addressing cold start in recommender systems: a semi-supervised co-training algorithm. Proc. 37th Int. ACM SIGIR Conf. on Research and Development in Information Retrieval, p.73-82.

Open peer comments: Debate/Discuss/Question/Opinion


Please provide your name, email address and a comment

Journal of Zhejiang University-SCIENCE, 38 Zheda Road, Hangzhou 310027, China
Tel: +86-571-87952783; E-mail: cjzhang@zju.edu.cn
Copyright © 2000 - 2024 Journal of Zhejiang University-SCIENCE