Please wait a minute...
 Big Data Mining and Analytics  2018, Vol. 01 Issue (03): 211-221    DOI: 10.26599/BDMA.2018.9020019
A Novel Deep Hybrid Recommender System Based on Auto-encoder with Neural Collaborative Filtering
Yu Liu, Shuai Wang, M. Shahrukh Khan, Jieyu He*
Yu Liu, Shuai Wang, M. Shahrukh Khan, and Jieyue He are with School of Computer Science and Engineering, and also with MOE Key Laboratory of Computer Network and Information Integration, Southeast University, Nanjing 211189, China. E-mail: 220153311@seu.edu.cn; 53263887@ qq.com; mushahrukhkhan@outlook.com.
 Download: PDF (505 KB)      HTML   Export: BibTeX | EndNote (RIS)

Abstract

Due to the widespread availability of implicit feedback (e.g., clicks and purchases), some researchers have endeavored to design recommender systems based on implicit feedback. However, unlike explicit feedback, implicit feedback cannot directly reflect user preferences. Therefore, although more challenging, it is also more practical to use implicit feedback for recommender systems. Traditional collaborative filtering methods such as matrix factorization, which regards user preferences as a linear combination of user and item latent vectors, have limited learning capacities and suffer from data sparsity and the cold-start problem. To tackle these problems, some authors have considered the integration of a deep neural network to learn user and item features with traditional collaborative filtering. However, there is as yet no research combining collaborative filtering and content-based recommendation with deep learning. In this paper, we propose a novel deep hybrid recommender system framework based on auto-encoders (DHA-RS) by integrating user and item side information to construct a hybrid recommender system and enhance performance. DHA-RS combines stacked denoising auto-encoders with neural collaborative filtering, which corresponds to the process of learning user and item features from auxiliary information to predict user preferences. Experiments performed on the real-world dataset reveal that DHA-RS performs better than state-of-the-art methods.

Received: 31 January 2018      Published: 13 January 2020
Corresponding Authors: Jieyu He
 Service E-mail this article Add to my bookshelf Add to citation manager E-mail Alert RSS Articles by authors Yu Liu Shuai Wang M. Shahrukh Khan Jieyu He
 Cite this article: Yu Liu, Shuai Wang, M. Shahrukh Khan, Jieyu He. A Novel Deep Hybrid Recommender System Based on Auto-encoder with Neural Collaborative Filtering. Big Data Mining and Analytics, 2018, 01(03): 211-221. URL:
 Table 1 Frequently used symbols. Fig. 1 Deep hybrid recommender system based on auto-encoders model. Fig. 2 A four-layer stacked denoising auto-encoder. Table 2 MovieLens-1M statistics. Table 3 User and item attributes. Fig. 3 Performances of HR@10 and NDCG@10 w.r.t. the dimension of latent vector. Fig. 4 Performances of HR@K and NDCG@K w.r.t. K. Fig. 5 HR@10 and NDCG@10 w.r.t the number of iterations. Fig. 6 Training loss w.r.t. number of iterations. Fig. 7 Trade-off effect on HR@10 and NDCG@10. Fig. 8 Performances of HR@10 and NDCG@10 w.r.t. the number of hidden layers.
 [1] Lu J. W., Guo Y., Mi Z. Q., and Yang Y., Trust-enhanced matrix factorization using PageRank for recommender system, in Proc. 2017 Int. Conf. Computer, Information and Telecommunication Systems, Dalian, China, 2017, pp. 123-127. [2] Linden G., Smith B., and York J., Amazon.com recommendations: Item-to-item collaborative filtering, IEEE Internet Comput., vol. 7, no. 1, pp. 76-80, 2003. [3] Konstan J. A., Miller B. N., Maltz D., Herlocker J. L., Gordon L. R., and Riedl J., Grouplens: Applying collaborative filtering to Usenet news, Commun. ACM, vol. 40, no. 3, pp. 77-87, 1997. [4] Salakhutdinov R., Mnih A., and Hinton G., Restricted Boltzmann machines for collaborative filtering, in Proc. 24th Int. Conf. Machine Learning, Corvalis, OR, USA, 2007, pp. 791-798. [5] Ouyang Y. X., Liu W. Q., Rong W. G., and Xiong Z., Autoencoder-based collaborative filtering, in Proc. Int. Conf. Neural Information Processing, Kuching, Malaysia, 2014, pp. 284-291. [6] He X. N., Liao L. Z., Zhang H. W., Nie L. Q., Hu X., and Chua T. S., Neural collaborative filtering, in Proc. 26th Int. Conf. World Wide Web, Perth, Australia, 2017, pp. 173-182. [7] Li S., Kawale J., and Fu Y., Deep collaborative filtering via marginalized denoising auto-encoder, in Proc. 24th ACM Int. Conf. Information and Knowledge Management, Melbourne, Australia, 2015, pp. 811-820. [8] Zhang F. Z., Yuan N. J., Lian D. F., Xie X., and Ma W. Y., Collaborative knowledge base embedding for recommender systems, in Proc. 22ndACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, 2016, pp. 353-362. [9] Herlocker J. L., Konstan J. A., Terveen L. G., and Riedl J. T., Evaluating collaborative filtering recommender systems, ACM Trans. Inf. Syst., vol. 22, no. 1, pp. 5-53, 2004. [10] Wang H., Wang N. Y., and Yeung D. Y., Collaborative deep learning for recommender systems, in Proc. 21th ACM SIGKDD Int. Conf. Knowledge Discovery and Data Mining, Sydney, Australia, 2015, pp. 1235-1244. [11] Lee D. D. and Seung H. S., Algorithms for non-negative matrix factorization, in Proc. 13th Int. Conf. Neural Information Processing Systems, Denver, CO, USA, 2001, pp. 556-562. [12] Koren Y., Bell R., and Volinsky C., Matrix factorization techniques for recommender systems, Computer, vol. 42, no. 8, pp. 30-37, 2009. [13] Salakhutdinov R. and Mnih A., Probabilistic matrix factorization, in Proc. 20th Int. Conf. Neural Information Processing Systems, Vancouver, Canada, 2008, pp. 1257-1264. [14] Larochelle H., Erhan D., Courville A., Bergstra J., and Bengio Y., An empirical evaluation of deep architectures on problems with many factors of variation, in Proc. 24th Int. Conf. Machine Learning, Corvalis, OR, USA, 2007, pp. 473-480. [15] Georgiev K. and Nakov P., A non-IID framework for collaborative filtering with restricted Boltzmann machines, in Proc. 30th Int. Conf. Machine Learning, Atlanta, GA, USA, 2013, pp. 1148-1156. [16] Wu Y., DuBois C., Zheng A. X., and Ester M., Collaborative denoising auto-encoders for top-N recommender systems, in Proc. 9th ACM Int. Conf. Web Search and Data Mining, San Francisco, CA, USA, 2016, pp. 153-162. [17] Vincent P., Larochelle H., Bengio Y., and Manzagol P. A., Extracting and composing robust features with denoising autoencoders, in Proc. 25th Int. Conf. Machine Learning, Helsinki, Finland, 2008, pp. 1096-1103. [18] He R. N. and McAuley J., VBPR: Visual Bayesian personalized ranking from implicit feedback, in Proc. 30th AAAI Conf. Artificial Intelligence, Phoenix, AZ, USA, 2016, pp. 144-150. [19] Zeiler M. D. and Fergus R., Visualizing and understanding convolutional networks, in Proc. European Conf. Computer Vision, Zurich, Switzerland, 2014, pp. 818-833. [20] Krizhevsky A., Sutskever I., and Hinton G. E., ImageNet classification with deep convolutional neural networks, in Proc. 25th Int. Conf. Neural Information Processing Systems, Lake Tahoe, NV, USA, 2012, pp. 1097-1105. [21] Bengio Y., Lamblin P., Popovici D., and Larochelle H., Greedy layer-wise training of deep networks, in Proc. 19th Int. Conf. Neural Information Processing Systems , 2007, pp. 153-160. [22] He X. N., Chen T., Kan M. Y., and Chen X., TriRank: Review-aware explainable recommendation by modeling aspects, in Proc. 24th ACM Int. Conf. Information and Knowledge Management, Melbourne, Australia, 2015, pp. 1661-1670. [23] Sarwar B., Karypis G., Konstan J., and Riedl J., Item-based collaborative filtering recommendation algorithms, in Proc. 10th Int. Conf. World Wide Web, Hong Kong, China, 2001, pp. 285-295. [24] Rendle S., Factorization machines, in Proc. 10th Int. Conf. Data Mining, Sydney, Australia, 2010, pp. 995-1000. [25] Rendle S., Freudenthaler C., Gantner Z., and Schmidt-Thieme L., BPR: Bayesian personalized ranking from implicit feedback, in Proc. 25th Conf. Uncertainty in Artificial Intelligence, Montreal, Canada, 2009, pp. 452-461. [26] Kingma D. P. and Ba J., Adam: A method for stochastic optimization, arXiv preprint arXiv: 1412.6980, 2014.
 No related articles found!