超图神经网络驱动的跨视角群组推荐算法

doi:10.3969/j.issn.0255-8297.2026.03.010

摘要/Abstract

摘要： 近年来，随着信息技术的发展和网络社交的广泛普及，传统推荐系统在刻画复杂用户需求方面逐渐暴露出局限性，从而引发了对群体推荐系统的日益关注。然而，现有群组推荐方法多依赖于对个体成员偏好的简单汇聚，难以捕捉群体行为中的隐含共识信息。本文针对该问题，提出一种融合多视角信息的超图神经网络群组推荐模型IConcen。该模型从成员级、物品级和群体级三种互补视角对群组交互行为进行建模，并引入自适应融合模块动态协调各视图权重，生成高表达性融合特征，有效提升推荐性能。在Mafengwo和CAMRa2011数据集上的实验结果表明，该方法在群组推荐与用户推荐任务中的性能均优于HCR等主流模型。其中，在Mafengwo数据集上，相较于S²-HHGR、Agree和HCR模型，HR@5和NDCG@5指标分别提升24.3%和28.2%以上，验证了所提方法的有效性与优越性。

关键词: 群组推荐, 超图, 多视角学习, 群体偏好, 推荐系统

Abstract: In recent years, with the development of information technology and the widespread popularity of online social networking, traditional recommender systems have gradually exposed limitations in characterizing complex user needs, thus drawing increasing attention to group recommendation systems. However, most existing group recommendation methods rely on simple aggregation of individual members' preferences, making it difficult to capture implicit consensus in group behavior. To address this problem, this paper proposed IConcen, a hypergraph neural network-based group recommendation model that integrated multi-view information. The model captured group interactions from three complementary perspectives: member level, item level, and group level. It also introduced an adaptive fusion module that dynamically balances the weights of these views to generate highly expressive fused features, effectively improving recommendation performance.Experimental results on the Mafengwo and CAMRa2011 datasets show that the proposed method outperforms mainstream models such as HCR in both group recommendation and user recommendation tasks. Specifically, on the Mafengwo dataset, the proposed method improves HR@5 and NDCG@5 by more than 24.3% and 28.2%, respectively, compared with the S2-HHGR, Agree, and HCR models, verifying its effectiveness and superiority.

Key words: group recommendation, hypergraph, multi-view learning, group preference, recommender system

中图分类号:

TP391

郭艳, 王浩然, 侯嵩松, 段旭良, 穆炯. 超图神经网络驱动的跨视角群组推荐算法[J]. 应用科学学报, 2026, 44(3): 486-502.

GUO Yan, WANG Haoran, HOU Songsong, DUAN Xuliang, MU Jiong. Cross-View Group Recommendation Algorithm Driven by Hypergraph Neural Networks[J]. Journal of Applied Sciences, 2026, 44(3): 486-502.

参考文献

[1] 许晓明, 梅红岩, 于恒, 等. 基于偏好融合的群组推荐方法研究综述[J]. 小型微型计算机系统, 2020, 41(12): 2500-2508. Xu X M, Mei H Y, Yu H, et al. Review of group recommendation methods based on preference fusion [J]. Journal of Chinese Computer Systems, 2020, 41(12): 2500-2508. (in Chinese)
[2] Feng Y F, You H X, Zhang Z Z, et al. Hypergraph neural networks [C]//33rd AAAI Conference on Artificial Intelligence/31st Innovative Applications of Artificial Intelligence Conference/9th AAAI Symposium on Educational Advances in Artificial Intelligence, 2019: 3558-3565.
[3] Yu J L, Yin H Z, Li J D, et al. Self-supervised multi-channel hypergraph convolutional network for social recommendation [C]//30th World Wide Web Conference (WWW), 2021: 413-424.
[4] Wang J L, Ding K Z, Zhu Z W, et al. Session-based recommendation with hypergraph attention networks [DB/OL]. (2021-12-28) [2025-08-15]. https://arxiv.org/abs/2112.14266.
[5] 房志明, 吴鑫卓, 林原, 等. 基于用户画像的高校采购评审专家推荐算法[J]. 实验技术与管理, 2024, 41(4): 228-237. Fang Z M, Wu X Z, Lin Y, et al. Expert recommendation algorithm for university procurement review based on user portraits [J]. Experimental Technology and Management, 2024, 41(4): 228-237. (in Chinese)
[6] 王永贵, 陈书铭, 刘义海, 等. 结合超图对比学习和关系聚类的知识感知推荐算法[J]. 计算机科学与探索, 2024, 18(8): 2140-2155. Wang Y G, Chen S M, Liu Y H, et al. Knowledge-aware recommendation algorithm combining hypergraph contrastive learning and relational clustering [J]. Journal of Frontiers of Computer Science and Technology, 2024, 18(8): 2140-2155. (in Chinese)
[7] Xia X, Yin H Z, Yu J L, et al. Self-supervised hypergraph convolutional networks for sessionbased recommendation [C]//35th AAAI Conference on Artificial Intelligence/33rd Conference on Innovative Applications of Artificial Intelligence/11th Symposium on Educational Advances in Artificial Intelligence, 2021: 4503-4511.
[8] 王浩南, 贺平安, 代琦. 基于完整超图神经网络的捆绑推荐模型[J]. 计算机应用研究, 2025, 42(7): 2003-2010. Wang H N, He P A, Dai Q. Bundle recommendation model based on complete hypergraph neural networks [J]. Application Research of Computers, 2025, 42(7): 2003-2010. (in Chinese)
[9] Massouros C, Massouros G. An overview of the foundations of the hypergroup theory [J]. Mathematics, 2021, 9(9): 1014.
[10] Krishnan R, Rajpurkar P, Topol E J. Self-supervised learning in medicine and healthcare [J]. Nature Biomedical Engineering, 2022, 6(12): 1346-1352.
[11] Defferrard M, Bresson X, Vandergheynst P. Convolutional neural networks on graphs with fast localized spectral filtering [DB/OL]. (2017-02-05) [2025-08-15]. https://arxiv.org/abs/1606.09375.
[12] Kipf T N, Welling M. Semi-supervised classification with graph convolutional networks [DB/OL]. (2017-02-22) [2025-08-15]. https://arxiv.org/abs/1606.02907.
[13] Gan D Y, Gao M, Li W T, et al. LARGE: a leadership perception framework for group recommendation [J]. Expert Systems with Applications, 2025, 260: 125416.
[14] Wang C, Shi Y C, Peng J. Personalized group recommendation model based on hybrid graph neural network [C]//20th International Conference on Intelligent Computing (ICIC), 2024: 458- 466.
[15] Cremonesi P, Koren Y, Turrin R. Performance of recommender algorithms on top-N recommendation tasks [C]//4th ACM conference on Recommender systems, 2010: 39-46.
[16] Zhang J W, Gao M, Yu J L, et al. Double-scale self-supervised hypergraph learning for group recommendation [C]//30th ACM International Conference on Information and Knowledge Management (CIKM), 2021: 2557-2567.
[17] Cao D, He X N, Miao L H, et al. Attentive group recommendation [C]//41st Annual International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2018: 645-654.
[18] Jia R Q, Zhou X F, Dong L H, et al. Hypergraph convolutional network for group recommendation [C]//21st IEEE International Conference on Data Mining (IEEE ICDM), 2021: 260-269.
[19] Chen T, Yin H Z, Long J, et al. Thinking inside the box: learning hypercube representations for group recommendation [C]//45th International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2022: 1664-1673.
[20] Sankar A, Wu Y H, Wu Y H, et al. GroupIM: a mutual information maximization framework for neural group recommendation [C]//43rd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), 2020: 1279-1288.
[21] Wu X X, Xiong Y, Zhang Y, et al. ConsRec: learning consensus behind interactions for group recommendation [DB/OL]. (2023-02-07) [2025-08-15]. https://arxiv.org/abs/2302.03555.
[22] Xu S S, Sun F Z, Wu X S, et al. A heterogeneous graph neural recommendation model with hierarchical social trust [J]. Computers and Electrical Engineering, 2023, 111: 108912.
[23] Chen G D, Sun R N, Jiang Y Z, et al. A multi-modal modeling framework for cold-start short-video recommendation [C]//18th ACM Conference on Recommender Systems (RecSys), 2024: 391-400.