Session Recommendation Algorithm Combining Item Transition Relations and Time-Order Information

doi:10.3778/j.issn.1673-9418.2211090

Abstract

Abstract: Aiming at the problem that the existing graph neural network session recommendation algorithm ignores all kinds of auxiliary information, which leads to the inability to accurately model the session sequence, a session recommendation algorithm combining the item transition relations and time-order information (RTSR) is proposed. Firstly, the shortest path sequence between any two nodes is obtained by using the graph network structure, which is encoded as the item transition relations between corresponding items through the gated recurrent unit (GRU), and then the global dependency information of the session is captured from the perspective of the graph by combining the self-attention mechanism. At the same time, a lossless graph coding scheme is designed to alleviate the problem of information loss in the process of session graph coding. The scheme quantifies the time-order information in the session sequence reasonably, and takes it as the weight of the edges in the session graph, and then combines the gated graph sequence neural network to obtain the local dependency information of the session. Finally, with linear combination of global dependency information and local dependency information, and in combination with reverse position information, the user??s preference for item is finally generated, and the recommendation list is given. The performance comparison experiment with mainstream models such as SR-GNN, GC-SAN and GCE-GNN on the public benchmark datasets Gowalla and Diginetica shows that RTSR improves at least 6.13% and 1.58% in average reciprocal ranking respectively, and the recommendation accuracy is also improved accordingly.

Key words: graph neural network, session recommendation, shortest path sequence, time-order information, reverse position information

摘要： 针对现有图神经网络会话推荐算法忽略了各类辅助信息，导致不能准确地建模会话序列的问题，提出了一种融合物品的转换关系和时序信息的会话推荐算法（RTSR）。首先利用图网络结构得到任意两个节点之间的最短路径序列，经过双向门控循环单元（GRU）将其编码为对应物品之间的转换关系，再结合自注意力机制从图的角度捕捉会话的全局依赖信息。同时设计了一种无损图编码方案来缓解会话图编码过程中信息损失的问题。该方案将会话序列中的时序信息进行合理的量化，并将其作为会话图中边的权重，再结合门控图神经网络获取会话的局部依赖信息。最后，线性组合全局依赖信息和局部依赖信息并结合反向位置信息，最终生成用户对物品的兴趣偏好，并给出推荐列表。在公共基准数据集Gowalla和Diginetica上与SR-GNN、GC-SAN、GCE-GNN等主流模型进行性能对比实验，结果表明RTSR在平均倒数排名方面分别至少提高了6.13%和1.58%，同时推荐精准度方面也有相应的提高。

WU Wenzheng, LU Xianling. Session Recommendation Algorithm Combining Item Transition Relations and Time-Order Information[J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(3): 768-779.

吴文政, 卢先领. 融合物品转换关系和时序信息的会话推荐算法[J]. 计算机科学与探索, 2024, 18(3): 768-779.

References

[1] 朱扬勇, 孙婧. 推荐系统研究进展[J]. 计算机科学与探索, 2015, 9(5): 513-525.
ZHU Y Y, SUN J. Recommender system: up to now[J]. Journal of Frontiers of Computer Science and Technology, 2015, 9(5): 513-525.
[2] 赵海燕, 赵佳斌, 陈庆奎, 等. 会话推荐系统[J]. 小型微型计算机系统, 2019, 40(9): 1869-1875.
ZHAO H Y, ZHAO J B, CHEN Q K, et al. Session-based recommendation system[J]. Journal of Chinese Computer Systems, 2019, 40(9): 1869-1875.
[3] 曾义夫, 牟其林, 周乐, 等. 基于图表示学习的会话感知推荐模型[J]. 计算机研究与发展, 2020, 57(3): 590-603.
ZENG Y F, MOU Q L, ZHOU L, et al. Graph embedding based session perception model for next-click recommendation[J]. Journal of Computer Research and Development, 2020, 57(3): 590-603.
[4] 方军, 管业鹏. 基于双编码器的会话型推荐模型[J]. 西安交通大学学报, 2021, 55(8): 166-174.
FANG J, GUAN Y P. A session recommendation model based on dual encoders[J]. Journal of Xi??an Jiaotong University, 2021, 55(8): 166-174.
[5] SARWAR B, KARYPIS G, KONSTAN J, et al. Item-based collaborative filtering recommendation algorithms[C]//Proceedings of the 10th International World Wide Web Conference, Hong Kong, China, May 1-5, 2001: 285-295.
[6] HE R N, MCAULEY J. Fusing similarity models with Markov chains for sparse sequential recommendation[C]//Proceedings of the 16th International Conference on Data Mining, Barcelona, Dec 12-15, 2016: 191-200.
[7] HIDASI B, KARAT Z A, BALTRUNAS L, et al. Session-based recommendations with recurrent neural networks[C]//Proceedings of the 4th International Conference on Learning Representations, San Juan, May 2-4, 2016.
[8] LI J, REN P, CHEN Z, et al. Neural attentive session-based recommendation[C]//Proceedings of the 2017 ACM Conference on Information and Knowledge Management. New York: ACM, 2017: 1419-1428.
[9] LIU Q, ZENG Y F, MOKHOSI R, et al. Short-term attention/memory priority model for session-based recommendation[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, Aug 19-23, 2018. New York: ACM, 2018: 1831-1839.
[10] LIN J C W, SHAO Y, DJENOURI Y, et al. ASRNN: a recurrent neural network with an attention model for sequence labeling[J]. Knowledge-Based Systems, 2021, 212: 106548.
[11] 黄震华, 林小龙, 孙圣力, 等. 会话场景下基于特征增强的图神经推荐方法[J]. 计算机学报, 2022, 45(4): 766-780.
HUANG Z H, LIN X L, SUN S L, et al. Feature augmentation based graph neural recommendation method in session scenarios[J]. Chinese Journal of Computers, 2022, 45(4): 766-780.
[12] 任俊伟, 曾诚, 肖丝雨, 等. 基于会话的多粒度图神经网络推荐模型[J]. 计算机应用, 2021, 41(11): 3164-3170.
REN J W, ZENG C, XIAO S Y, et al. Session-based recommendation model of multi-granular graph neural network[J]. Journal of Computer Applications, 2021, 41(11): 3164-3170.
[13] 吴静, 谢辉, 姜火文. 图神经网络推荐系统综述[J]. 计算机科学与探索, 2022, 16(10): 2249-2263.
WU J, XIE H, JIANG H W. Survey of graph neural network in recommendation system[J]. Journal of Frontiers of Computer Science and Technology, 2022, 16(10): 2249-2263.
[14] WU S, TANG Y Y, ZHU Y Q, et al. Session-based recommendation with graph neural networks[C]//Proceedings of the 2019 AAAI Conference on Artificial Intelligence. Menlo Park: AAAI, 2019: 346-353.
[15] XU C F, ZHAO P P, LIU Y C, et al. Graph contextualized self-attention network for session-based recommendation[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China, Aug 10-16, 2019: 3940-3946.
[16] RENDLE S, FREUDEN T C, SCHMIDT T L. Factorizing personalized Markov chains for next-basket recommendation[C]//Proceedings of the 19th International Conference on World Wide Web, Raleigh, Apr 26-30, 2010. New York: ACM, 2010: 811-820.
[17] KOREN Y, BELL R, VOLINSKY C. Matrix factorization techniques for recommender systems[J]. Computer, 2009, 42(8): 30-37.
[18] ISENSEE F, JAEGER P F, KOHL S A A, et al. nnU-Net: a self-configuring method for deep learning-based biomedical image segmentation[J]. Nature Methods, 2021, 18(2): 203-211.
[19] CHO K, VAN MERRI?NBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[C]//Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Oct 26-28, 2014. Stroudsburg: ACL, 2014: 1724-1734.
[20] WANG M, REN P, MEI L, et al. A collaborative session-based recommendation approach with parallel memory modules[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2019: 345-354.
[21] ASWANI A V, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in Neural Information Processing Systems 30, Long Beach, Dec 4-9, 2017: 5998-6008.
[22] CHEN T W, WONG R C W. Handling information loss of graph neural networks for session-based recommendation[C]//Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York: ACM, 2020: 1172-1180.
[23] WANG Z Y, WEI W, CONG G, et al. Global context enhanced graph neural networks for session-based recommendation[C]//Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2020: 169-178.
[24] CAI D, LAM W. Graph transformer for graph-to-sequence learning[C]//Proceedings of the 2020 AAAI Conference on Artificial Intelligence. Menlo Park: AAAI, 2020: 7464-7471.
[25] ZHU G, HOU H, CHEN J, et al. Transition relation aware self-attention for session-based recommendation[J]. arXiv:2203.06407, 2022.
[26] GUPTA P, GARG D, MALHOTRA P, et al. NISER: normalized item and session representations to handle popularity bias[J]. arXiv:1909.04276, 2019.