Cross-view contrastive learning and multi-channel hypergraph convolution for session-based recommendation

REN Yubin; WANG Ruiqin; SUI Xinyi; FANG Chi

doi:10.11959/j.issn.1000-0801.2025233

您当前的位置：

首页 >

文章列表页 >

Cross-view contrastive learning and multi-channel hypergraph convolution for session-based recommendation

Research and Development | 更新时间：2025-11-06

- Cross-view contrastive learning and multi-channel hypergraph convolution for session-based recommendation
- Telecommunications Science Vol. 41, Issue 10, Pages: 172-183(2025)
- 作者机构：
  
  湖州师范学院信息工程学院，浙江湖州 313000
- 作者简介：
- 基金信息：
- DOI：10.11959/j.issn.1000-0801.2025233
  CLC： TP393;TN99
- Received：08 March 2025，
  
  Revised：2025-05-30，
  
  Accepted：03 June 2025，
  
  Published：20 October 2025
- 稿件说明：
移动端阅览
任宇彬,王瑞琴,隋欣怡等.基于多通道超图卷积与跨视图对比学习的会话推荐[J].电信科学,2025,41(10):172-183.

REN Yubin,WANG Ruiqin,SUI Xinyi,et al.Cross-view contrastive learning and multi-channel hypergraph convolution for session-based recommendation[J].Telecommunications Science,2025,41(10):172-183.
任宇彬,王瑞琴,隋欣怡等.基于多通道超图卷积与跨视图对比学习的会话推荐[J].电信科学,2025,41(10):172-183. DOI： 10.11959/j.issn.1000-0801.2025233.

REN Yubin,WANG Ruiqin,SUI Xinyi,et al.Cross-view contrastive learning and multi-channel hypergraph convolution for session-based recommendation[J].Telecommunications Science,2025,41(10):172-183. DOI： 10.11959/j.issn.1000-0801.2025233.

摘要

会话推荐通过分析匿名用户的历史交互数据来预测下一个交互项。由于用户行为数据的稀疏性，从单个维度对会话表示进行建模可能无法全面地捕获用户的真实意图。此外，现有的会话推荐模型主要考虑会话项的顺序信息而忽略了不同会话项之间的高阶关系。因此，提出对比学习和多通道超图卷积（cross-view contrastive learning and multi-channel hypergraph convolution，CLMHC）模型，该模型构建了超图和全局超图两个互补的视图，通过通道混合注意力机制自适应地融合从两个超图通道中捕获的用户意图，并对不同视图空间的用户意图进行对比学习。在3个数据集上的实验研究表明，所提模型较现有模型在推荐准确性方面具有显著的提升，进一步的消融实验表明两个维度的视图表示均起到了积极作用。

Abstract

Session-based recommendation predicts the next interaction item by analyzing anonymous users’ historical interaction data. Because of the sparsity of user behavior data

modeling session representations from a single perspective may fail to fully capture users’ true intentions. Moreover

existing session-based recommendation models primarily focus on the sequential order of session items while overlooking the higher-order relationships between them. To address this

the cross-view contrastive learning and multi-channel hypergraph convolution （CLMHC）model that constructs two complementary views was proposed: a hypergraph and a global hypergraph. By leveraging a channel-mixing attention mechanism

the model adaptively integrated the user intentions captured from both hypergraph channels while employing contrastive learning to refine user representations across different views. Extensive experiments on three datasets demonstrate that our model significantly outperforms existing approaches in recommendation accuracy. The ablation studies further confirm that both views contribute positively to performance improvement.

关键词

Keywords

references

HIDASI B , KARATZOGLOU A , BALTRUNAS L , et al . Session-based recommendations with recurrentneural networks [EB ] . arXiv preprint , 2015 , arXiv: 1511. 06939

YUAN F J , ALEXANDROS K , IOANNIS A , 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 (WSDM) . New York : ACM Press , 2019 : 582 - 590 .

SCARSELLI F , GORI M , TSOI A H , et al . The graph neural network model [J ] . IEEE Transactionson Neural Networks , 2009 , 20 ( 1 ): 61 - 80 .

YUAN J H , SONG Z H , SUN M Y , et al . Dual sparse attention network for session-based recommendation [C ] // Proceedings of the Thirtyfifth AAAI Conference on Artificial Intelligence . Palo Alto : AAAI Press , 2021 , 35 ( 5 ): 4635 - 4643 .

ZHANG P Y , GUO J Y , LI C Z , et al . Efficiently leveraging multi-level user intent for session-based recommendation via atten-mixer network [C ] // Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining (WSDM) . New York : ACM Press , 2023 : 168 - 176 .

FENG Y F , YOU H X , ZHANG Z Z , et al . Hypergraph neural networks [C ] // Proceedings of the Thirtythird AAAI Conference on Artificial Intelligence . Palo Alto : AAAI Press , 2019 : 3558 - 3565 .

WANG J L , DING K Z , ZHU Z W , et al . Session-based recommendation with hypergraph attention networks [C ] // Proceedings of the 2021 SIAM International Conference on Data Mining (SDM) . Piscataway : IEEE Press , 2021 : 82 - 90 .

PENG D L , ZHANG S . GC-HGNN: a global-context supported hypergraph neural network for enhancing session-based recommendation [J ] . Electronic Commerce Research and Applications , 2022 , 52 ( C ): 101129 .

DING C X , ZHONG Z Y , LI C , et al . Session-based recommendation with hypergraph convolutional networks and sequential information embeddings [J ] . Expert Systems with Applications , 2023 , 223 : 119875 - 119875 .

ZHANG Z G , ZHANG H M , ZHANG Z F , et al . Context-embedded hypergraph attention network and self-attention for session recommendation [J ] . Scientific Reports , 2024 , 14 ( 1 ): 19413 .

XIA X , YIN H Z , YU J L , et al . Self-supervised hypergraph convolutional networks for session-based recommendation [C ] // Proceedings of the Thirtyfifth AAAI Conference on Artificial Intelligence . Palo Alto : AAAI Press , 2021 , 35 ( 5 ): 4503 - 4511 .

LI X B , TANG Y , GUO C J , et al . Attribute-enhanced hypergraph neural networks for session-based recommendation [C ] // Proceedings of the Thirtyforth International Joint Conference on Neural Networks (IJCNN) . Piscataway : IEEE Press , 2024 : 1 - 7 .

WANG F Y , GAO X Y , CHEN Z Y , et al . Contrastive multi-level graph neural networks for session-based recommendation [J ] . IEEE Transactions on Multimedia , 2023 , 25 : 9278 - 9289 .

ZHAO Q B , ZHOU X M , ZHANG X Z , et al . Unified Empirical Evaluation and Comparison of Session-based Recommendation Algorithms [J ] . ACM Computing Surveys , 2025 , 57 ( 10 ): 1 - 39 .

FANG X S , WU Y G , LU J H , et al . Intent enhanced self-supervised hypergraph learning for session-based recommendation [C ] // Proceedings of the 2024 European Conference on Machine Learning and Knowledge Discovery in Databases . Vilnius, Lithuania : ECML PKDD Press , 2024 : 83 - 99 .

SARWAR B , KARYPIS G , KONSTAN J , et al . Item-based collaborative filtering recommendation algorithms [C ] // Proceedings of the Tenth International World Wide Web Conference . New York : ACM Press , 2001 : 285 - 295 .

LIU Q , ZENG Y F , MOKHOSI R , et al . Stamp: short-term attention memory priority model for session-based recommendation [C ] // Proceedings of the Twentyfourth ACM SIGKDD International Conference on Knowledge Discovery & Data Mining . New York : ACM Press , 2018 , 1831 - 1839 .

WU S , TANG Y Y , ZHU Y Q , et al . Session-based recommendation with graph neural networks [C ] // Proceedings of the Thirtythird International Joint Conference on Artificial Intelligence . Palo Alto : AAAI Press , 2019 , 33 ( 1 ): 346 - 353 .

Views

114

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Attention aware edge-node exchange graph neural network

Research on human action recognition based on mobile communication network signals

Heterogeneous graph neural network algorithm based on topology information enhancement

Node classification of complex network based on enhanced graph neural network and contrastive learning

Semantic embedding via joint loss function and composite contrastive learning

Related Author

Ruiqin WANG

Yimin HUANG

Qishun JI

Chaoyi WAN

Zhifeng ZHOU

Qian Neng

Lu Chengling

Wan Yuxuan

Related Institution

Library of Wenzhou University

Institute of Cyberspace Security, Zhejiang University of Technology

School of Electronics and Communication Engineering, Zhejiang Post and Telecommunication College

College of Artificial Intelligence, Jiaxing University

College of Information Science and Engineering, Jiaxing University

⁰