双通道异构图神经网络序列推荐算法

doi:10.3778/j.issn.1673-9418.2205053

摘要/Abstract

摘要： 基于用户行为序列的推荐系统的目的是根据上一次序列的顺序预测用户的下一次点击。目前的研究一般是根据用户行为序列中项目的转换来了解用户偏好。然而，行为序列中的其他有效信息被忽略，如用户配置文件，这会导致模型无法了解用户的特定偏好。提出了一种基于双通道异构图神经网络的用户行为序列推荐算法（DC-HetGNN），该方法通过异构图神经网络通道和异构图线图通道学习行为序列嵌入，并捕获用户的特定偏好。DC-HetGNN会根据行为序列构造包含各种类型节点的异构图，可以捕获项目、用户和序列之间的依赖关系。其次，异构图神经网络通道和异构图线图通道捕获物品复杂转换及序列之间的交互信息，并学习包含用户信息的物品嵌入。最后，考虑到用户长期和短期偏好的影响，将局部和全局序列嵌入与注意力网络相结合，得到最终的序列嵌入。在两个电商用户行为序列数据集Diginetica和Tmall上进行的实验表明，DC-HetGNN与新近模型FGNN相比在指标平均倒数排名（MRR）和召回率（Recall）中平均分别提升2.08%和0.78%，与TGSRec相比在指标MRR@n和Recall@n中平均分别提升2.70%和0.49%。

关键词: 推荐系统, 用户行为序列, 异构图神经网络

Abstract: The purpose of recommendation system based on user behavior sequence is to predict user??s next click according to the order of last sequence. The current research is generally based on the conversion of items in the user behavior sequence to understand user preferences. However, other valid information in the behavior sequence is ignored, such as the user profile, which results in the model failing to understand user??s specific preferences. In this paper, a user behavior sequence recommendation with dual channel heterogeneous graph neural network (DC-HetGNN) is proposed. The method uses a heterogeneous graph neural network channel and a heterogeneous graph line channel to learn behavior sequence embedding and capture the specific preferences of users. DC-HetGNN constructs heterogeneous graphs containing various types of nodes based on behavior sequences that capture dependencies between projects, users, and sequences. Then, the heterogeneous graph neural network channel and the heterogeneous graph line channel capture the complex transformation of items and the interaction between the sequences, and learn the embedding of items containing user information. Finally, considering the influence of users’ long-term and short-term preferences, local and global sequence embedding is combined with attention network to obtain the final sequence embedding. A large number of experiments conducted on Diginetica and Tmall, two real e-commerce user behavior sequence datasets, show that compared with recent model FGNN, DC-HetGNN is improved by 2.08% and 0.78% on average in performance criterions mean reciprocal rank (MRR) and Recall, respectively, and by 2.70% and 0.49% in performance criterions MRR@n and Recall@n, respectively, compared with recent model TGSRec.

Key words: recommender system, user behavior sequence, heterogeneous graph neural network

邬锦琛, 杨兴耀, 于炯, 李梓杨, 黄擅杭, 孙鑫杰. 双通道异构图神经网络序列推荐算法[J]. 计算机科学与探索, 2023, 17(6): 1473-1486.

WU Jinchen, YANG Xingyao, YU Jiong, LI Ziyang, HUANG Shanhang, SUN Xinjie. Sequence Recommendation with Dual Channel Heterogeneous Graph Neural Network[J]. Journal of Frontiers of Computer Science and Technology, 2023, 17(6): 1473-1486.

参考文献

[1] WANG S, CAO L, WANG Y, et al. A survey on session-based recommender systems[J]. ACM Computing Surveys, 2021, 54(7): 1-38.
[2] WU Z, PAN S, CHEN F, et al. A comprehensive survey on graph neural networks[J]. IEEE Transactions on Neural Net-works and Learning Systems, 2020, 32(1): 4-24.
[3] XU K, HU W, LESKOVEC J, et al. How powerful are graph neural networks?[J]. arXiv:1810.00826, 2018.
[4] WU S, TANG Y Y, ZHU Y Q, et al. Session-based recommen-dation with graph neural networks[C]//Proceedings of the 33rd AAAI Conference on Artificial Intelligence, the 31st Innovative Applications of Artificial Intelligence Conference, the 9th AAAI Symposium on Educational Advances in Arti-ficial Intelligence, Honolulu, Jan 27-Feb 1, 2019. Menlo Park: AAAI, 2019: 346-353.
[5] ZHANG C, SONG D, HUANG C, et al. Heterogeneous graph neural network[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Aug 4-8, 2019. New York: ACM, 2019: 793-803.
[6] ZHANG J, LIN Y, LIN M, et al. An effective collaborative filtering algorithm based on user preference clustering[J]. Applied Intelligence, 2016, 45(2): 230-240.
[7] RENDLE S, KRICHENE W, ZHANG L, et al. Neural colla-borative filtering vs. matrix factorization revisited[C]//Procee-dings of the 14th ACM Conference on Recommender Systems, Brazil, Sep 22-26, 2020. New York: ACM, 2020: 240-248.
[8] RENDLE S, FREUDENTHALER C, GANTNER Z, et al. BPR: Bayesian personalized ranking from implicit feedback[J]. arXiv:1205.2618, 2012.
[9] HIDASI B, KARATZOGLOU A, BALTRUNAS L, et al. Session-based recommendations with recurrent neural networks[J]. arXiv:1511.06939, 2015.
[10] XU C, ZHAO P, LIU Y, 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. San Francisco: Morgan Kaufmann, 2019: 3940-3946.
[11] QIU R H, HUANG Z, LI J J, et al. Exploiting cross-session information for session-based recommendation with graph neural networks[J]. ACM Transactions on Information Systems, 2020, 38(3): 1-23.
[12] FAN Z W, LIU Z W, ZHANG J W, et al. Continuous-time sequential recommendation with temporal graph collaborative transformer[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management, Queens-land, Nov 1-5, 2021. New York: ACM, 2021: 433-442.
[13] 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 Con-ference on Research and Development in Information Retrieval, Jul 25-30, 2020. New York: ACM, 2020: 169-178.
[14] YU B, ZHANG R, CHEN W, et al. Graph neural network based model for multi-behavior session-based recommendation[J]. GeoInformatica, 2022, 26(4): 429-447.
[15] YANG D Q, WANG Z Y, JIANG J Y, et al. Knowledge embed-ding towards the recommendation with sparse user-item in-teractions[C]//Proceedings of the 2019 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining, Vancouver, Aug 27-30, 2019. New York: ACM, 2019: 325-332.
[16] PEROZZI B, AL-RFOU R, SKIENA S. DeepWalk: online learning of social representations[C]//Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, Aug 24-27, 2014. New York: ACM, 2014: 701-710.
[17] DONG Y X, CHAWLA N V, SWAMI A. metapath2vec: scala-ble representation learning for heterogeneous networks[C]//Proceedings of the 23rd ACM SIGKDD International Con-ference on Knowledge Discovery and Data Mining, Halifax, Aug 13-17, 2017. New York: ACM, 2017: 135-144.
[18] GROVER A, LESKOVEC J. node2vec: scalable feature learning for networks[C]//Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, Aug 13-17, 2016. New York: ACM, 2016: 855-864.
[19] TANG J, QU M, WANG M Z, et al. LINE: large-scale infor-mation network embedding[C]//Proceedings of the 24th In-ternational Conference on World Wide Web, Florence, May 18-22, 2015. New York: ACM, 2015: 1067-1077.
[20] LIAO L, HE X, ZHANG H, et al. Attributed social network embedding[J]. IEEE Transactions on Knowledge and Data Engineering, 2018, 30(12): 2257-2270.
[21] SUN Y, HAN J, YAN X, et al. PathSim: meta path-based top-k similarity search in heterogeneous information networks[J]. Proceedings of the VLDB Endowment, 2011, 4(11): 992-1003.
[22] SUN Y, NORICK B, HAN J, et al. PathSelClus: integrating meta-path selection with user-guided object clustering in hetero-geneous information networks[J]. ACM Transactions on Know-ledge Discovery from Data , 2013, 7(3): 1-23.
[23] REN X, LIU J L, YU X, et al. ClusCite: effective citation recommendation by information network-based clustering[C]//Proceedings of the 20th ACM SIGKDD International Con-ference on Knowledge Discovery and Data Mining, New York, Aug 24-27, 2014. New York: ACM, 2014: 821-830.
[24] HU B B, SHI C, ZHAO W X, et al. Leveraging meta-path based context for top-n recommendation with a neural co-attention model[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, London, Aug 19-23, 2018. New York: ACM, 2018: 1531-1540.