在现有基于知识图谱的推荐方法中,大多采用单一用户或项目表示,在合并来自知识图谱的实体时,用户或项目表示所携带的信息容易丢失,用户兴趣欠拟合,进而导致模型的次优表示。为此,该文提出了融合用户-项目的邻居实体表示推荐方法,联合用户和项目的特征表示挖掘用户更感兴趣的内容,使用TransR模型在知识图谱中进行实体传播,获取用户的嵌入表示;使用GCN聚合候选项目在知识图谱的邻域实体,获取项目的嵌入表示。为验证该文方法的有效性,在MovieLens-20M、Book-Crossing、Last-FM公共数据集上进行了实验,并与Wide&Deep、RippleNet、KGAT等10种方法进行了对比,实验结果表明,该文方法的平均AUC和ACC分别提升约8.75%和7.10%。
Abstract
Most of the existing recommendation methods based on knowledge graphs use either the user or the item. We propose an improved recommendation method incorporating user-item neighbor entity. This model uses TransR for entity propagation in the knowledge graph to obtain user embedding representations. It uses GCN to aggregate candidate items in the neighborhood entities of the knowledge graph to obtain item embedding representations. Experiments on the MovieLens-20M, Book-Crossing, and Last-FM datasets prove that the average AUC and ACC values of this method are increased by 8.75% and 7.10%, compared with other 10 methods such as Wide&Deep, RippleNet, and KGAT.
关键词
知识图谱 /
推荐算法 /
用户兴趣 /
特征表示
{{custom_keyword}} /
Key words
knowledge graph /
recommendation algorithm /
user interest /
feature representation
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] Rendle S, Freudenthaler C, Gantner Z, et al. BPR: Bayesian personalized ranking from implicit feedback[J]. arXiv preprint arXiv:1205.2618, 2012.
[2] Rendle S. Factorization machines with Libfm[J]. ACM Transactions on Intelligent Systems and Technology, 2012, 3(3): 1-22.
[3] He X, Chua T S. Neural factorization machines for sparse predictive analytics[C]//Proceedings of the 40th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2017: 355-364.
[4] Cheng H, Koc L, Harmsen J, et al. Wide and Deeplearning for recommender systems[C]//Proceedings of the Conference on Recommender Systems, 2016: 7-10.
[5] Yu X, Ren X, Sun Y, et al. Personalized entity recommendation: A heterogeneous information network approach[C]//Proceedings of the 7th ACM International Conference on Web Search and Data Mining, 2014: 283-292.
[6] Ma W, Zhang M, Cao Y, et al. Jointly learning explainable rules for recommendation with knowledge graph[C]//Proceedings of the World Wide Web Conference,2019: 1210-1221.
[7] Zhang F, Yuan N J, Lian D, et al. Collaborativeknowledge base embedding for recommender systems[C]//Proceedings of the 22nd ACM SIGKDD International Knowledge Discovery and Data Mining, 2016: 353-362.
[8] Wang H, Zhang F, Hou M, et al. SHINE: Signed heterogeneous information network embedding for sentiment link prediction[C]//Proceedings of the 11th ACM International Conference on Web Search and Data Mining, 2018: 592-600.
[9] Wang H, Zhang F, Xie X, et al. DKN: Deep knowledge-aware network for news recommendation[C]//Proceedings of the Web Conference, 2018: 1835-1844.
[10] Wang H, Zhang F, Wang J, et al. RippleNet: Propagating user preferences on the knowledge graph for recommender systems[C]//Proceedings of the 27th ACM Conference on Information and Knowledge Management, 2018: 417-426.
[11] Wang H, Zhang F, Zhang M, 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, 2019: 968-977.
[12] Wang X, He X, Cao Y, et al. Kgat: Knowledge graph attention network for recommendation[C]//Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2019: 950-958.
[13] Wang X, Xu Y, He X, et al. Reinforced negative sampling over knowledge graph for recommendation[C]//Proceedings of the Web Conference 2020: 99-109.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
宁夏自然科学基金(2020AAC03218)
{{custom_fund}}
PDF(2633 KB)
