Session recommendation method based on graph model and attention model

doi:10.11772/j.issn.1001-9081.2021091696

Journal of Computer Applications ›› 2022, Vol. 42 ›› Issue (11): 3610-3616.DOI: 10.11772/j.issn.1001-9081.2021091696

Special Issue: 人工智能

• Artificial intelligence • Previous Articles Next Articles

Session recommendation method based on graph model and attention model

Weichao DANG, Zhiyu YAO(), Shangwang BAI, Gaimei GAO, Chunxia LIU

College of Computer Science and Technology，Taiyuan University of Science and Technology，Taiyuan Shanxi 030024，China

Received:2021-09-26 Revised:2022-03-07 Accepted:2022-03-21 Online:2022-11-14 Published:2022-11-10
Contact: Zhiyu YAO
About author:DANG Weichao， born in 1974， Ph. D.， associate professor. His research interests include intelligent computing， software reliability.
YAO Zhiyu， born in 1995， M. S. candidate. His research interests include session recommendation.
BAI Shangwang， born in 1964， M. S.， professor. His research interests include digital intelligent software system.
GAO Gaimei， born in 1978， Ph. D.， lecturer. Her research interests include network security， cryptography.
LIU Chunxia， born in 1977， M. S.， associate professor. Her research interests include software engineering， database.
Supported by:
Natural Science Foundation of Shanxi Province(201901D111266)

基于图模型和注意力模型的会话推荐方法

党伟超, 姚志宇(), 白尚旺, 高改梅, 刘春霞

太原科技大学计算机科学与技术学院，太原 030024

通讯作者: 姚志宇
作者简介:党伟超（1974—），男，山西运城人，副教授，博士，CCF会员，主要研究方向：智能计算、软件可靠性
姚志宇（1995—），男，山西朔州人，硕士研究生，主要研究方向：会话推荐 S20190660@stu.tyust.edu.cn
白尚旺（1964—），男，山西吕梁人，教授，硕士，主要研究方向：智能软件系统
高改梅（1978—），女，山西吕梁人，副教授，博士，CCF会员，主要研究方向：网络安全、密码学
刘春霞（1977—），女，山西大同人，副教授，硕士，CCF会员，主要研究方向：软件工程、数据库。
基金资助:
山西省自然科学基金资助项目(201901D111266)

Abstract

Abstract:

To solve the problem that representation of interest preferences based on the Recurrent Neural Network （RNN） is incomplete and inaccurate in session recommendation， a Session Recommendation method based on Graph Model and Attention Model （SR?GM?AM） was proposed. Firstly， the graph model used global graph and session graph to obtain neighborhood information and session information respectively， and used Graph Neural Network （GNN） to extract item graph features， which were passed through the global item representation layer and session item representation layer to obtain the global? level embedding and the session?level embedding， and the two levels of embedding were combined into graph embedding. Then， attention model used soft attention to fuse graph embedding and reverse position embedding， target attention activated the relevance of the target items， as well as attention model generated session embedding through linear transformation. Finally， SR?GM?AM outputted the recommended list of the N items for the next click through the prediction layer. Comparative experiments of SR?GM?AM and Lossless Edge?order preserving aggregation and Shortcut graph attention for Session?based Recommendation （LESSR） were conducted on two real public e?commerce datasets Yoochoose and Diginetica， and the results showed that SR?GM?AM had the highest P@20 of 72.41% and MRR@20 of 35.34%， verifying the effectiveness of it.

Key words: session recommendation, global graph, session graph, Graph Neural Network (GNN), neighborhood information

摘要：

为解决基于循环神经网络（RNN）会话推荐方法的兴趣偏好表示不全面、不准确问题，提出基于图模型和注意力模型的会话推荐（SR?GM?AM）方法。首先，图模型利用全局图和会话图分别获取邻域信息和会话信息，并且利用图神经网络（GNN）提取项目图特征，项目图特征经过全局项目表示层和会话项目表示层得到全局级嵌入和会话级嵌入，两种级别嵌入结合生成图嵌入；然后，注意力模型使用软注意力进行图嵌入和反向位置嵌入融合，目标注意力激活目标项目相关性，注意力模型通过线性转换生成会话嵌入；最后，SR?GM?AM经过预测层，输出下次点击的N项推荐列表。在两个真实的公共电子商务数据集Yoochoose和Diginetica上对比了SR?GM?AM方法与基于无损边缘保留聚合和快捷图注意力的推荐（LESSR）方法，结果显示，SR?GM?AM方法的P@20最高达到了72.41%，MRR@20最高达到了35.34%，验证了SR?GM?AM的有效性。

关键词: 会话推荐, 全局图, 会话图, 图神经网络, 邻域信息

CLC Number:

TP391.4

Weichao DANG, Zhiyu YAO, Shangwang BAI, Gaimei GAO, Chunxia LIU. Session recommendation method based on graph model and attention model[J]. Journal of Computer Applications, 2022, 42(11): 3610-3616.

党伟超, 姚志宇, 白尚旺, 高改梅, 刘春霞. 基于图模型和注意力模型的会话推荐方法[J]. 《计算机应用》唯一官方网站, 2022, 42(11): 3610-3616.

Figures/Tables 10

References 20

1	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）：63-69. 10.3969/j.issn.1000-1220.2019.09.010
	ZHAO H Y， ZHAO J B， CHEN Q K， et al. Session‑based recommendation system［J］. Journal of Chinese Computer Systems， 2019， 40（9）： 63-69. 10.3969/j.issn.1000-1220.2019.09.010
2	桂越.基于会话的推荐算法研究［D］.北京：北京邮电大学，2019：7-16.
	GUI Y. Research on session‑based recommendation algorithm［D］. Beijing： Beijing University of Posts and Telecommunications， 2019： 7-16.
3	WU S， TANG Y， ZHU Y， et al. Session‑based recommendation with graph neural networks ［C］// Proceedings of the 33rd AAAI Conference on Artificial Intelligence. Menlo Park， CA： AAAI Press， 2019： 346-353. 10.1609/aaai.v33i01.3301346
4	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. Menlo Park， CA： AAAI Press， 2019： 3940-3946. 10.24963/ijcai.2019/547
5	LI J， REN P， CHEN Z， et al. Neural attentive session‑based recommendation ［C］// Proceedings of the 2017 ACM on Conference on Information and Knowledge Management. New York： ACM， 2017： 1419-1428. 10.1145/3132847.3132926
6	LIU Q， ZENG Y， 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 & Data Mining. New York： ACM， 2018： 1831-1839. 10.1145/3219819.3219950
7	TAN Y K， XU X， LIU Y. Improved recurrent neural networks for session‑based recommendations ［C］// Proceedings of the 1st Workshop on Deep Learning for Recommender Systems. New York： ACM， 2016： 17-22. 10.1145/2988450.2988452
8	VASWANI A， SHAZEER N， PARMAR N， et al. Attention is all you need ［C］// Proceedings of the 31st International Conference on Neural Information Processing Systems. Red Hook， NY： Curran Associates Inc.， 2017： 6000-6010.
9	WANG H， LIU G， LIU A， et al. DMRAN： a hierarchical fine‑ grained attention‑based network for recommendation ［C］// Proceedings of the 28th International Joint Conference on Artificial Intelligence. Menlo Park： AAAI Press， 2019： 3698-3704. 10.24963/ijcai.2019/513
10	KANG W‑C， MCAULEY J. Self‑attentive sequential recommendation ［C］// Proceedings of the 2018 IEEE International Conference on Data Mining. Piscataway： IEEE， 2018： 197-206. 10.1109/icdm.2018.00035
11	SONG J， SHEN H， OU Z， et al. ISLF： interest shift and latent factors combination model for session‑based recommendation ［C］// Proceedings of the Twenty‑Eighth International Joint Conference on Artificial Intelligence. California： IJCAI， 2019： 5765‑5771. 10.24963/ijcai.2019/799
12	WANG S， HU L， WANG Y， et al. Modeling multi‑purpose sessions for next‑item recommendations via mixture‑channel purpose routing networks ［C］// Proceedings of the 28th International Joint Conference on Artificial Intelligence. California： IJCAI， 2019： 3771-3777. 10.24963/ijcai.2019/523
13	南宁，杨程屹，武志昊.基于多图神经网络的会话感知推荐模型［J］.计算机应用，2021，41（2）：330-336. 10.11772/j.issn.1001-9081.2020060805
	NAN N， YANG C Y， WU Z H. Multi‑graph neural network‑based session perception recommendation model［J］. Journal of Computer Applications， 2021， 41（2）： 330-336. 10.11772/j.issn.1001-9081.2020060805
14	孙鑫，刘学军，李斌，等.基于图神经网络和时间注意力的会话序列推荐［J］.计算机工程与设计，2020，41（10）：2913-2920. 10.16208/j.issn1000-7024.2020.10.036
	SUN X， LIU X J， LI B， et al. Graph neural networks with time attention mechanism for session‑based recommendations［J］. Computer Engineering and Design， 2020， 41（10）： 2913-2920. 10.16208/j.issn1000-7024.2020.10.036
15	SHEN Y， LI H， YI S， et al. Person re‑identification with deep similarity‑guided graph neural network ［C］// Proceedings of the 2018 European Conference on Computer Vision， LNIP 11219. Cham： Springer， 2018： 508-526.
16	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.
	HU Y 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.
17	QIU R， LI 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： ACM， 2019： 579-588. 10.1145/3357384.3358010
18	党伟超，姚志宇，白尚旺，等.基于图神经网络和注意力机制的会话推荐［J］. 计算机工程与设计， 2022， 43（10）： 2953-2958.
	DANG W C， YAO Z Y， BAI S W， et al. Session recommendation based on graph neural network and attention mechanism ［J］. Computer Engineering and Design， 2022，43（10）： 2953-2958.
19	CHEN T， C‑W WONG R. Handling information loss of graph neural networks for session‑based recommendation ［C］// Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York： ACM， 2020： 1172-1180. 10.1145/3394486.3403170
20	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. 10.11772/j.issn.1001-9081.2021010060
	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. 10.11772/j.issn.1001-9081.2021010060

方法	Yoochoose 1/4		Diginetica
方法	P@20	MRR@20	P@20	MRR@20
NARM^［5］	69.73	29.23	49.70	16.17
STAMP^［6］	70.44	30.00	45.64	14.32
SR‑GNN^［3］	71.36	31.89	50.73	17.59
LESSR^［19］	71.83	32.70	51.71	18.15
SRMGNN^［20］	70.62	31.28	50.16	17.04
SR‑GM‑AM	72.41	35.34	53.86	18.98

方法	Yoochoose 1/4		Diginetica
方法	P@20	MRR@20	P@20	MRR@20
NARM^［5］	69.73	29.23	49.70	16.17
STAMP^［6］	70.44	30.00	45.64	14.32
SR‑GNN^［3］	71.36	31.89	50.73	17.59
LESSR^［19］	71.83	32.70	51.71	18.15
SRMGNN^［20］	70.62	31.28	50.16	17.04
SR‑GM‑AM	72.41	35.34	53.86	18.98

方法	Yoochoose 1/4		Diginetica
方法	P@20	MRR@20	P@20	MRR@20
L	71.83	35.23	52.69	18.67
1‑hop	72.44	35.38	53.64	18.82
SR‑GM‑AM	72.41	35.34	53.86	18.98

方法	Yoochoose 1/4		Diginetica
方法	P@20	MRR@20	P@20	MRR@20
L	71.83	35.23	52.69	18.67
1‑hop	72.44	35.38	53.64	18.82
SR‑GM‑AM	72.41	35.34	53.86	18.98

方法	Yoochoose 1/4		Diginetica
方法	P@20	MRR@20	P@20	MRR@20
SR‑GM‑TA	72.06	35.27	53.24	18.77
SR‑GM‑SA	72.18	35.30	53.52.	18.86
SR‑GM‑AM	72.41	35.34	53.86	18.98

Session recommendation method based on graph model and attention model

基于图模型和注意力模型的会话推荐方法

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 20

Related Articles 15

Recommended Articles

Metrics

激活函数	Yoochoose 1/4		Diginetica
激活函数	P@20	MRR@20	P@20	MRR@20
Sigmoid	72.24	35.31	53.62	18.88
Tanh	72.29	35.31	53.67	18.91
ReLU	72.41	35.34	53.86	18.98

[1]	Tingjie TANG, Jiajin HUANG, Jin QIN. Session-based recommendation with graph auxiliary learning [J]. Journal of Computer Applications, 2024, 44(9): 2711-2718.
[2]	Xinrui LIN, Xiaofei WANG, Yan ZHU. Academic anomaly citation group detection based on local extended community detection [J]. Journal of Computer Applications, 2024, 44(6): 1855-1861.
[3]	Jie GUO, Jiayu LIN, Zuhong LIANG, Xiaobo LUO, Haitao SUN. Recommendation method based on knowledge‑awareness and cross-level contrastive learning [J]. Journal of Computer Applications, 2024, 44(4): 1121-1127.
[4]	Dapeng XU, Xinmin HOU. Feature selection method for graph neural network based on network architecture design [J]. Journal of Computer Applications, 2024, 44(3): 663-670.
[5]	Beijing ZHOU, Hairong WANG, Yimeng WANG, Lisi ZHANG, He MA. Recommendation method using knowledge graph embedding propagation [J]. Journal of Computer Applications, 2024, 44(10): 3252-3259.
[6]	Runchao PAN, Qishan YU, Hongfei XIONG, Zhihui LIU. Collaborative recommendation algorithm based on deep graph neural network [J]. Journal of Computer Applications, 2023, 43(9): 2741-2746.
[7]	Haodong ZHENG, Hua MA, Yingchao XIE, Wensheng TANG. Knowledge tracing model based on graph neural network blending with forgetting factors and memory gate [J]. Journal of Computer Applications, 2023, 43(9): 2747-2752.
[8]	Hongjun HENG, Dingcheng YANG. Knowledge enhanced aspect word interactive graph neural network [J]. Journal of Computer Applications, 2023, 43(8): 2412-2419.
[9]	Kun ZHANG, Fengyu YANG, Fa ZHONG, Guangdong ZENG, Shijian ZHOU. Source code vulnerability detection based on hybrid code representation [J]. Journal of Computer Applications, 2023, 43(8): 2517-2526.
[10]	Zifang XIA, Yaxin YU, Ziteng WANG, Jiaqi QIAO. Explainable recommendation mechanism by fusion collaborative knowledge graph and counterfactual inference [J]. Journal of Computer Applications, 2023, 43(7): 2001-2009.
[11]	Kejun JIN, Hongtao YU, Yiteng WU, Shaomei LI, Jianpeng ZHANG, Honghao ZHENG. Improved defense method for graph convolutional network based on singular value decomposition [J]. Journal of Computer Applications, 2023, 43(5): 1511-1517.
[12]	Hao SUN, Jian CAO, Haisheng LI, Dianhui MAO. Session-based recommendation model based on enhanced capsule network [J]. Journal of Computer Applications, 2023, 43(4): 1043-1049.
[13]	Lubao LI, Tian CHEN, Fuji REN, Beibei LUO. Bimodal emotion recognition method based on graph neural network and attention [J]. Journal of Computer Applications, 2023, 43(3): 700-705.
[14]	Yu WANG, Yubo YUAN, Yi GUO, Jiajie ZHANG. Sentiment boosting model for emotion recognition in conversation text [J]. Journal of Computer Applications, 2023, 43(3): 706-712.
[15]	Xuanyu SUN, Yancui SHI. Session-based recommendation model by graph neural network fused with item influence [J]. Journal of Computer Applications, 2023, 43(12): 3689-3696.