Abstract
A recommender system is an active tool for information filtering that can be deployed in a complex and dynamic online environment to provide the most relevant and accurate content to the users based on their unique preferences and tastes. The recent direction towards enhancing the recommender system leverages deep learning techniques and trust information. However, building a unified model for a recommender system that integrates deep architecture with trust information is an open challenge. Here, we propose a hybrid method by modeling a joint optimization function which extends deep Autoencoder with top-k semantic social information. We use network representation learning methods to capture the implicit semantic social information. We conducted experiments with various real-world data sets and evaluated the performance of the proposed method using different evaluation measures. Experimental results show the performance improvement of the proposed system compared to state-of-the-art methods.
Similar content being viewed by others
Notes
Throughout this paper we consider the functions f(.)and g(.) as ReLU function given by \(ReLU(x)=\left \{\begin {array}{l}0 for x<0\\x for x\geq 0 \end {array}\right . \)
References
Bengio Y, Courville AC, Vincent P (2012) Unsupervised feature learning and deep learning: a review and new perspectives, vol 1, pp 2012. arXiv:12065538
Benkaddour FZ, Taghezout N, Kaddour-Ahmed FZ, Hammadi IA (2018) An adapted approach for user profiling in a recommendation system: application to industrial diagnosis. In: International journal of interactive multimedia and artificial intelligence. https://doi.org/10.9781/ijimai.2018.06.003
Cao S, Lu W, Xu Q (2016) Deep neural networks for learning graph representations. In: AAAI, pp 1145–1152
Chaney AJ, Blei DM, Eliassi-Rad T (2015) A probabilistic model for using social networks in personalized item recommendation. In: Proceedings of the 9th ACM conference on recommender systems, pp 43–50
Chen H, Perozzi B, Hu Y, Skiena S (2017) Harp: Hierarchical representation learning for networks. arXiv:170607845
Chen Y, Perozzi B, Skiena S (2015) Vector-based similarity measurements for historical figures. In: International conference on similarity search and applications, pp 179–190
Coates A, Ng A, Lee H (2011) An analysis of single-layer networks in unsupervised feature learning. In: Proceedings of the fourteenth international conference on artificial intelligence and statistics, pp 215–223
Conneau A, Schwenk H, Barrault L, Lecun Y (2016) Very deep convolutional networks for natural language processing. arXiv:1606.01781
Crespo RG, Martínez OS, Lovelle JMC, García-Bustelo BCP, Gayo JEL, De Pablos PO (2011) Recommendation system based on user interaction data applied to intelligent electronic books. In: Computers in human behavior, vol 27(4), pp 1445–1449
da Silva EDS, Langseth H, Ramampiaro H (2017) Content-based social recommendation with poisson matrix factorization. In: Joint european conference on machine learning and knowledge discovery in databases. Springer, pp 530–546
Devooght R, Bersini H (2016) Collaborative filtering with recurrent neural networks. arXiv:160807400
Dommeti R (2009) Neighborhood based methods for collaborative filtering. A case study I, pp 1–5
Dosovitskiy A, Springenberg JT, Riedmiller M, Brox T (2014) Discriminative unsupervised feature learning with convolutional neural networks. In: Advances in neural information processing systems, pp 766–774
Eirinaki M, Gao J, Varlamis I, Tserpes K (2018) Recommender systems for large-scale social networks: a review of challenges and solutions. In: Future generation computer systems, vol 78, pp 413–418
Gizaw, Tilahun Z, Dong Jun H, Oad A (2017) Solving cold-start problem by combining personality traits and demographic attributes in a user based recommender system. International journal of advanced research in computer science and software engineering, 7(5)
Goldberg Y, Levy O (2014) Word2vec explained: Deriving Mikolov et al.’s negative-sampling word-embedding method. arXiv:14023722
Goodfellow I, Bengio Y, Courville A, Bengio Y (2016) Deep learning, vol 1. MIT Press, Cambridge
Goyal P, Ferrara E (2017) Graph embedding techniques, applications, and performance: a survey. arXiv:170502801
Grbovic M, Radosavljevic V, Djuric N, Bhamidipati N, Savla J, Bhagwan V, Sharp D (2015) E-commerce in your inbox: Product recommendations at scale. In: Proceedings of the 21th ACM SIGKDD international conference on knowledge discovery and data mining, pp 1809–1818
Grover A, Leskovec J (2016) Node2vec: Scalable feature learning for networks. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 855–864
Guan X, Li CT, Guan Y (2016) Enhanced svd for collaborative filtering. In: Pacific-Asia conference on knowledge discovery and data mining, pp 503–514
Guo G, Zhang J, Yorke-Smith N (2015) Trustsvd: collaborative filtering with both the explicit and implicit influence of user trust and of item ratings. In: AAAI, vol 15, pp 123–125
Guo X, Lu J (2007) Intelligent e-government services with personalized recommendation techniques. In: International journal of intelligent systems, vol 22(5), pp 401–417
Hamilton WL, Ying R, Leskovec J (2017) Representation learning on graphs: methods and applications. arXiv:170905584
Jin Z, Liu R, Li Q, Zeng DD, Zhan Y, Wang L (2016) Predicting user’s multi-interests with network embedding in health-related topics. In: 2016 International joint conference on neural networks (IJCNN), pp 2568–2575
Khusro S, Ali Z, Ullah I (2016) Recommender systems: issues, challenges, and research opportunities. In: Information science and applications (ICISA). Springer, pp 1179–1189
Kim D, Yum BJ (2005) Collaborative filtering based on iterative principal component analysis. Expert Syst Appl 28(4):823–830
Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:160902907
Kipf TN, Welling M (2016) Variational graph auto-encoders. arXiv:161107308
Koren Y, Bell R, Volinsky C (2009) Matrix factorization techniques for recommender systems. In: Computer, vol 8, pp 30–37
Koskela P (2017) Comparing ranking based collaborative filtering algorithms to a rating - based alternative in recommender systems context
Kouemou GL (2011) History and theoretical basics of hidden markov models
Langseth H (2009) Bayesian networks for collaborative filtering. In: Proceedings of Norwegian artificial intelligens symposium, pp 67–78
Lee DD, Seung HS (2001) Algorithms for non-negative matrix factorization. In: Advances in neural information processing systems, pp 556–562
Lee J, Sun M, Lebanon G (2012) A comparative study of collaborative filtering algorithms. arXiv:12053193
Liao Y, Du W, Geurts P, Leduc G (2013) Dmfsgd: a decentralized matrix factorization algorithm for network distance prediction. IEEE/ACM Trans Networking (TON) 21(5):1511–1524
Matek T, Zebec ST (2016) Github open source project recommendation system. arXiv:160202594
Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems, pp 3111–3119
Mnih A, Salakhutdinov RR (2008) Probabilistic matrix factorization. In: Advances in neural information processing systems, pp 1257–1264
Mnih RSA (2008) Bayesian probabilistic matrix factorization using markov chain Monte Carlo
Mochón MC (2016) Social network analysis and big data tools applied to the systemic risk supervision. In: International journal of interactive multimedia and artificial intelligence, vol 3, pp 34–37
Noda K, Yamaguchi Y, Nakadai K, Okuno HG, Ogata T (2015) Audio-visual speech recognition using deep learning. In: Applied intelligence, vol 42(4), pp 722–737
Ou M, Cui P, Pei J, Zhang Z, Zhu W (2016) Asymmetric transitivity preserving graph embedding. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining, pp 1105–1114
Perozzi B, Al-Rfou R, Skiena S (2014) Deepwalk: Online learning of social representations. In: Proceedings of the 20th ACM SIGKDD international conference on knowledge discovery and data mining, pp 701–710
Qibing L, Xiaolin Z (2017) Deep collaborative autoencoder for recommender systems: a unified framework for explicit and implicit feedback. arXiv:1712.09043
Sainath TN, Kingsbury B, Ramabhadran B (2012) Auto-encoder bottleneck features using deep belief networks. In: 2012 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 4153–4156
Sedhain S, Menon AK, Sanner S, Xie L (2015) Autorec: Autoencoders meet collaborative filtering. In: Proceedings of the 24th international conference on world wide web, pp 111–112
Sharma S, Mahajan* A (2017) Suggestive approaches to create a recommender system for github
Srivastava N, Salakhutdinov RR (2012) Multimodal learning with deep boltzmann machines. In: Advances in neural information processing systems, pp 2222–2230
Strub F, Mary J, Gaudel R (2016) Hybrid collaborative filtering with autoencoders. arXiv:160300806
Sun K, Gonçalves JP, Larminie C, Pržulj N (2014) Predicting disease associations via biological network analysis. In: BMC Bioinformatics, vol 15(1), pp 304
Sun Y, Wang X, Tang X (2013) Hybrid deep learning for face verification. In: 2013 IEEE international conference on computer vision (ICCV), pp 1489–1496
Sun Z, Han L, Huang W, Wang X, Zeng X, Wang M, Yan H (2015) Recommender systems based on social networks. In: Journal of systems and software, vol 99, pp 109–119
Tang J, Qu M, Wang M, Zhang M, Yan J, Mei Q (2015) Line: Large-scale information network embedding. In: Proceedings of the 24th international conference on world wide web, pp 1067–1077
van Baalen M (2016) Deep matrix factorization for recommendation. Master’s thesis, University of Amsterdam, the Netherlands
Vincent P, Larochelle H, Bengio Y, Manzagol PA (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning, pp 1096–1103
Wang D, Cui P, Zhu W (2016) Structural deep network embedding. In: Proceedings of the 22nd ACM SIGKDD international conference on Knowledge discovery and data mining, pp 1225–1234
Xing S, Liu F, Zhao X, Li T (2017) Points-of-interest recommendation based on convolution matrix factorization. In: Applied intelligence, pp 1–12
Xue S, Abdel-Hamid O, Jiang H, Dai L (2014) Direct adaptation of hybrid dnn/hmm model for fast speaker adaptation in lvcsr based on speaker code. In: 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp 6339– 6343
Yang B, Lei Y, Liu J, Li W (2017) Social collaborative filtering by trust. IEEE Trans Pattern Anal Mach Intell 39(8):1633–1647
Yang C, Fan Q, Wang T, Yin G, Wang H (2016) Repolike: personal repositories recommendation in social coding communities. In: Proceedings of the 8th Asia-Pacific symposium on internetware, pp 54–62
Zhang C, Yu L, Wang Y, Shah C, Zhang X (2017) Collaborative user network embedding for social recommender systems. In: Proceedings of the 2017 SIAM international conference on data mining, pp 381–389
Zhang S, Yao L, Sun A (2017) Deep learning based recommender system: A survey and new perspectives. arXiv:170707435
Zhao T, McAuley J, King I (2014) Leveraging social connections to improve personalized ranking for collaborative filtering. In: Proceedings of the 23rd ACM international conference on conference on information and knowledge management, pp 261–270
Acknowledgments
We are thankful to the Department of Computer Science and Engineering at N.S.S. College of Engineering, Palakkad for providing required facilities.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
C C, N., Mohan, A. A social recommender system using deep architecture and network embedding. Appl Intell 49, 1937–1953 (2019). https://doi.org/10.1007/s10489-018-1359-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-018-1359-z