Session-based recommendation model based on time-aware and space-enhanced dual channel graph neural network

doi:10.11772/j.issn.1001-9081.2025010097

Journal of Computer Applications ›› 2026, Vol. 46 ›› Issue (1): 104-112.DOI: 10.11772/j.issn.1001-9081.2025010097

• Data science and technology • Previous Articles Next Articles

Session-based recommendation model based on time-aware and space-enhanced dual channel graph neural network

Xingyao YANG¹(), Zheng QI¹, Jiong YU¹, Zulian ZHANG², Shuai MA¹, Hongtao SHEN¹

^1.School of Software，Xinjiang University，Urumqi Xinjiang 830091，China
^2.Xinjiang Xinnong Network Information Center，Meteorological Bureau of Xinjiang Uygur Autonomous Region，Urumqi Xinjiang 830002，China

Received:2025-01-23 Revised:2025-04-01 Accepted:2025-04-02 Online:2026-01-10 Published:2026-01-10
Contact: Xingyao YANG
About author:QI Zheng， born in 1999， M. S. candidate. His research interests include recommender system.
YU Jiong， born in 1964， Ph. D.， professor. His research interests include grid computing， parallel computing.
ZHANG Zulian， born in 1984， M. S.， senior engineer. Her research interests include numerical prediction， information retrieval.
MA Shuai， born in 1998， M. S. candidate. His research interests include recommender system.
SHEN Hongtao， born in 2001， M. S. candidate. His research interests include recommender system.
Supported by:
Xinjiang Uygur Autonomous Region Natural Science Foundation(2023D01C17);National Natural Science Foundation of China(62262064);Xinjiang Uygur Autonomous Region Science and Technology Program-Tianshan Innovative Team Program(2023D4012);Xinjiang Meteorological Bureau Key Project(ZD202503)

时间感知和空间增强的双通道图神经网络会话推荐模型

杨兴耀¹(), 齐正¹, 于炯¹, 张祖莲², 马帅¹, 沈洪涛¹

^1.新疆大学软件学院，乌鲁木齐 830091
^2.新疆维吾尔自治区气象局新疆兴农网信息中心，乌鲁木齐 830002

通讯作者: 杨兴耀
作者简介:齐正（1999—），男，山西大同人，硕士研究生，主要研究方向：推荐系统
于炯（1964—），男，新疆乌鲁木齐人，教授，博士， CCF会员，主要研究方向：网格计算、并行计算
张祖莲（1984—），女，湖北襄阳人，高级工程师，硕士，主要研究方向：数值预报、信息检索
马帅（1998—），男，山东菏泽人，硕士研究生，主要研究方向：推荐系统
沈洪涛（2001—），男，安徽淮南人，硕士研究生，主要研究方向：推荐系统。
基金资助:
新疆维吾尔自治区自然科学基金面上项目(2023D01C17);新疆维吾尔自治区自然科学基金面上项目(2023D01A123);新疆维吾尔自治区自然科学基金面上项目(20220412003);国家自然科学基金资助项目(62262064);新疆维吾尔自治区科技计划项目—天山创新团队计划项目(2023D4012);新疆气象局重点项目(ZD202503)

Abstract

Abstract:

To address the problem that session-based recommendation models ignore temporal information and spatial relationships among items， leading to an inability to capture complex transition patterns among items accurately， a session-based recommendation model based on time-aware and space-enhanced dual channel Graph Neural Network （GNN） was proposed. Firstly， for the temporal channel， adaptive temporal weights were used to process the items， thereby constructing a time-aware session graph， and the users’ interest-shifting patterns were captured through a time-aware GNN. Secondly， for the spatial channel， spatial relationships among items were embedded into a Graph ATtention network （GAT）， so as to aggregate the information from the perspective of spatial graph structure. Finally， a contrastive learning strategy was introduced to enhance recommendation performance. The results of comparative experiments conducted on three publicly available datasets， Diginetica， Tmall， and Nowplaying — where the proposed model was compared with baseline models including Atten-Mixer （multi-level Attention Mixture network） and GCE-GNN （Global Context Enhanced GNN） — show that the proposed model achieves superior precision （P） and Mean Reciprocal Rank （MRR）. Compared to the suboptimal results， the proposed model has the P@10 improved by 2.09%， 24.97%， and 10.45%， respectively， and the MRR@10 improved by 2.52%， 11.60%， and 4.43%， respectively.

Key words: recommendation system, graph neural network, session-based recommendation, contrastive learning, Graph ATtention network (GAT)

摘要：

为了解决会话推荐模型忽略项目之间的时间信息和空间关系，导致无法准确捕获项目之间复杂转换模式的问题，提出一种时间感知和空间增强的双通道图神经网络（GNN）的会话推荐模型。首先，对于时间通道，采用自适应时间权重对项目进行处理，以构建时间感知的会话图，并通过时间感知的GNN捕获用户的兴趣转移模式；其次，对于空间通道，将项目之间的空间关系嵌入一个图注意力网络（GAT）中，以从空间图结构的角度对信息进行聚合；最后，引入一种对比学习策略增强推荐效果。在Diginetica、Tmall和Nowplaying 3个公开数据集上，将所提模型与Atten-Mixer（multi-level Attention Mixture network）和GCE-GNN（Global Context Enhanced GNN）等基线模型进行对比实验，实验结果表明，所提模型的精确率（P）和平均倒数排名（MRR）取得了更优的效果。相较于次优结果，所提模型的P@10分别提高了2.09%、24.97%和10.45%， MRR@10分别提高2.52%、11.60%和4.43%。

CLC Number:

TP391.3

Xingyao YANG, Zheng QI, Jiong YU, Zulian ZHANG, Shuai MA, Hongtao SHEN. Session-based recommendation model based on time-aware and space-enhanced dual channel graph neural network[J]. Journal of Computer Applications, 2026, 46(1): 104-112.

杨兴耀, 齐正, 于炯, 张祖莲, 马帅, 沈洪涛. 时间感知和空间增强的双通道图神经网络会话推荐模型[J]. 《计算机应用》唯一官方网站, 2026, 46(1): 104-112.

Figures/Tables 12

References 39

[1]	AN G， SUN J， YANG Y， et al. Enhancing collaborative information with contrastive learning for session-based recommendation ［J］. Information Processing and Management， 2024， 61（4）： No.103738.
[2]	FU J， GAO R， YU Y， et al. Contrastive graph learning long and short-term interests for POI recommendation ［J］. Expert Systems with Applications， 2024， 238（Pt B）： No.121931.
[3]	CHOI M， KIM H， CHO H， et al. Multi-intent-aware session-based recommendation ［C］// Proceedings of the 47th International ACM SIGIR Conference on Research and Development in Information Retrieval. New York： ACM， 2024： 2532-2536.
[4]	ZHU X， ZHANG Y， WANG J， et al. Graph-enhanced and collaborative attention networks for session-based recommendation ［J］. Knowledge-Based Systems， 2024， 289： No.111509.
[5]	MAO T， HAO T， FU J， et al. Hierarchical graph fusion network and a new argumentative dataset for multiparty dialogue discourse parsing ［J］. Information Processing and Management， 2024， 61（2）： No.103613.
[6]	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. New York： ACM， 2019： 793-803.
[7]	MAO T， YOSHIE O， FU J， et al. Seeing both sides： context-aware heterogeneous graph matching networks for extracting-related arguments ［J］. Neural Computing and Applications， 2024， 36（9）： 4741-4762.
[8]	YANG Y， WU L， WANG Z， et al. Graph bottlenecked social recommendation ［C］// Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. New York： ACM， 2024： 3853-3862.
[9]	LU X， WU J. Combining association-rule-guided sequence augmentation with listwise contrastive learning for session-based recommendation ［J］. Information Processing and Management， 2025， 62（3）： No.103999.
[10]	ZHOU W， HAQ A U， QIU L， et al. Multi-view social recommendation via matrix factorization with sub-linear convergence rate ［J］. Expert Systems with Applications， 2024， 237（Pt C）： No.121687.
[11]	ZHOU X， SUN A， LIU Y， et al. SelfCF： a simple framework for self-supervised collaborative filtering ［J］. ACM Transactions on Recommender Systems， 2023， 1（2）： No.9.
[12]	VERMA M， PATNAIK P K. An automatic college library book recommendation system using optimized hidden Markov based weighted fuzzy ranking model ［J］. Engineering Applications of Artificial Intelligence， 2024， 130： No.107664.
[13]	WU Y， GOU J. Leveraging neighborhood session information with dual attentive neural network for session-based recommendation ［J］. Neurocomputing， 2021， 439： 234-242.
[14]	YANG F， PENG D. MVC-HGAT： multi-view contrastive hypergraph attention network for session-based recommendation ［J］. Applied Intelligence， 2025， 55（1）： No.27.
[15]	GOPI P S S， KARTHIKEYAN M. Red fox optimization with ensemble recurrent neural network for crop recommendation and yield prediction model ［J］. Multimedia Tools and Applications， 2024， 83（5）： 13159-13179.
[16]	HIDASI B， KARATZOGLOU A， BALTRUNAS L， et al. Session-based recommendations with recurrent neural networks ［EB/OL］. ［2025-01-05］. .
[17]	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 and Data Mining. New York： ACM， 2018： 1831-1839.
[18]	ZHAO P， LUO A， LIU Y， et al. Where to go next： a spatio-temporal gated network for next POI recommendation ［J］. IEEE Transactions on Knowledge and Data Engineering， 2022， 34（5）： 2512-2524.
[19]	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. New York： ACM， 2018： 565-573.
[20]	杨兴耀，陈羽，于炯，等.结合自我特征和对比学习的推荐模型［J］.计算机应用， 2024， 44（9）： 2704-2710.
	YANG X Y， CHEN Y， YU J， et al. Recommendation model combining self-features and contrastive learning ［J］. Journal of Computer Applications， 2024， 44（9）： 2704-2710.
[21]	XIA X， YIN H， YU J， et al. Self-supervised graph co-training for session-based recommendation ［C］// Proceedings of the 30th ACM International Conference on Information and Knowledge Management. New York： ACM， 2021： 2180-2190.
[22]	XIE X， SUN F， LIU Z， et al. Contrastive learning for sequential recommendation ［C］// Proceedings of the IEEE 38th International Conference on Data Engineering. Piscataway： IEEE， 2022： 1259-1273.
[23]	PEINTNER A， MOHAMMADI A R， ZANGERLE E. SPARE： shortest path global item relations for efficient session-based recommendation ［C］// Proceedings of the 17th ACM Conference on Recommender Systems. New York： ACM， 2023： 58-69.
[24]	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. Palo Alto： AAAI Press， 2019： 346-353.
[25]	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. New York： ACM， 2020： 1921-1924.
[26]	GUO J， YANG Y， SONG X， et al. Learning multi-granularity consecutive user intent unit for session-based recommendation ［C］// Proceedings of the 15th ACM International Conference on Web Search and Data Mining. New York： ACM， 2022： 343-352.
[27]	邬锦琛，杨兴耀，于炯，等.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 J C， YANG X Y， YU J， et al. Sequence recommendation with dual channel heterogeneous graph neural network ［J］. Journal of Frontiers of Computer Science and Technology， 2023， 17（6）： 1473-1486.
[28]	ZHANG Z， YANG B， XU H， et al. Multi-level category-aware graph neural network for session-based recommendation ［J］. Expert Systems with Applications， 2024， 242： No.122773.
[29]	LI A， ZHU J， LI Z， et al. Transition information enhanced disentangled graph neural networks for session-based recommendation ［J］. Expert Systems with Applications， 2022， 210： No.118336.
[30]	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： Curran Associates Inc.， 2017： 6000-6010.
[31]	HASSANI K， KHASAHMADI A H. Contrastive multi-view representation learning on graphs ［C］// Proceedings of the 37th International Conference on Machine Learning. New York： JMLR.org， 2020： 4116-4126.
[32]	ZANGERLE E， PICHL M， GASSLER W， et al. #nowplaying Music dataset： extracting listening behavior from Twitter ［C］// Proceedings of the 1st International Workshop on Internet-Scale Multimedia Management. New York： ACM， 2014： 21-26.
[33]	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： ACM， 2010： 811-820.
[34]	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.
[35]	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.
[36]	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. New York： ACM， 2020： 169-178.
[37]	XIA X， YIN H， YU J， et al. Self-supervised hypergraph convolutional networks for session-based recommendation ［C］// Proceedings of the 35th AAAI Conference on Artificial Intelligence. Palo Alto： AAAI Press， 2021： 4503-4511.
[38]	LI A， CHENG Z， LIU F， et al. Disentangled graph neural networks for session-based recommendation ［J］. IEEE Transactions on Knowledge and Data Engineering， 2023， 35（8）： 7870-7882.
[39]	ZHANG P， GUO J， LI C， et al. Efficiently leveraging multi-level user intent for session-based recommendation via atten-mixer network ［C］// Proceedings of the 16th ACM International Conference on Web Search and Data Mining. New York： ACM， 2023： 168-176.

数据集	点击次数	样本数		项目数	平均会话长度
数据集	点击次数	训练集	测试集	项目数	平均会话长度
Diginetica	982 961	719 470	60 858	43 097	5.12
Tmall	818 479	351 268	25 898	40 728	6.69
Nowplaying	1 367 963	825 304	89 824	60 417	7.42

数据集	点击次数	样本数		项目数	平均会话长度
数据集	点击次数	训练集	测试集	项目数	平均会话长度
Diginetica	982 961	719 470	60 858	43 097	5.12
Tmall	818 479	351 268	25 898	40 728	6.69
Nowplaying	1 367 963	825 304	89 824	60 417	7.42

模型	P@10	MRR@10	P@20	MRR@20
FPMC	15.43	6.20	26.53	6.95
GRU4Rec	17.93	7.33	29.45	8.33
NARM	35.44	15.13	49.70	16.17
STAMP	33.98	14.26	45.64	14.32
CSRM	36.59	15.41	50.55	16.38
SR-GNN	36.86	15.52	50.73	17.59
GCE-GNN	41.55	18.29	54.64	19.20
S²-DHCN	41.16	18.15	53.18	18.43
Disen-GNN	40.90	18.17	53.70	19.05
Atten-Mixer	41.47	17.94	55.12	18.90
TSG-SR	42.42	18.75	56.02	20.10

模型	P@10	MRR@10	P@20	MRR@20
FPMC	15.43	6.20	26.53	6.95
GRU4Rec	17.93	7.33	29.45	8.33
NARM	35.44	15.13	49.70	16.17
STAMP	33.98	14.26	45.64	14.32
CSRM	36.59	15.41	50.55	16.38
SR-GNN	36.86	15.52	50.73	17.59
GCE-GNN	41.55	18.29	54.64	19.20
S²-DHCN	41.16	18.15	53.18	18.43
Disen-GNN	40.90	18.17	53.70	19.05
Atten-Mixer	41.47	17.94	55.12	18.90
TSG-SR	42.42	18.75	56.02	20.10

模型	P@10	MRR@10	P@20	MRR@20
FPMC	13.10	7.12	16.06	7.32
GRU4Rec	9.47	5.78	10.93	5.89
NARM	19.17	10.42	23.30	10.70
STAMP	22.63	13.12	26.47	13.36
CSRM	25.54	13.62	29.46	13.96
SR-GNN	23.41	13.45	27.57	13.72
GCE-GNN	29.19	15.55	34.35	15.91
S²-DHCN	26.22	14.60	31.41	15.05
Disen-GNN	26.34	15.19	31.58	15.46
Atten-Mixer	29.27	16.55	34.98	16.72
TSG-SR	36.58	18.47	42.74	18.73

Session-based recommendation model based on time-aware and space-enhanced dual channel graph neural network

时间感知和空间增强的双通道图神经网络会话推荐模型

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 12

References 39

Related Articles 15

Recommended Articles

Metrics

模型	P@10	MRR@10	P@20	MRR@20
FPMC	5.28	2.68	7.36	2.82
GRU4Rec	6.74	4.40	7.92	4.48
NARM	13.60	6.60	18.59	6.93
STAMP	13.22	6.57	17.66	6.88
CSRM	13.20	6.08	18.14	6.42
SR-GNN	14.17	7.15	18.87	7.74
GCE-GNN	16.94	8.03	22.37	8.40
S²-DHCN	17.35	7.87	23.50	8.81
Disen-GNN	15.93	8.04	22.22	8.22
Atten-Mixer	16.57	8.12	22.00	8.49
TSG-SR	18.71	8.48	24.81	8.86

[1]	Fan HE, Li LI, Zhongxu YUAN, Xiu YANG, Dongxuan HAN. Knowledge tracking model based on concept association memory network with graph attention [J]. Journal of Computer Applications, 2026, 46(1): 43-51.
[2]	Ziyang CHENG, Ruizhang HUANG, Jingjing XUE. Deep evolutionary topic clustering model [J]. Journal of Computer Applications, 2026, 46(1): 85-94.
[3]	Wen LI, Kairong LI, Kai YANG. Subgraph-aware contrastive learning with data augmentation [J]. Journal of Computer Applications, 2026, 46(1): 1-9.
[4]	Yonghao LIANG, Jinlong LI. Novel message passing network for neural Boolean satisfiability problem solver [J]. Journal of Computer Applications, 2025, 45(9): 2934-2940.
[5]	Yanqun LU, Yiyi ZHAO. Customer churn prediction model integrating hierarchical graph neural network and specific feature learning [J]. Journal of Computer Applications, 2025, 45(9): 3057-3066.
[6]	Zhixiong XU, Bo LI, Xiaoyong BIAN, Qiren HU. Adversarial sample embedded attention U-Net for 3D medical image segmentation [J]. Journal of Computer Applications, 2025, 45(9): 3011-3016.
[7]	Chao LIU, Yanhua YU. Knowledge-aware recommendation model combining denoising strategy and multi-view contrastive learning [J]. Journal of Computer Applications, 2025, 45(9): 2827-2837.
[8]	Zhiyuan WANG, Tao PENG, Jie YANG. Integrating internal and external data for out-of-distribution detection training and testing [J]. Journal of Computer Applications, 2025, 45(8): 2497-2506.
[9]	Shuo ZHANG, Guokai SUN, Yuan ZHUANG, Xiaoyu FENG, Jingzhi WANG. Dynamic detection method of eclipse attacks for blockchain node analysis [J]. Journal of Computer Applications, 2025, 45(8): 2428-2436.
[10]	Yi WANG, Yinglong MA. Multi-task social item recommendation method based on dynamic adaptive generation of item graph [J]. Journal of Computer Applications, 2025, 45(8): 2592-2599.
[11]	Kaile YU, Jiajun LIAO, Jiali MAO, Xiaopeng HUANG. Multi-objective optimization of steel logistics vehicle-cargo matching under multiple constraints [J]. Journal of Computer Applications, 2025, 45(8): 2477-2483.
[12]	Quan JIANG, Wenqing HUANG, Zhiyong GOU. Lagrangian particle flow simulation by equivariant graph neural network [J]. Journal of Computer Applications, 2025, 45(8): 2666-2671.
[13]	Yinchuan TU, Yong GUO, Heng MAO, Yi REN, Jianfeng ZHANG, Bao LI. Evaluation of training efficiency and training performance of graph neural network models based on distributed environment [J]. Journal of Computer Applications, 2025, 45(8): 2409-2420.
[14]	Chen LIANG, Yisen WANG, Qiang WEI, Jiang DU. Source code vulnerability detection method based on Transformer-GCN [J]. Journal of Computer Applications, 2025, 45(7): 2296-2303.
[15]	Zimo ZHANG, Xuezhuan ZHAO. Multi-scale sparse graph guided vision graph neural networks [J]. Journal of Computer Applications, 2025, 45(7): 2188-2194.