Abstract
Recommender systems help users by filtering a large amount of content to which they are exposed daily, in order to recommend products in e-commerce, music, movies, people on social networks and others in a personalized way, thus being a complex task. Currently, sequential recommender systems have been increasingly used in these tasks. They receive behavior trajectories as input, that is, items accessed during a given time, and use recommendation algorithms to suggest the next item. In a graph-based representation of these sequences, an initial step involves learning representations for the items, vectors of real numbers called embeddings. In this work we propose to change the module responsible for building these item representations, which originally employs the GGNN technique in the SR-GNN Sequential Recommendation System, by the Graph-Sage technique with its aggregators: Mean, Maxpooling and LSTM. We validated our proposal with the datasets: yoochoose, diginetica, aotm and 30music. The results indicate that, with the Mean aggregator, it is possible to reduce the execution time in all tested scenarios, maintaining the original effectiveness.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Zhang, S., Yao, L., Sun, A., Tay, Y.: Deep learning for sequential recommendation: algorithms, influential factors, and evaluations. ACM Trans. Inf. Syst. 39(1), 1–41 (2020)
LeCun, Y., Bengio, Y., Hinton, G.: Deep learning. Nature 521, 436–444 (2015)
Wu, S., Tang, Y., Zhu, Y., Wang, L., Xie, X., Tan, T.: Session-based recommendation with graph neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33(1), pp. 346–353 (2019)
Wang, B., Cai, W.: Knowledge-enhanced graph neural networks for sequential recommendation. Information 11(8) (2020)
Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735–1780 (1997)
Li, J., Ren, P., Chen, Z., Ren, Z., Lian, T., Ma, J.: Neural attentive session-based recommendation. In: Proceedings of the 2017 ACM on Conference on Information and Knowledge Management, pp. 1419–1428. ACM, New York (2017)
Liu, Q., Zeng, Y., Mokhosi, R., Zhang, H.: STAMP: short-term attention/memory priority model for session-based recommendation. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1831–1839. ACM, New York (2018)
Wang, W., et al.: Beyond clicks: modeling multi-relational item graph for session-based target behavior prediction. In: Proceedings of the Web Conference 2020, New York, pp. 3056–3062 (2020)
Qiu, R., Li, J., Huang, Z., Yin, H.: Rethinking the item order in session-based recommendation with graph neural networks. In: Proceedings of the 28th ACM International Conference on Information and Knowledge Management, pp. 579–588. ACM, New York (2019)
Hamilton, W.L., Ying, R., Leskovec, J.: Inductive representation learning on large graphs. In: Proceedings of the 31st International Conference on Neural Information Processing Systems, pp. 1025–1035. Red Hook, USA (2017)
Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: Proceedings of the 32nd International Conference on Machine Learning, pp. 2048–2057. Lille, France (2015)
Chengfeng, X., et al.: Graph contextualized self-attention network for session-based recommendation. In: Proceedings of the 38th International Joint Conference on Artificial Intelligence, pp. 3940–3946. (2019)
Medsker, L.R., Jain, L.C.: Recurrent Neural Networks Desing and Applications, 1ft edn. CRC Press (1999)
Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. https://arxiv.org/abs/1609.02907. Accessed 09 June 2022
Li, Y., Tarlow, D., Brockschmidt, M., Zemel, R.: Gated graph sequence neural networks. https://arxiv.org/abs/1511.05493. Accessed 09 June 2022
Wu, S., Zhang, W., Sun, F., Cui, B.: Graph neural networks in recommender systems - a survey. https://arxiv.org/abs/2011.02260. Accessed 09 June 2022
Cucurull, G., Veličković, P., Casanova, A., Romero, A., Liò, P., Bengio, Y.: Graph attention networks. https://arxiv.org/abs/1710.10903. Accessed 09 June 2022
Gupta, P., Garg, D., Malhotra, P., Vig, L., Shroff, G.: NISER: normalized item and session representations to handle popularity bias. https://arxiv.org/abs/1909.04276. Accessed 09 June 2022
Liu, F., Liu, W., Li, X., Ye, Y.: Inter-sequence enhanced framework for personalized sequential recommendation. https://arxiv.org/abs/2004.12118. Accessed 09 June 2022
Wang, B.: Ranking evaluation metrics for recommender systems. https://towardsdatascience.com/ranking-evaluation-metrics-for-recommender-systems-263d0a66ef54. Accessed 09 June 2022
Acknowledgements
The authors thank CNPq for the financial support.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
da Silva, A.B., Spinosa, E.J. (2022). A Sequential Recommender System with Embeddings Based on GraphSage Aggregators. In: Xavier-Junior, J.C., Rios, R.A. (eds) Intelligent Systems. BRACIS 2022. Lecture Notes in Computer Science(), vol 13654 . Springer, Cham. https://doi.org/10.1007/978-3-031-21689-3_1
Download citation
DOI: https://doi.org/10.1007/978-3-031-21689-3_1
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-21688-6
Online ISBN: 978-3-031-21689-3
eBook Packages: Computer ScienceComputer Science (R0)