基于会话的结合全局潜在信息的图神经网络推荐模型

doi:10.13229/j.cnki.jdxbgxb.20211335

Abstract

Abstract:

Aiming at the problem of insufficient acquisition and use of the global relationship between items in various current session based recommendation models， a session based graph neural network recommendation model combined with global potential information is proposed. The model constructs session graph and global graph according to all session sequences， introduces the spacing information between nodes in the sequence and the contribution of adjacent nodes of sequence nodes to each other， obtains the final session representation through model training， and predicts the next interaction behavior. The experimental results show that fully mining the global potential information in the recommendation algorithm combined with graph neural network can effectively improve the accuracy of the recommendation algorithm. This improvement has certain guiding significance for improving the performance of session based graph neural network model.

Key words: computer software, recommendation system, session-based recommendation, graph neural network, global information

CLC Number:

TP301.6

Li-yan DONG,Wei-ye LIANG,Yue-qun WANG,Yong-li LI. Global potential information combined graph neural networks for session-based recommendation[J].Journal of Jilin University(Engineering and Technology Edition), 2023, 53(10): 2964-2972.

Figures/Tables 11

Fig.1

Fig.2

Fig.3

Fig.4

Table 1

Table 2

Fig.5

Fig.6

Table 3

Fig.7

Fig.8

References 25

1	Wang S, Pasi G, Hu L, et al. The era of intelligent recommendation: editorial on intelligent recommendation with advanced AI and learning[J]. IEEE Intelligent Systems, 2020, 35(5): 3-6.
2	Sri Hari Nallamala, Nallamala Sri Hari, Bajjuri Usha Rani, et al. A brief analysis of collaborative and content based filtering algorithms used in recommender systems[J]. IOP Conference Series: Materials Science and Engineering, 2020, 981(2): No.022008.
3	Mahesh Mali, Mishra Dhirendra S, Vijayalaxmi M. Multifaceted recommender systems methods: a review[J]. Journal of Statistics and Management Systems, 2020, 23(2): 349-361.
4	Dang T K, Nguyen Q P, Nguyen V S. A study of deep learning-based approaches for session-based recommendation systems[J]. SN Computer Science, 2020, 1(4): 1-13.
5	Wang S, Cao L, Wang Y, et al. A survey on session-based recommender systems[J]. ACM Computing Surveys(CSUR), 2021, 54(7): 1-38.
6	Abdi Mohamed Hussein, Okeyo George Onyango, Mwangi Ronald Waweru. Matrix factorization techniques for context-aware collaborative filtering recommender systems: a survey[J]. Computer and Information Science, 2018, 11(2): 1-10.
7	Liu S, Wang L. A self-adaptive point-of-interest recommendation algorithm based on a multi-order Markov model[J]. Future Generation Computer Systems, 2018, 89(4): 506-514.
8	Rendle S, Freudenthaler C, Schmidt-Thieme L. Factorizing personalized markov chains for next-basket recommendation[C]∥Proceedings of the 19th International Conference on World Wide Web, New York,USA, 2010: 811-820.
9	Hidasi B, Karatzoglou A, Baltrunas L, et al. Sessionbased recommendations with recurrent neural networks[EB/OL]. [2021-11-12]. .
10	Li J, Ren P, Chen Z, et al. Neural attentive session-based recommendation[C]∥Proceedings of the ACM on Conference on Information and Knowledge Management, New York,USA, 2017: 1419-1428.
11	Vaswani Ashish, Shazeer Noam, Parmar Niki, et al. Attention is all you need[C]∥Proceedings of 31st Conference on Neural Information Processing Systems, Long Beach, USA, 2017: 5998-6008.
12	Liu Q, Zeng Y, 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, London, United Kingdom, 2018: 1831-1839.
13	Jannach D, Ludewig M. When recurrent neural networks meet the neighborhood for session-based recommendation[C]∥Proceedings of the 11th ACM Conference on Recommender Systems, Como, Italy, 2017: 306-310.
14	Tuan T X, Phuong T M. 3D convolutional networks for session-based recommendation with content features[C]∥Proceedings of the 11th ACM Conference on Recommender Systems, Como, Italy, 2017: 138-146.
15	Wu C, Yan M. Session-aware information embedding for e-commerce product recommendation[C]∥Proceedings of the 2017 ACM on conference on information and knowledge management, Singapore, 2017: 2379-2382.
16	Tang J, Wang K. Personalized top-n sequential recommendation via convolutional sequence embedding[C]∥Proceedings of the 11th ACM International Conference on Web Search and Data Mining, Berkeley, USA, 2018: 565-573.
17	Yuan F, Karatzoglou A, Arapakis I, et al. A simple convolutional generative network for next item recommendation[C]∥Proceedings of the Twelfth ACM International Conference on Web Search and Data Mining, Melbourne, Australia, 2019: 582-590.
18	Xu Keyulu, Hu Wei-hua, Jure Leskovec, et al. How powerful are graph neural networks?[EB/OL]. [2021-11-12]. .
19	Wu S, Tang Y, Zhu Y, et al. Session-based recommendation with graph neural networks[C]∥Proceedings of the AAAI Conference on Artificial Intelligence, Palo Alto, USA, 2019: 346-353.
20	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, San Francisco, USA, 2019: 3940-3946.
21	Yu F, Zhu Y, 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, Xi'an, China, 2020: 1921-1924.
22	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, Atlanta,USA, 2019: 579-588.
23	Wang Z, 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, Xi'an, China, 2020: 169-178.
24	Sarwar B, Karypis G, Konstan J, et al. Item-based collaborative filtering recommendation algorithms[C]∥Proceedings of the 2001 International Conference on World Wide Web, Hong Kong, China, 2001:285-295.
25	Wu Z, Pan S, Chen F, et al. A comprehensive survey on graph neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(1): 4-24.

Related Articles 15

[1]	Da-juan FAN,Zhi-qiu HUANG,Yan CAO. Adaptive access control method for SaaS privacy protection [J]. Journal of Jilin University(Engineering and Technology Edition), 2023, 53(10): 2897-2908.
[2]	Man YUAN,Yun-long JIANG,Chao HU. A new method for link validity assessment based on linked data [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(5): 1792-1797.
[3]	Shuai LYU,Jing LIU. Stochastic local search heuristic method based on deep reinforcement learning [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(4): 1420-1426.
[4]	Rong QIAN,Ru ZHANG,Ke-jun ZHANG,Xin JIN,Shi-liang GE,Sheng JIANG. Capsule graph neural network based on global and local features fusion [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(3): 1048-1054.
[5]	Xiao-hui WEI,Bing-yi SUN,Jia-xu CUI. Recommending activity to users via deep graph neural network [J]. Journal of Jilin University(Engineering and Technology Edition), 2021, 51(1): 278-284.
[6]	Man YUAN,Chao HU,Ting-ting QIU. A new method for data integrity assessment based on Linked data [J]. Journal of Jilin University(Engineering and Technology Edition), 2020, 50(5): 1826-1831.
[7]	Lei LIU,Jie WENG,De-gui GUO. Static input determination method in partial evaluation for compiler test [J]. Journal of Jilin University(Engineering and Technology Edition), 2020, 50(1): 262-267.
[8]	MA Jian, FAN Jian-ping, LIU Feng, LI Hong-hui. The evolution model of objective-oriented software system [J]. 吉林大学学报(工学版), 2018, 48(2): 545-550.
[9]	LUO Yang-xia, GUO Ye. Software recognition based on features of data dependency [J]. 吉林大学学报(工学版), 2017, 47(6): 1894-1902.
[10]	YING Huan, WANG Dong-hui, WU Cheng-gang, WANG Zhe, TANG Bo-wen, LI Jian-jun. Efficient deterministic replay technique on commodity system environment [J]. 吉林大学学报(工学版), 2017, 47(1): 208-217.
[11]	LI Yong, HUANG Zhi-qiu, WANG Yong, FANG Bing-wu. New approach of cross-project defect prediction based on multi-source data [J]. 吉林大学学报(工学版), 2016, 46(6): 2034-2041.
[12]	WANG Nian-bin, ZHU Guan-wen, ZHOU Lian-ke, WANG Hong-wei. Novel dataspace index for efficient processing of path query [J]. 吉林大学学报(工学版), 2016, 46(3): 911-916.
[13]	CHEN Peng-fei, TIAN Di, YANG Guang. Design and implementation of LIBS software based on MVC architecture [J]. 吉林大学学报(工学版), 2016, 46(1): 242-245.
[14]	TE Ri-gen, JIANG Sheng, LI Xiong-fei, LI Jun. Document compression scheme based on integer data [J]. 吉林大学学报(工学版), 2016, 46(1): 228-234.
[15]	FENG Xiao-ning, WANG Zhuo, ZHANG Xu. Formal method for routing protocol of WSN based on L-π calculus [J]. 吉林大学学报(工学版), 2015, 45(5): 1565-1571.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

Comments

Recommended 0

No Suggested Reading articles found!

数据集	Diginetica	Tmall
点击数量	982961	818479
训练集会话数量	719470	351268
测试集会话数量	60858	25898
物品数量	43097	40728
平均长度	5.12	6.69

模型	Diginetica				Tmall
模型	P@10	MRR@10	P@20	MRR@20	P@10	MRR@10	P@20	MRR@20
POP	0.76	0.26	1.18	0.28	1.67	0.88	2.00	0.90
Item-KNN	25.07	10.77	35.75	11.57	6.65	3.11	9.15	3.31
FPMC	15.43	6.20	22.14	6.66	13.10	7.12	16.06	7.32
GRU4Rec	17.93	7.73	30.79	8.22	9.47	5.78	10.93	5.89
NARM	35.44	15.13	48.32	16.00	19.17	10.42	23.30	10.70
STAMP	33.98	14.26	46.62	15.13	22.63	13.12	26.47	13.36
SR-GNN	38.78	16.98	51.61	17.93	23.43	13.15	28.24	13.41
GC-SAN	31.25	12.97	42.85	13.62	10.43	5.96	12.28	6.10
TA-GNN	38.66	17.01	50.98	17.75	34.80	17.17	31.68	13.96
GCE-GNN	41.07	18.02	54.22	19.02	27.44	14.79	32.48	15.09
GPICGNN	41.01	18.07	54.35	19.05	27.51	14.77	32.63	15.09

模型	Diginetica		Tmall
模型	P@20	MRR@20	P@20	MRR@20
模型1	54.31	19.04	32.52	15.16
模型2	54.31	19.00	32.30	15.04
GPICGNN	54.35	19.05	32.63	15.09

Global potential information combined graph neural networks for session-based recommendation

RICH HTML

PDF (PC)