基于用户行为特征融合与异常点检测的知识图谱推荐模型

doi:10.19678/j.issn.1000-3428.0070696

摘要/Abstract

摘要： 知识图谱作为一种图结构数据组织方式,为推荐系统提供了更为丰富的语义信息和上下文背景,使得推荐系统能够有效地处理复杂的用户行为和物品特征。现有的基于知识图谱的推荐方法仍然面临诸如信息过度平滑和异常数据处理等问题,尤其是在大规模数据处理的场景中,过度平滑往往导致模型无法捕捉到个性化的用户需求,异常数据的干扰也可能影响推荐结果的准确性和鲁棒性。为此,提出了一种基于用户行为特征融合与异常点检测的知识图谱推荐模型。该模型通过引入用户融合行为特征,有效避免信息过度平滑的问题;且该模型结合了异常点检测机制,通过识别和剔除噪声数据和异常行为,显著提升了推荐结果的准确性和鲁棒性,减少了不良数据对推荐结果的影响。为了验证模型的有效性,在3个真实世界数据集上进行了实验。实验结果表明,与现有的最优基线模型相比,提出的模型在受试者工作特征曲线下面积(AUC)和F1值等指标上分别平均提升了0.067 7和0.050 9,尤其在数据稀疏程度较高的数据集上,模型的性能提升尤为显著,能够有效缓解数据稀疏性带来的问题。

关键词: 推荐系统, 图神经网络, 知识图谱, 特征融合, 异常点检测

Abstract: Knowledge graphs, a graph-based data organization method, provide rich semantic information and contextual background for recommendation systems, enabling them to effectively handle complex user behaviors and item features. Existing knowledge graph-based recommendation methods still face challenges such as information over-smoothing and handling of anomalies, particularly in large-scale data processing scenarios. Over-smoothing often prevents the model from capturing personalized user needs, and interference from anomalies can affect the accuracy and robustness of the recommendations. To address these issues, this paper proposes a knowledge graph recommendation model based on user behavior feature fusion and anomaly detection. The model effectively avoids information over-smoothing by incorporating fused user behavior features. Additionally, the model integrates an anomaly detection mechanism that identifies and removes noisy data and abnormal behaviors, significantly improving the accuracy and robustness of the recommendations while reducing the impact of poor data on the recommendation results. To validate the effectiveness of the model, experiments are conducted on three real-world datasets. The experimental results show that, compared to the existing best baseline models, the proposed model achieves an average improvement of 0.067 7 in Area Under the Receiver Operating Characteristic Curve (AUC) and 0.050 9 in F1 values. The performance improvement is particularly significant in datasets with high sparsity, effectively alleviating the challenges posed by data sparsity.

Key words: recommendation system, graph neural network, knowledge graph, feature fusion, anomaly detection

中图分类号:

TP311.1

闫世泽, 方志军. 基于用户行为特征融合与异常点检测的知识图谱推荐模型[J]. 计算机工程, 2026, 52(10): 81-93.

YAN Shize, FANG Zhijun. Knowledge Graph Recommendation Model Based on User Behavior Feature Fusion and Anomaly Detection[J]. Computer Engineering, 2026, 52(10): 81-93.

https://www.ecice06.com/CN/Y2026/V52/I10/81

参考文献

[1] 吴国栋, 刘旭旭, 毕海娇, 等. 基于元学习个性化推荐研究综述[J]. 计算机工程与科学, 2024, 46(2): 338-352. WU G D, LIU X X, BI H J, et al. Review of personalized recommendation research based on meta-learning[J]. Computer Engineering & Science, 2024, 46(2): 338-352. (in Chinese)
[2] 冷亚军, 陆青, 梁昌勇. 协同过滤推荐技术综述[J]. 模式识别与人工智能, 2014, 27(8): 720-734. LENG Y J, LU Q, LIANG C Y. Survey of recommendation based on collaborative filtering[J]. Pattern Recognition and Artificial Intelligence, 2014, 27(8): 720-734. (in Chinese)
[3] CHEN X J, JIA S B, XIANG Y. A review: knowledge reasoning over knowledge graph[J]. Expert Systems with Applications, 2020, 141: 112948.
[4] ZHANG J C, ZAIN A M, ZHOU K Q, et al. A review of recommender systems based on knowledge graph embedding[J]. Expert Systems with Applications, 2024, 250: 123876.
[5] LI J, ZHANG Q R, LIU W X, et al. Another perspective of over-smoothing: alleviating semantic over-smoothing in deep GNNs[J]. IEEE Transactions on Neural Networks and Learning Systems, 2025, 36(4): 6897-6910.
[6] SHOKRZADEH Z, FEIZI-DERAKHSHI M R, BALAFAR M A, et al. Knowledge graph-based recommendation system enhanced by neural collaborative filtering and knowledge graph embedding[J]. Ain Shams Engineering Journal, 2024, 15(1): 102263.
[7] WU Z H, PAN S R, CHEN F W, et al. A comprehensive survey on graph neural networks[J]. IEEE Transactions on Neural Networks and Learning Systems, 2021, 32(1): 4-24.
[8] 刘广腾, 王峰, 吴中博. 下一个兴趣点推荐算法综述[J]. 计算机科学与探索, 2025, 19(7): 1747-1770. LIU G T, WANG F, WU Z B. Survey on next point-of-interest recommendation algorithms[J]. Journal of Frontiers of Computer Science & Technology, 2025, 19(7): 1747-1770. (in Chinese)
[9] 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. New York, USA: ACM Press, 2013: 2787-2795.
[10] LIN Y K, LIU Z Y, SUN M S, et al. Learning entity and relation embeddings for knowledge graph completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence. New York, USA: ACM Press, 2015: 2181-2187.
[11] WANG Z, ZHANG J W, FENG J L, et al. Knowledge graph embedding by translating on hyperplanes[C]//Proceedings of the AAAI Conference on Artificial Intelligence. New York, USA: ACM Press, 2014: 1112-1119.
[12] WANG H W, ZHAO M, XIE X, et al. Knowledge graph convolutional networks for recommender systems[C]//Proceedings of the World Wide Web Conference. New York, USA: ACM Press, 2019: 3307-3313.
[13] 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 and Data Mining. New York, USA: ACM Press, 2019: 950-958.
[14] WANG X, HUANG T L, WANG D X, et al. Learning intents behind interactions with knowledge graph for recommendation[C]//Proceedings of the Web Conference 2021. New York, USA: ACM Press, 2021: 878-887.
[15] LU J W, LI J P, LI W H, et al. Heterogeneous propagation graph convolution network for a recommendation system based on a knowledge graph[J]. Engineering Applications of Artificial Intelligence, 2024, 138: 109395.
[16] MA R X, GUO F Q, LI Z Y, et al. Knowledge graph random neural networks for recommender systems[J]. Expert Systems with Applications, 2022, 201: 117120.
[17] SCARSELLI F, GORI M, TSOI A C, et al. The graph neural network model[J]. IEEE Transactions on Neural Networks, 2009, 20(1): 61-80.
[18] KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB/OL]. [2024-11-08]. https://arxiv.org/abs/1609.02907.
[19] VELI AČG KOVIĆ P, CUCURULL G, CASANOVA A, et al. Graph attention networks[EB/OL]. [2024-11-08]. https://arxiv.org/abs/1710.10903.
[20] HAMILTON W L, YING R, LESKOVEC J. Inductive representation learning on large graphs[EB/OL]. [2024-11-08]. https://arxiv.org/abs/1706.02216.
[21] SCHLICHTKRULL M, KIPF T N, BLOEM P, et al. Modeling relational data with graph convolutional networks[C]//Proceedings of the Semantic Web Conference. Berlin, Germany: Springer, 2018: 593-607.
[22] GAO Y, WANG X, HE X N, et al. Addressing heterophily in graph anomaly detection: a perspective of graph spectrum[C]//Proceedings of the ACM Web Conference 2023. New York, USA: ACM Press, 2023: 1528-1538.
[23] ZHAO N, LONG Z, WANG J, et al. AGRE: a knowledge graph recommendation algorithm based on multiple paths embeddings RNN encoder[J]. Knowledge-Based Systems, 2023, 259: 110078.
[24] HUANG W J, WU J H, SONG W H, et al. Cross attention fusion for knowledge graph optimized recommendation[J]. Applied Intelligence, 2022, 52(9): 10297-10306.
[25] LIU X Q, YANG Z S, CHENG J Y. Music recommendation algorithms based on knowledge graph and multi-task feature learning[J]. Scientific Reports, 2024, 14(1): 2055.
[26] 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, USA: ACM Press, 2018: 417-426.
[27] 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 and Data Mining. New York, USA: ACM Press, 2019: 968-977.
[28] WANG H W, ZHANG F Z, ZHAO M, et al. Multi-task feature learning for knowledge graph enhanced recommendation[C]//Proceedings of the World Wide Web Conference. New York, USA: ACM Press, 2019: 2000-2010.
[29] 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, USA: ACM Press, 2020: 219-228.
[30] WANG W, SHEN X X, YI B L, et al. Knowledge-aware fine-grained attention networks with refined knowledge graph embedding for personalized recommendation[J]. Expert Systems with Applications, 2024, 249: 123710.
[31] JIANG M Y, LI M, CAO W M, et al. Multi-task convolutional deep neural network for recommendation based on knowledge graphs[J]. Neurocomputing, 2025, 619: 129136.
[32] KINGMA D P, BA J. Adam: a method for stochastic optimization[EB/OL]. [2024-11-08]. https://arxiv.org/abs/1412.6980.
[33] GLOROT X, BENGIO Y. Understanding the difficulty of training deep feedforward neural networks[C]//Proceedings of the International Conference on Artificial Intelligence and Statistics. [S. l.]: PMLR, 2010: 249-256.

选择文件类型/文献管理软件名称

选择包含的内容