Sequence Recommendation Algorithm of Graph Neural Networks Based on Complex Structure Information

doi:10.19678/j.issn.1000-3428.0061308

Abstract

Abstract: Graph structures have received significant attention, owing to their natural adaptability for sessions.Thus, many researchers have investigated Graph Neural Networks (GNN)-based recommending algorithms and achieved state-of-the-art performances.Existing session-based recommendations based on GNN can yield relatively accurate recommendations, utilizing structural graph information.However, they neither consider repetitive submissions from users and complex transition between items nor fully utilize complex graph structural information.Consequently, they result in prediction losses.This paper proposes a GNN sequence recommendation algorithm based on the fusion of directed and undirected information with attention.The proposed algorithm combines directed and undirected structural information of session graphs into new hidden embeddings of items.By using repetitive behavioral information and attention mechanisms, the model incorporates complex transitions of items to form better session embeddings.During feature propagation, each node strikes a balance between preserving its information and absorbing its neighbors' information, improving the accuracy of recommendation predictions.The experimental results for Diginetica, Yoochoose 1/64, and Yoochoose 1/4 data sets show that compared with the best existing algorithms, that is, Session-based Recommendation with GNN (SR-GNN) and Target Attentive GNN (TAGNN), the accuracy of the algorithm can be improved by up to 4.34%. The proposed algorithm can predict the accuracy of the user's next click better in a session.

Key words: graph structure, Graph Neural Networks(GNN), session sequence, recommending algorithm, attention mechanism

摘要： 图结构因其在序列推荐场景中的自然适应性而备受关注，而现有的基于图神经网络的会话序列推荐算法虽然能够利用图结构信息达到较好的推荐效果，但是没有考虑用户在会话序列中的重复点击行为和项目之间的复杂转换，且未很好地利用图中复杂的结构信息，导致推荐的效果受到一定程度的限制。提出有向与无向信息同注意力相融合的图神经网络序列推荐算法，并基于推荐算法给出项目隐含向量建模算法，结合会话序列图中的有向结构信息与无向结构信息，通过考虑用户的重复点击行为和引入注意力机制建立会话中点击项目的复杂转换模型。图节点在特征传播的过程中平衡邻居节点信息与自身信息的比例，以更准确地预测推荐过程中生成的会话向量。在Diginetica、Yoochoose 1/64、Yoochoose 1/4 3个数据集上的实验结果表明，与SR-GNN、TAGNN算法相比，该算法精度最高提升4.34%，能够更好地预测用户在会话中的下一次点击精度。

关键词: 图结构, 图神经网络, 会话序列, 推荐算法, 注意力机制

CLC Number:

TP399

HU Chengzuo, WANG Qingmei, LI Dichao, WANG Zheng. Sequence Recommendation Algorithm of Graph Neural Networks Based on Complex Structure Information[J]. Computer Engineering, 2022, 48(5): 82-90,97.

胡承佐, 王庆梅, 李迪超, 王铮. 基于复杂结构信息的图神经网络序列推荐算法[J]. 计算机工程, 2022, 48(5): 82-90,97.

/ / Recommend / Download Citations

URL: http://www.ecice06.com/EN/10.19678/j.issn.1000-3428.0061308

http://www.ecice06.com/EN/Y2022/V48/I5/82

Figures/Tables 7

References

[1] 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, USA:ACM Press, 2020:1172-1180.
[2] CHENG Z Y, SHEN J L, ZHU L, et al.Exploiting music play sequence for music recommendation[C]//Proceedings of IEEE IJCAIʼ17.Washington D.C., USA:IEEE Press, 2017:3654-3660.
[3] QIU R H, LI J J, HUANG Z, et al.Rethinking the item order in session-based recommendation with graph neural networks[C]//Proceedings of the 28th ACM International Conference on Information and Knowledge Management.New York, USA:ACM Press, 2019:579-588.
[4] WU S, TANG Y Y, ZHU Y Q, et al.Session-based recommendation with graph neural networks[EB/OL].[2021-02-20].https://arxiv.org/abs/1811.00855.
[5] 王健宗, 孔令炜, 黄章成, 等.图神经网络综述[J].计算机工程, 2021, 47(4):1-12. WANG J Z, KONG L W, HUANG Z C, et al.Survey of graph neural network[J].Computer Engineering, 2021, 47(4):1-12.(in Chinese)
[6] 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:[s.n.], 2019:3940-3946.
[7] DAVIDSON J, LIEBALD B, LIU J N, et al.The YouTube video recommendation system[C]//Proceedings of the 4th ACM Conference on Recommender Systems.New York, USA:ACM Press, 2010:293-296.
[8] DIAS R, FONSECA M J.Improving music recommendation in session-based collaborative filtering by using temporal context[C]//Proceedings of the 25th IEEE International Conference on Tools with Artificial Intelligence.Washington D.C., USA:IEEE Press, 2013:783-788.
[9] PARK S E, LEE S, LEE S G.Session-based collaborative filtering for predicting the next song[C]//Proceedings of the 1st ACIS/JNU International Conference on Computers, Networks, Systems and Industrial Engineering.Washington D.C., USA:IEEE Press, 2011:353-358.
[10] SHANI G, BRAFMAN R I, HECKERMAN D.An MDP-based recommender system[EB/OL].[2021-02-20].https://arxiv.org/ftp/arxiv/papers/1301/1301.0600.pdf.
[11] RENDLE S, FREUDENTHALER C, SCHMIDT-THIEME L.Factorizing personalized Markov chains for next-basket recommendation[C]//Proceedings of the 19th IEEE Inter-national Conference on World Wide Web.Washington D.C., USA:IEEE Press, 2010:811-820.
[12] CHEN S, MOORE J L, TURNBULL D, et al.Playlist prediction via metric embedding[C]//Proceedings of the 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining.New York, USA:ACM Press, 2012:714-722.
[13] HIDASI B, KARATZOGLOU A, BALTRUNAS L, et al.Session-based recommendations with recurrent neural networks[EB/OL].[2021-02-20].https://arxiv.org/abs/1511.06939.
[14] LI J, REN P J, CHEN Z M, et al.Neural attentive session-based recommendation[C]//Proceedings of 2017 ACM Conference on Information and Knowledge Management.New York, USA:ACM Press, 2017:1419-1428.
[15] CHEN T W, WONG R C W.Session-based recommendation with local invariance[C]//Proceedings of 2019 IEEE International Conference on Data Mining.Washington D.C., USA:IEEE Press, 2019:994-999.
[16] REN P J, CHEN Z M, LI J, et al.RepeatNet:a repeat aware neural recommendation machine for session-based recommendation[C]//Proceedings of AAAI Conference on Artificial Intelligence.[S.1.]:AAAI Press, 2019:4806-4813.
[17] SONG J, SHEN H, OU Z J, et al.ISLF:interest shift and latent factors combination model for session-based recommendation[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence.Macao, China:[s.n.], 2019:5765-5771.
[18] 呼延康, 樊鑫, 余乐天, 等.图神经网络回归的人脸超分辨率重建[J].软件学报, 2018, 29(4):914-925. HUYAN K, FAN X, YU L T, et al.Graph based neural network regression strategy for facial image super-resolution[J].Journal of Software, 2018, 29(4):914-925.(in Chinese)
[19] KIPF T N, WELLING M.Semi-supervised classification with graph convolutional networks[EB/OL].[2021-02-20].https://arxiv.org/abs/1609.02907.
[20] WU F, ZHANG T Y, SOUZA A H J, et al.Simplifying graph convolutional networks[EB/OL].[2021-02-20].https://arxiv.org/abs/1902.07153.
[21] LI Y J, TARLOW D, BROCKSCHMIDT M, et al.Gated graph sequence neural networks[EB/OL].[2021-02-20].https://arxiv.org/abs/1511.05493.
[22] YU F, ZHU Y Q, LIU Q, et al.TAGNN:target attentive 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, USA:ACM Press, 2020:1921-1924.
[23] LIU Q, ZENG Y F, MOKHOSI R, et al.STAMP:short-term attention/memory priority model for session-based recommendation[C]//Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining.New York, USA:ACM Press, 2018:1831-1839.
[24] TAN Y K, XU X X, LIU Y.Improved recurrent neural networks for session-based recommendations[C]//Proceedings of the 1st IEEE Workshop on Deep Learning for Recommender Systems.Washington D.C., USA:IEEE Press, 2016:17-22.
[25] SARWAR B, KARYPIS G, KONSTAN J, et al.Item-based collaborative filtering recommendation algorithms[C]//Proceedings of the 10th International Conference on World Wide Web.Washington D.C., USA:IEEE Press, 2001:285-295.
[26] RENDLE S, FREUDENTHALER C, GANTNER Z, et al.BPR:Bayesian personalized ranking from implicit feedback[EB/OL].[2021-02-20].https://arxiv.org/abs/1205.2618.

Please choose a citation manager

Content to export