基于多语义与时序卷积的知识图谱推荐模型

doi:10.16088/j.issn.1001-6600.2025071802

摘要/Abstract

摘要： 推荐系统是解决信息过载问题的重要手段,知识图谱是目前推荐系统应用最为广泛的辅助信息来源。现有知识图谱在推荐系统中存在多语义关系动态建模不足、邻居序列依赖与长程关联建模缺失、图结构多层次特征提取能力不足的问题。为解决上述问题,本文提出一种基于多语义与时序卷积的推荐模型MSTC-KG。该模型通过多头注意力机制与门控机制动态融合用户-关系交互,区分邻居节点语义贡献;利用GRU捕捉邻居序列的时序依赖和长程关联;通过一维卷积神经网络提取图结构的局部-全局多层次特征。在2个公开数据集上与14个基线模型的对比实验显示,MSTC-KG在Book-Crossing、MovieLens-20M数据集上AUC分别为0.737和0.982,F₁值分别为0.680和0.938,均领先于其他基准模型。实验表明,模型通过“多语义动态区分+时序依赖捕捉+层次特征提取”架构,有效提升推荐准确性和对复杂知识图谱结构的建模能力。

关键词: 知识图谱, 推荐系统, 多头注意力, GRU, 卷积神经网络

Abstract: Recommendation systems are a crucial means to address the problem of information overload, and knowledge graphs serve as the most widely used auxiliary information source in recommendation systems. Existing knowledge graph-based approaches suffer from limitations including insufficient dynamic modeling of multi-semantic relationships, lack of modeling for neighbor sequence dependencies and long-range associations, and inadequate capability in extracting multi-level features from graph structures. To tackle these issues, this paper proposes a Multi-Semantic and Temporal Convolutional model for Knowledge Graph recommendation (MSTC-KG). The model dynamically fuses user-relation interactions through a multi-head attention mechanism and a gating mechanism to distinguish the semantic contributions of neighbor nodes, employs GRU to capture the temporal dependencies and long-range associations of neighbor sequences, and utilizes 1D convolutional neural networks to extract local-to-global multi-level features of graph structures. Compared with 14 baseline models on two public datasets, MSTC-KG achieves an AUC of 0.737 and 0.982, and an F₁-score of 0.680 and 0.938 on the Book-Crossing and MovieLens-20M datasets respectively, outperforming all other baseline models. Experiments demonstrate that through the architecture characterized by “dynamic multi-semantic differentiation + temporal dependency capture + hierarchical feature extraction”, the model effectively enhances recommendation accuracy and the capability to model complex graph structures.

Key words: knowledge graph, recommendation system, multi-head attention, GRU, convolutional neural network

中图分类号: TP391.3

王慧, 祝君豪, 杨志成, 胡昌志. 基于多语义与时序卷积的知识图谱推荐模型[J]. 广西师范大学学报（自然科学版）, 2026, 44(3): 107-120.

WANG Hui, ZHU Junhao, YANG Zhicheng, HU Changzhi. A Multi-semantic and Temporal Convolutional Model for Knowledge Graph Recommendation[J]. Journal of Guangxi Normal University(Natural Science Edition), 2026, 44(3): 107-120.

参考文献

[1] ZHAO L, LIU G Z, YAN S L, et al. Emotion-driven music recommendation system based on fully convolutional recurrent attention networks and collaborative filtering[J]. Alexandria Engineering Journal, 2025, 125: 354-366. DOI: 10.1016/j.aej.2025.03.114.
[2] 高仰, 刘渊. 融合知识图谱和短期偏好的推荐算法[J]. 计算机科学与探索, 2021, 15(6): 1133-1144.
[3] 张玉洁, 董政, 孟祥武. 个性化广告推荐系统及其应用研究[J]. 计算机学报, 2021, 44(3): 531-563.
[4] LI D J, ESQUIVEL J A. Lightweight and personalised e-commerce recommendation based on collaborative filtering and LSH[J]. International Journal of Ad Hoc and Ubiquitous Computing, 2024, 45(2): 82-91. DOI: 10.1504/ijahuc.2024.136826.
[5] 戴紫纯. 基于混合算法的个性化新闻推荐系统的设计与实现[D]. 北京: 北京邮电大学, 2024. DOI: 10.26969/d.cnki.gbydu.2024.002180.
[6] 吴正洋, 汤庸, 刘海. 个性化学习推荐研究综述[J]. 计算机科学与探索, 2022, 16(1): 21-40.
[7] 赵晔辉, 柳林, 王海龙, 等. 知识图谱推荐系统研究综述[J]. 计算机科学与探索, 2023, 17(4): 771-791.
[8] 陆浩言. 基于协同过滤和内容的推荐算法在电影推荐系统中的融合研究[J]. 电脑知识与技术, 2025, 21(1): 79-81. DOI: 10.14004/j.cnki.ckt.2025.0085.
[9] 丁少衡, 姬东鸿, 王路路. 基于用户属性和评分的协同过滤推荐算法[J]. 计算机工程与设计, 2015, 36(2): 487-491, 497. DOI: 10.16208/j.issn1000-7024.2015.02.039.
[10] 阎红灿, 王子茹, 李伟芳, 等. 伴随时间的模糊聚类协同过滤推荐算法[J]. 计算机工程与科学, 2021, 43(11): 2084-2090.
[11] ADOMAVICIUS G, TUZHILIN A. Toward the next generation of recommender systems: a survey of the state-of-the-art and possible extensions[J]. IEEE Transactions on Knowledge and Data Engineering, 2005, 17(6): 734-749. DOI: 10.1109/TKDE.2005.99.
[12] 蒋雪瑶, 力维辰, 刘井平, 等. 基于多模态模式迁移的知识图谱实体配图[J]. 计算机工程, 2022, 48(8): 70-76. DOI: 10.19678/j.issn.1000-3428.0064039.
[13] 邹长龙, 安敬民, 李冠宇. 基于邻域聚合与CNN的知识图谱实体类型补全[J]. 计算机工程, 2023, 49(3): 134-141. DOI: 10.19678/j.issn.1000-3428.0063989.
[14] BORDES A, USUNIER N, GARCIA-DURáN A, et al. Translating embeddings for modeling multi-relational data[C]// Proceedings of the 27th International Conference on Neural Information Processing Systems: Volume 2. Red Hook, NY: Curran Associates Inc., 2013: 2787-2795.
[15] TROUILLON T, WELBL J, RIEDEL S, et al. Complex embeddings for simple link prediction[C]// Proceedings of the 33rd International Conference on International Conference on Machine Learning: PMLR 48. New York, NY: JMLR, 2016: 2071-2080.
[16] XIAO Y, XU J, YANG J, et al. Determinate node selection for semi-supervised classification oriented graph convolutional networks[J]. International Journal of Bio-Inspired Computation, 2025, 25(1): 1-10. DOI: 10.1504/ijbic.2025.143648.
[17] ZHANG F Z, YUAN N J, LIAN D F, et al. Collaborative knowledge base embedding for recommender systems[C]// Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York, NY: Association for Computing Machinery, 2016: 353-362. DOI: 10.1145/2939672.2939673.
[18] LIN Y K, LIU Z Y, SUN M S, et al. Learning entity and relation embeddings for knowledge graph completion[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2015, 29(1): 2181-2187. DOI: 10.1609/aaai.v29i1.9491.
[19] ZHANG J Y, DUAN H C, GUO L, et al. Towards lightweight cross-domain sequential recommendation via external attention-enhanced graph convolution network[C]// Database Systems for Advanced Applications. Cham: Springer Nature Switzerland AG, 2023: 205-220. DOI: 10.1007/978-3-031-30672-3_14.
[20] YING R, HE R N, CHEN K F, et al. Graph convolutional neural networks for web-scale recommender systems[C]// Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York, NY: Association for Computing Machinery, 2018: 974-983. DOI: 10.1145/3219819.3219890.
[21] WANG X, HE X N, CAO Y X, et al. KGAT: knowledge graph attention network for recommendation[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York, NY: Association for Computing Machinery, 2019: 950-958. DOI: 10.1145/3292500.3330989.
[22] MA R X, BU X Y, CHEN Z X, et al. Knowledge graph preference migration network for recommendation[J]. Expert Systems with Applications, 2024, 237: 121256. DOI: 10.1016/j.eswa.2023.121256.
[23] WANG X, HE X N, WANG M, et al. Neural graph collaborative filtering[C]// Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, NY: Association for Computing Machinery, 2019: 165-174. DOI: 10.1145/3331184.3331267.
[24] WANG H W, ZHANG F Z, WANG J L, et al. RippleNet: propagating user preferences on the knowledge graph for recommender systems[C]// Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York, NY: Association for Computing Machinery, 2018: 417-426. DOI: 10.1145/3269206.3271739.
[25] XU H C, BAO J P, LIU W B. Double-branch multi-attention based graph neural network for knowledge graph completion[C]// Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Stroudsburg, PA: Association for Computational Linguistics, 2023: 15257-15271. DOI: 10.18653/v1/2023.acl-long.850.
[26] GUO Q Y, ZHUANG F Z, QIN C, et al. A survey on knowledge graph-based recommender systems[J]. IEEE Transactions on Knowledge and Data Engineering, 2022, 34(8): 3549-3568. DOI: 10.1109/TKDE.2020.3028705.
[27] 陈思宇, 陈茫, 周力青, 等. 基于知识图谱嵌入的旅游电子商务个性化推荐[J]. 商业经济研究, 2023(19): 86-90.
[28] YU X, REN X, SUN Y Z, et al. Personalized entity recommendation: a heterogeneous information network approach[C]// Proceedings of the 7th ACM International Conference on Web Search and Data Mining. New York, NY: Association for Computing Machinery, 2014: 283-292. DOI: 10.1145/2556195.2556259.
[29] 李政, 黄勃, 王晨明, 等. 基于异构注意力网络的知识图嵌入元路径推荐算法[J]. 电子科技大学学报, 2025, 54(5): 776-788. DOI: 10.12178/1001-0548.2024129.
[30] 李伟玥, 朱志国, 董昊, 等. 循环神经网络和注意力增强的门控图神经网络会话推荐模型[J]. 模式识别与人工智能, 2024, 37(3): 191-206. DOI: 10.16451/j.cnki.issn1003-6059.202403001.
[31] WANG H W, ZHANG F Z, ZHANG M D, et al. Knowledge-aware graph neural networks with label smoothness regularization for recommender systems[C]// Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. New York, NY: Association for Computing Machinery, 2019: 968-977. DOI: 10.1145/3292500.3330836.
[32] GAO M, LI J Y, CHEN C H, et al. Enhanced multi-task learning and knowledge graph-based recommender system[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(10): 10281-10294. DOI: 10.1109/TKDE.2023.3251897.
[33] RENDLE S. Factorization machines with libFM[J]. ACM Transactions on Intelligent Systems and Technology, 2012, 3(3): 1-22. DOI: 10.1145/2168752.2168771.
[34] WANG H W, ZHAO M, XIE X, et al. Knowledge graph convolutional networks for recommender systems[C]// WWW'19: The World Wide Web Conference. New York, NY: Association for Computing Machinery, 2019: 3307-3313. DOI: 10.1145/3308558.3313417.
[35] ZHANG Y H, YUAN M, ZHAO C, et al. Aggregating knowledge-aware graph neural network and adaptive relational attention for recommendation[J]. Applied Intelligence, 2022, 52(15): 17941-17953. DOI: 10.1007/s10489-022-03359-w.
[36] WANG Z, LIN G Y, TAN H B, et al. CKAN: collaborative knowledge-aware attentive network for recommender systems[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York, NY: Association for Computing Machinery, 2020: 219-228. DOI: 10.1145/3397271.3401141.
[37] GUO L M, LIU T T, ZHOU S M, et al. Knowledge graph-based personalized multitask enhanced recommendation[J]. IEEE Transactions on Computational Social Systems, 2024, 11(6): 7685-7697. DOI: 10.1109/TCSS.2024.3446289.
[38] LIU T Q, ZHANG X X, WANG W Z, et al. KAT: knowledge-aware attentive recommendation model integrating two-terminal neighbor features[J]. International Journal of Machine Learning and Cybernetics, 2024, 15(11): 4941-4958. DOI: 10.1007/s13042-024-02194-4.
[39] LIU X Y, FENG H W, ZHANG X Q, et al. Graph contrast learning for recommendation based on relational graph convolutional neural network[J]. Journal of King Saud University: Computer and Information Sciences, 2024, 36(8): 102168. DOI: 10.1016/j.jksuci.2024.102168.
[40] FAN H L, ZHONG Y C, ZENG G P, et al. Improving recommender system via knowledge graph based exploring user preference[J]. Applied Intelligence, 2022, 52(9): 10032-10044. DOI: 10.1007/s10489-021-02872-8.
[41] ZHOU Y, GUO J, SONG B, et al. Trust-aware multi-task knowledge graph for recommendation[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(8): 8658-8671. DOI: 10.1109/TKDE.2022.3221160.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed