Abstract
We propose “Deep Autoencoders for Feature Learning in Recommender Systems,” a novel discriminative model based on the incorporation of features from autoencoders in combination with embeddings into a deep neural network to predict ratings in recommender systems. The work has two major motivations. The first is to engineer features for recommender systems in a domain-agnostic way using autoencoders. The second is to develop a method that sets a benchmark for predictive accuracy. In our proposed solution, we build a user autoencoder and item autoencoder that extract latent features for the users and items, respectively. The additional features engineered are the latent features for the users and items, and these come from the bottleneck activations of the autoencoder. Our method of feature engineering is domain agnostic, as the inner-most activations would differ for domains without any additional effort required on part of the modeler. Next, we then use the activations of the inner-most layers of the autoencoders as features in a subsequent deep neural network to predict the ratings along-with user and item embeddings. Our method incorporates additional linear and nonlinear latent features from the autoencoders to improve predictive accuracy. This is different from the existing approaches that use autoencoders as full-fledged recommender systems or use autoencoders to generate features for a subsequent supervised learning algorithm or without using embeddings. We demonstrate the out performance of our solution on four different datasets of varying sizes and sparsity, namely MovieLens 100 K, MovieLens 1 M, FilmTrust and BookCrossing datasets, with strong experimental results. We have compared our DAFERec method against mDA-CF, TrustSVD, SVD variants, BiasedMF, ItemKNN and I-AutoRec methods. The results demonstrate that our proposed solution beats the benchmarks and is a highly flexible model that works on different datasets solving different business problems like book recommendations, movie recommendations and trust.
Similar content being viewed by others
Data availability
Publicly datasets used with links below.
Book-Crossing: http://www2.informatik.uni-freiburg.de/~cziegler/BX/BX-CSV-Dump.zip, MovieLens100K: http://files.grouplens.org/datasets/movielens/ml-latest-small.zip, MovieLens1M: http://files.grouplens.org/datasets/movielens/ml-1m.zip, FilmTrust: https://www.librec.net/datasets/filmtrust.zip.
Code availability
Code made available for reproducible research at https://github.com/efpm04013/experiment3.
References
Aggarwal CC (2016) An introduction to recommender systems. RecomSyst. https://doi.org/10.1007/978-3-319-29659-3_1
Ketkar N (2017) Introduction to pytorch. Deep learning with python. Apress, Berkeley, pp 195–208. https://doi.org/10.1007/978-1-4842-2766-4_12
Chen T, Li M, Li Y, Lin M, Wang N, Wang M, Xiao T, Xu B, Zhang C, Zhang, Z. (2015) MXNet: a flexible and efficient machine learning library for heterogeneous distributed systems. https://doi.org/10.1145/2532637
Google (2018) Tensorflow. 2018
Kiran R, Kumar P, Bhasker B (2020) DNNRec: a novel deep learning based hybrid recommender system. Expert SystAppl. https://doi.org/10.1016/j.eswa.2019.113054
Lee W, Song K, Moon IC (2017) Augmented variational autoencoders for collaborative filtering with auxiliary information. In: Proceedings of the 2017 ACM on conference on information and knowledge management - CIKM ’17. pp 1139–1148. https://doi.org/10.1145/3132847.3132972
Langville A (2005) Nonnegative matrix factorization. Matrix 25(6):1336–1353. https://doi.org/10.1109/TPAMI.2011.18
Salakhutdinov R, Mnih A (2008) Bayesian probabilistic matrix factorization using Markov chain Monte Carlo. In: Proceedings of the 25th international conference on machine learning - ICML ’08. https://doi.org/10.1145/1390156.1390267
Sarwar BM., Karypis G, Konstan JA, Riedl JT (2000) Application of dimensionality reduction in recommender system - a case study. Architecture. https://doi.org/10.1138/744
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: Proceedings of the national conference on artificial intelligence.
Salakhutdinov, R., Mnih, A., & Hinton, G. (2007). Restricted Boltzmann machines for collaborative filtering. In: Proceedings of the 24th international conference on Machine learning - ICML ’07. pp 791–798. https://doi.org/10.1145/1273496.1273596
He X, Liao L, Zhang H, Nie L, Hu X, Chua T-S (2017) (NCF) Neural collaborative filtering. https://doi.org/10.1145/3038912.3052569
Catherine R, Cohen W (2017) Transnets. In: Proceedings of the eleventh ACM conference on recommender systems - RecSys ’17. pp 288–296. https://doi.org/10.1145/3109859.3109878
Cheng HT, Ispir M, Anil R, Haque Z, Hong L, Jain V, et al. (2016) Wide & deep learning for recommender systems. In: Proceedings of the 1st workshop on deep learning for recommender systems - DLRS 2016. pp 7–10. https://doi.org/10.1145/2988450.2988454
van den Oord A, Dieleman S, Schrauwen B (2013) Deep content-based music recommendation. Electron InfSyst Depart (ELIS). https://doi.org/10.1109/MMUL.2011.34.van
Liang D (2014) Content-aware collaborative music recommendation using pre-trained neural networks. In: ISMIR 2015: Proceedings of the 16th international society for music information retrieval conference. pp 295–301
Tan J, Wan X, Xiao J (2016) A neural network approach to quote recommendation in writings. In: Proceedings of the 25th ACM international on conference on information and knowledge management - CIKM ’16. pp 65–74. https://doi.org/10.1145/2983323.2983788
Bansal T, Belanger D, McCallum A (2016) Ask the GRU. In Proceedings of the 10th ACM conference on recommender systems - RecSys ’16. pp 107–114. https://doi.org/10.1145/2959100.2959180
Ko Y-J, Maystre L, Grossglauser M, Durrant RJ, Kim K-E (2016) Collaborative recurrent neural networks for dynamic recommender systems. JMLR 63:366–381. https://doi.org/10.1109/ICDE.2016.7498326
Balakrishnan A (2014) Deepplaylist: using recurrent neural networks to predict song similarity. In: Stanfort University, pp 1–7. Retrieved from https://cs224d.stanford.edu/reports/BalakrishnanDixit.pdf
Wu Y, DuBois C, Zheng AX, Ester M (2016) Collaborative denoising auto-encoders for top-N recommender systems. In: Proceedings of the ninth ACM international conference on web search and data mining - WSDM ’16. pp 153–162. https://doi.org/10.1145/2835776.2835837
Li X, She J (2017) Collaborative variational autoencoder for recommender systems. In: Proceedings of the 23rd ACM SIGKDD international conference on knowledge discovery and data mining - KDD ’17. pp 305–314. https://doi.org/10.1145/3097983.3098077
Sedhain S, Menon AK, Sanner S, Xie L (2015) Autorec: autoencoders meet collaborative filtering. In: WWW 2015 companion: proceedings of the 24th international conference on world wide web. pp 111–112. https://doi.org/10.1145/2740908.2742726
Sedhain S, Menon AK, Sanner S, Xie L (2015) Autorec: autoencoders meet collaborative filtering. In: 24th international conference on world wide web. https://doi.org/10.1145/2740908.2742726
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 - ICML ’08. https://doi.org/10.1145/1390156.1390294
Li S, Kawale J, Fu Y (2015) Deep collaborative filtering via marginalized denoising auto-encoder. In: Proceedings of the 24th ACM international on conference on information and knowledge management - CIKM ’15. pp 811–820. https://doi.org/10.1145/2806416.2806527
Strub F, Gaudel R, Mary J (2016) Hybrid recommender system based on autoencoders. In: proceedings of the 1st workshop on deep learning for recommender systems - DLRS 2016. pp 11–16. https://doi.org/10.1145/2988450.2988456
Braida F, Mello CE, Pasinato MB, Zimbrão G (2015) Transforming collaborative filtering into supervised learning. Expert SystAppl. https://doi.org/10.1016/j.eswa.2015.01.023
Barbieri J, Alvim LGM, Braida F, Zimbrão G (2017) Autoencoders and recommender systems: COFILS approach. Expert SystAppl 89:81–90. https://doi.org/10.1016/j.eswa.2017.07.030
Strub F, Mary J, Strub F, Mary J, Filtering C, Autoencoders D, Strub F (2015) Collaborative filtering with stacked denoising autoencoders and sparse inputs. In: NIPS workshop on machine learning for ecommerce, December 2015
Ziegler CN, McNee SM, Konstan JA, Lausen G (2005) Improving recommendation lists through topic diversification. https://doi.org/10.1145/1060745.1060754
Guo G, Zhang J, Yorke-Smith N (2013) A novel bayesian similarity measure for recommender systems. In: IJCAI international joint conference on artificial intelligence
Li S, Kawale J, Fu Y (2015) Deep collaborative filtering via marginalized denoising auto-encoder. https://doi.org/10.1145/2806416.2806527
LibRec - Examples & Comparison with Other Recommendation Libraries (n.d.). Retrieved 24 Nov 2018, from https://www.librec.net/release/v1.3/example.html
LibRec - Examples & comparison with other recommendation libraries. (n.d.). Retrieved 27 July 2019, from https://www.librec.net/release/v1.3/example.html
MyMediaLite: Example Experiments. (n.d.). Retrieved 24 Nov 2018, from http://www.mymedialite.net/examples/datasets.html
Funding
Not applicable.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interests
Not Applicable.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Rama, K., Kumar, P. & Bhasker, B. Deep autoencoders for feature learning with embeddings for recommendations: a novel recommender system solution. Neural Comput & Applic 33, 14167–14177 (2021). https://doi.org/10.1007/s00521-021-06065-9
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s00521-021-06065-9