Abstract
Sequential Recommendation with Bidirectional Encoder Representations from Transformer, BERT4Rec, is an efficient and effective model for sequential recommendation, regarded as a state-of-the-art in this field. However, studies of said architecture achieve varying results, causing doubts whether it is possible to consistently reproduce the result with reported training parameters. This study aims to test the performance and reproducibility of a BERT4Rec implementation on MovieLens1M and Netflix Prize datasets. Overall findings suggest that while using a proper implementation, BERT4Rec can still be called a state-of-the-art solution, additional work is needed to increase reproducibility of the original model. Moreover, possible avenues for further improvement are discussed.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Bennett, J., Lanning, S., et al.: The netflix prize. In: KDD cup and workshop. vol. 2007, p. 35. New York (2007)
Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. preprint arXiv:1810.04805 (2018)
Elahi, M., Ricci, F., Rubens, N.: A survey of active learning in collaborative filtering recommender systems. Comput. Sci. Rev. 20, 29–50 (2016)
Fan, Z., Liu, Z., Zhang, J., Xiong, Y., Zheng, L., Yu, P.S.: Continuous-time sequential recommendation with temporal graph collaborative transformer. In: 30th ACM International Conference on Information and Knowledge Management, pp. 433–442 (2021)
Harper, F., Konstan, J.: Movielens data set. ACM Trans. Interact. Intell. Syst. 5(4), 1–19 (2006)
Herlocker, J.L., Konstan, J.A., Terveen, L.G., Riedl, J.: Evaluating collaborative filtering recommender systems. ACM Trans. Inf. Syst. 22, 5–53 (2004)
Hidasi, B., Karatzoglou, A., Baltrunas, L., Tikk, D.: Session-based recommendations with recurrent neural networks. preprint arXiv:1511.06939 (2015)
Jaywonchung: Pytorch implementation of bert4rec and netflix vae. https://github.com/jaywonchung/BERT4Rec-VAE-Pytorch
Kang, W.C., McAuley, J.: Self-attentive sequential recommendation. In: 2018 IEEE ICDM, pp. 197–206. IEEE (2018)
Kannout, E.: Context clustering-based recommender systems. In: 2020 15th FedCSIS, pp. 85–91. IEEE (2020)
Karpus, A., Raczynska, M., Przybylek, A.: Things you might not know about the k-nearest neighbors algorithm. In: KDIR, pp. 539–547 (2019)
Koren, Y.: Factorization meets the neighborhood: a multifaceted collaborative filtering model. In: 14th ACM SIGKDD, pp. 426–434 (2008)
Liang, D., Krishnan, R.G., Hoffman, M.D., Jebara, T.: Variational autoencoders for collaborative filtering (2018)
Lin, Z., et al.: A structured self-attentive sentence embedding. preprint arXiv:1703.03130 (2017)
Lops, P., De Gemmis, M., Semeraro, G.: Content-based recommender systems: State of the art and trends. Recommender sys. handbook, pp. 73–105 (2011)
Ma, C., Kang, P., Liu, X.: Hierarchical gating networks for sequential recommendation. In: 25th ACM SIGKDD, pp. 825–833 (2019)
Paulina Leszczełowska, M.B., Grabski, M.: Systematic literature review on click through rate prediction. In: 2nd Workshop on PeRS at ADBIS’23 (2023)
Pazzani, M.J., Billsus, D.: Content-based recommendation systems. In: Brusilovsky, P., Kobsa, A., Nejdl, W. (eds.) The Adaptive Web. LNCS, vol. 4321, pp. 325–341. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-72079-9_10
Petrov, A., Macdonald, C.: Effective and efficient training for sequential recommendation using recency sampling. In: 16th ACM Conference on Recommender System (2022)
Petrov, A., Macdonald, C.: A systematic review and replicability study of bert4rec for sequential recommendation. In: 16th ACM Conference on Recommender System (2022)
Radford, A., Narasimhan, K., Salimans, T., Sutskever, I., et al.: Improving language understanding by generative pre-training (2018)
Rendle, S., Freudenthaler, C., Schmidt-Thieme, L.: Factorizing personalized markov chains for next-basket recommendation. In: 19th International Conference on World wide web, pp. 811–820 (2010)
Sarwar, B.M., Karypis, G., Konstan, J.A., Riedl, J.: Item-based collaborative filtering recommendation algorithms. In: The Web Conf. (2001)
Shenbin, I., Alekseev, A., Tutubalina, E., Malykh, V., Nikolenko, S.I.: Recvae: A new variational autoencoder for top-n recommendations with implicit feedback. In: 13th International Conference on Web Search and Data Mining. ACM (jan 2020). https://doi.org/10.1145/3336191.3371831
Shiguang, W.: Furyton/recommender-baseline-model: Common used recommend baseline model. https://github.com/Furyton/Recommender-Baseline-Model
Sun, F., et al.: Bert4rec: Sequential recommendation with bidirectional encoder representations from transformer. In: 28th ACM International Conference on Information and Knowledge Management (2019)
Tang, J., Wang, K.: Personalized top-n sequential recommendation via convolutional sequence embedding. In: 11th ACM International Conference on Web Search and Data Mining, pp. 565–573 (2018)
Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing System, vol. 30 (2017)
Yuan, F., Karatzoglou, A., Arapakis, I., Jose, J.M., He, X.: A simple convolutional generative network for next item recommendation. In: 12th ACM International Conference on Web Search and Data Mining, pp. 582–590 (2019)
Yue, Z., He, Z., Zeng, H., McAuley, J.: Black-box attacks on sequential recommenders via data-free model extraction. In: 15th ACM Conference on Recommender System (2021)
Zang, R., Zuo, M., Zhou, J., Xue, Y., Huang, K.: Sequence and distance aware transformer for recommendation systems. In: 2021 IEEE ICWS, pp. 117–124 (2021)
Zhao, W.X., et al.: Recbole 2.0: Towards a more up-to-date recommendation library. In: 31st ACM International Conference on Information & Knowledge Management, pp. 4722–4726 (2022)
Zhou, K., et al.: S3-rec: Self-supervised learning for sequential recommendation with mutual information maximization. In: 29th ACM International Conference on Information & Knowledge Management, pp. 1893–1902 (2020)
Acknowledgements
Special thanks to Shiguang Wu from Shandong University for sharing his implementation of BERT4Rec model.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Gałka, A., Grubba, J., Walentukiewicz, K. (2023). Performance and Reproducibility of BERT4Rec. In: Abelló, A., et al. New Trends in Database and Information Systems. ADBIS 2023. Communications in Computer and Information Science, vol 1850. Springer, Cham. https://doi.org/10.1007/978-3-031-42941-5_55
Download citation
DOI: https://doi.org/10.1007/978-3-031-42941-5_55
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-42940-8
Online ISBN: 978-3-031-42941-5
eBook Packages: Computer ScienceComputer Science (R0)