SGT: Session-based Recommendation with GRU and Transformer

Updata:01-01-1970

Source:
By:Author(s)

DOI: https://doi.org/10.30564/jcsr.v5i2.5610

Abstract:

Session-based recommendation aims to predict user preferences based on anonymous behavior sequences. Recent research on session-based recommendation systems has mainly focused on utilizing attention mechanisms on sequential patterns, which has achieved significant results. However, most existing studies only consider individual items in a session and do not extract information from continuous items, which can easily lead to the loss of information on item transition relationships. Therefore, this paper proposes a session-based recommendation algorithm (SGT) based on Gated Recurrent Unit (GRU) and Transformer, which captures user interests by learning continuous items in the current session and utilizes all item transitions on sessions in a more refined way. By combining short-term sessions and long-term behavior, user dynamic preferences are captured. Extensive experiments were conducted on three session-based recommendation datasets, and compared to the baseline methods, both the recall rate Recall@20 and the mean reciprocal rank MRR@20 of the SGT algorithm were improved, demonstrating the effectiveness of the SGT method.

References:

[1] Wang, H., Zeng, Y., Chen, J., et al., 2022. A spatiotemporal graph neural network for session-based recommendation. Expert Systems with Applications. 202, 117114. [2] Yang, C., Bai, L., Zhang, C., et al. (editors), 2017. Bridging collaborative filtering and semi-supervised learning: A neural approach for poi recommendation. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining; 2017 Aug 13-17; Halifax. New York: Association for Computing Machinery. p. 1245-1254. [3] Shu, K., Wang, S., Tang, J., et al. (editors), 2018. Crossfire: Cross media joint friend and item recommendations. Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining; 2018 Feb 5-9; Los Angeles. New York: Association for Computing Machinery. p. 522-530. [4] Corò, F., D' Angelo, G., Velaj, Y. (editors), 2019. Recommending links to maximize the influence in social networks. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI 2019); 2019 Aug 10-16; Macao. International Joint Conferences on Artificial Intelligence. p. 2195-2201. [5] Kim, Y., Kim, K., Park, C., et al. (editors), 2019. Sequential and diverse recommendation with long tail. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI 2019); 2019 Aug 10-16; Macao. International Joint Conferences on Artificial Intelligence. p.2740-2746. [6] Fan, W., Derr, T., Ma, Y., et al. (editors), 2019. Deep adversarial social recommendation. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19); 2019 Aug 10-16; Macao. International Joint Conferences on Artificial Intelligence. p. 1351-1357. [7] Al Ridhawi, I., Otoum, S., Aloqaily, M., et al., 2020. Providing secure and reliable communication for next generation networks in smart cities. Sustainable Cities and Society. 56, 102080. [8] Song, W., Xiao, Z., Wang, Y., et al. (editors), 2019. Session-based social recommendation via dynamic graph attention networks. Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining; 2019 Feb 11-15; Melbourne. New York: Association for Computing Machinery. p. 555-563. [9] Rendle, S., Freudenthaler, C, Schmidt-Thieme, L. (editors), 2010. Factorizing personalized Markov chains for next-basket recommendation. Proceedings of the 19th International Conference on World Wide Web; 2010 Apr 26-30; Raleigh. New York: Association for Computing Machinery. p. 811-820. [10] Kang, W.C., McAuley, J. (editors), 2018. Self-attentive sequential recommendation. 2018 IEEE International Conference on Data Mining (ICDM); 2018 Nov 17-20; Singapore. New York: IEEE. p. 197-206. [11] He, R., McAuley, J. (editors), 2016. Fusing similarity models with Markov chains for sparse sequential recommendation. 2016 IEEE 16th International Conference on Data Mining (ICDM); 2016 Dec 12-15; Barcelona. New York: IEEE. p. 191-200. [12] Hidasi, B., Karatzoglou, A., Baltrunas, L., et al. (editors), 2016. Session-based recommendations with recurrent neural networks. 4th International Conference on Learning Representations; 2016 May 2-4; San Juan. International Conference on Learning Representations. p. 289. [13] Li, J., Ren, P., Chen, Z., et al. (editors), 2017. Neural attentive session-based recommendation. Proceedings of the 2017 ACM on Conference on Information and Knowledge Management; 2017 Nov 6-10; Singapore. New York: Association for Computing Machinery. p. 1419-1428. [14] Tan, Y.K., Xu, X., Liu, Y. (editors), 2016. Improved recurrent neural networks for session-based recommendations. Proceedings of the 1st Workshop on Deep Learning for Recommender Systems; 2016 Sep 15; Boston. New York: Association for Computing Machinery. p. 17-22. [15] Song, K., Ji, M., Park, S., et al., 2019. Hierarchical context enabled recurrent neural network for recommendation. Proceedings of the AAAI Conference on Artificial Intelligence. 33(1), 4983-4991. [16] Wu, S., Tang, Y., Zhu, Y., et al., 2019. Session-based recommendation with graph neural networks. Proceedings of the AAAI Conference on Artificial Intelligence. 33(1), 346-353. [17] Xu, C., Zhao, P., Liu, Y., et al. (editors), 2019. Graph contextualized self-attention network for session-based recommendation. Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence (IJCAI-19); 2019 Aug 10-16; Macao. International Joint Conferences on Artificial Intelligence. p. 3940-3946. [18] Qiu, R., Li, J., Huang, Z. (editors), et al., 2019. Rethinking the item order in session-based recommendation with graph neural networks. Proceedings of the 28th ACM International Conference on Information and Knowledge Management; 2019 Nov 3-7; Beijing. New York: Association for Computing Machinery. p. 579-588. [19] Chen, T., Wong, R.C.W. (editors), 2020. Handling information loss of graph neural networks for session-based recommendation. Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining; 2020 Jul 6-10; New York. New York: Association for Computing Machinery. p. 1172-1180. [20] Pan, Z., Cai, F., Chen, W., et al. (editors), 2020. Star graph neural networks for session-based recommendation. Proceedings of the 29th ACM International Conference on Information & Knowledge Management; 2020 Oct 19-23; New York. New York: Association for Computing Machinery. p. 1195-1204. [21] Xu, K., Hu, W., Leskovec, J., et al., 2018. How powerful are graph neural networks? arXiv preprint arXiv:1810.00826. [22] Vaswani, A., Shazeer, N., Parmar, N., et al. (editors), 2017. Attention is all you need. 31st Conference on Neural Information Processing Systems (NIPS 2017); Long Beach. New York: Association for Computing Machinery. p. 5998-6008. [23] Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al., 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv: 2010.11929. [24] Rives, A., Meier, J., Sercu, T., et al., 2021. Biological structure and function emerge from scaling unsupervised learning to 250 million protein sequences. Proceedings of the National Academy of Sciences. 118(15), e2016239118. [25] Wang, P., Guo, J., Lan, Y., et al. (editors), 2015. Learning hierarchical representation model for nextbasket recommendation. Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval; 2015 Aug 9-13; Santiago. New York: Association for Computing Machinery. p. 403-412. [26] Cho, K., Van Merriënboer, B., Gulcehre, C., et al., 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078. [27] Liu, Q., Zeng, Y., Mokhosi, R., et al. (editors), 2018. STAMP: Short-term attention/memory priority model for session-based recommendation. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining; 2018 Aug 19-23; London. New York: Association for Computing Machinery. p. 1831-1839. [28] Wu, T., Sun, F., Dong, J., et al., 2022. Context-aware session recommendation based on recurrent neural networks. Computers and Electrical Engineering. 100, 107916. [29] Yu, F., Zhu, Y., Liu, Q., et al. (editors), 2020. TAGNN: target attentive graph neural networks for session-based recommendation. Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval; 2020 Jul 25-30; Xi'an. New York: Association for Computing Machinery. p. 1921-1924. [30] Zhang, M., Wu, S., Gao, M., et al., 2020. Personalized graph neural networks with attention mechanism for session-aware recommendation. IEEE Transactions on Knowledge and Data Engineering. 34(8), 3946-3957. [31] Sarwar, B., Karypis, G., Konstan, J., et al. (editors), 2001. Item-based collaborative filtering recommendation algorithms. Proceedings of the 10th International Conference on World Wide Web; 2001 May 1-5; Hong Kong.New York: Association for Computing Machinery. p. 285-295.

Tags: