随着信息的海量增长,推荐系统成为我们日常生活中一种重要的应用。传统的推荐系统根据用户和物品的交互行为进行推荐并利用用户对物品的评分来体现用户的喜好,但是数据的稀疏性会影响推荐结果的准确度,并且简单地评分数字也难以体现用户偏好的主观性以及用户选择的可解释性。因此,该文提出了一种融合标签和知识图谱的推荐方法,其中标签是一种文本信息,其包含的丰富内容和潜在的语义信息可以体现用户对物品的主观评价,对推荐起着关键作用。而知识图谱作为一种有效的推荐辅助技术,其包含的大量实体能为物品提供更多有效的特征信息。此外,该文还提出了一种融合注意力和自注意力的混合注意力模型,通过标签和实体为物品特征分配混合注意力权重,从而提高了推荐性能。实验结果表明,在MovieLens和Last.FM数据集上,该模型的推荐性能较其他推荐算法有所提升。
Abstract
The existing recommendation methods mostly adopt the interactive behavior of users and items, such as purchase records or ratings, to complete recommendation. To avoid the sparse interactions which affect the accuracy of the recommendation results, this paper proposes a recommendation method that combining tag and knowledge graph. The tag with rich content and inherited semantic information can reflect the user’s subjective evaluation for items, and it can play a key role in recommendation. The knowledge graph with a large number of entities which can provide more effective features for items. In addition, this paper also design a hybrid attention model that combines attention and self-attention to assign hybrid attention weights to item features based on tags and entities. Experiments on MovieLens and Last. FM datasets indicate an improved performance of the proposed model compared with other recommendation algorithms.
关键词
标签 /
知识图谱 /
推荐系统 /
卷积神经网络 /
注意力
{{custom_keyword}} /
Key words
tag /
knowledge graph /
recommendation system /
CNN /
attention
{{custom_keyword}} /
{{custom_sec.title}}
{{custom_sec.title}}
{{custom_sec.content}}
参考文献
[1] 李宇琦, 陈维政, 闫宏飞,等. 基于网络表示学习的个性化商品推荐[J]. 计算机学报, 2019,(8): 1767-1778.
[2] Shen C L, Yang D Q, Xiao Y H. A deep recommendation model incorporating adaptive knowledge-based representations[C]//Proceedings of the International Conference on Database Systems for Advanced Applications. Springer, Cham, 2019:481-486.
[3] Jiang J Y, Yang D Q, Xiao Y H, et al. Convolutional gaussian embeddings for personalized recommendation with uncertainty[C]//Proceedings of the 28th International Joint Conference on Artificial Intelligence IJCAI-19, 2019.
[4] Hofmann T. Latent semantic models for collaborative filtering[J]. ACM Transactions on Information Systems, 2004, (2): 89-115.
[5] Lin J, Sugiyama K, Kan M Y, et al. Addressing cold-start in app recommendation[C]//Proceedings of the 36th International ACM SIGIR Conference. ACM, 2013: 283-292.
[6] Ivan C, Ro B, Vallet D. Content-based recommendation in social tagging systems[C]//Proceedings of the ACM Conference on Recommender Systems, 2010: 237-240.
[7] Tso-sutter K H L, Marinho L B, Schmidt-Thieme L. Tag-aware recommender systems by fusion of collaborative filtering algorithms[C]//Proceedings of the ACM Symposium on Applied Computing, Fortaleza, Ceara, Brazil, March, 2008: 16-20.
[8] Zhang Z K, Zhou T, Zhang Y C.Tag-aware recommender systems: a state-of-the-art survey[J]. Journal of Computer Science and Technology, 2012, 26(5): 767-777.
[9] Deng Z H, Huang L, Wang C D. A unified framework of representation learning and matching function learning in recommender system.[J].Association for the Advancement of Artificial Intelligence, 2019(33):61-68.
[10] Yuan F J, Karatzoglou A, Arapakis I, et al. A simple convolutional generative network for next item recommendation[C]//Proceedings of 12th ACM Internation Conference on Web Serch and Data Mining, Australia. 2019: 582-590.
[11] Zhao J K, Liu Z, Chen H M, et al. Hybrid recommendation algorithms based on convmf deep learning model[C]//Proceedings of the International Conference on Wireless Communication, Network and Multimedia Engineering, 2019: 159-162.
[12] Yang D Q, Chen L H, Liang J Q, et al. Social tag embedding for the recommendation with sparse user-item interactions[C]//Proceedings of ACM International Conference on Advances in Social Networks Analysis and Mining. Barcelona, Spain, 2018: 127-134.
[13] 孔欣欣, 苏本昌, 王宏志,等. 基于标签权重评分的推荐模型及算法研究[J]. 计算机学报, 2017, 6(40), 1440-1452.
[14] 王瑜, 武延军, 吴敬征,等. 基于异构网络面向多标签系统的推荐模型研究[J]. 软件学报, 2017, 28(10), 2611-2624.
[15] 闫俊, 刘文飞, 林鸿飞. 基于标签混合语义空间的音乐推荐方法研究[J]. 中文信息学报, 2014, 28(4), 117-122.
[16] Liu Q, Li Y, Duan H, et al. Knowledge graph construction techniques[J]. Journal of Computer Research and Development, 2016, 53(3): 582-600.
[17] Antonio, Moreno, Aida, et al.igTur/E-Destination: ontology-based personalized recommendation of tourism and leisure activitie[J]. Engineering Applications of Artificial Intelligence, 2013: 633-651.
[18] Passant A. dbrec-music recommendations using dbpedia[C]//Proceedings of the 9th International Semantic Web Conference on the Semantic Web, 2010(2): 209-224.
[19] Zhao H, Yao Q M, Li J D, et al. Meta-graph based recommendation fusion over heterogeneous information networks[C]//Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Halifax, Canada, 2017:635-644.
[20] Ding Z H, Bin S, Sun G H. Recommendation with heterogeneous information networks based on meta-graph[C]//Proceedings of the International Conference on Artificial Intelligence and Security, 2019:379-390.
[21] Wang H W, Zhang F Z, Xie X, et al. DKN: Deep knowledge-aware network for news recommendation[C]//Proceedings of the International World Wide Web Conferences Steering Committee, 2018: 1835-1844.
[22] 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, 2018:417-426.
[23] Wang H W, Zhang F Z, Zhao M. Multi-task feature learning for knowledge graph enhanced recommendation[C]//Proceedings of Web Conference, 2019: 2000-2010.
[24] Vaswani A, Shazeer N, Parmar J, et al. Attention is all you need[C]//Proceedings of the Conference on Neural Information Processing Systems. Long Beach, CA, USA, 2017:6000-6010.
[25] Zhou G R, Song C R, Zhu X Q, et al. Deep interest network for click-through rate prediction[C]//Proceedings of the Conference on Knowledge Discovery and Data Mining, 2018: 1059-1068.
[26] Yuan W W, Peng D L, Wu S H, et al. Hybrid recommendation algorithm supported by self-attention mechanism[J]. Journal of Chinese Computer Systems, 2019(40): 1437-1441.
[27] Harper F M, Konstan J A. The movie lens datasets: history and context[M]. ACM, 2015,5(4):1-19.
[28] Kim D, Park C, Oh J, et al. Convolutional matrix factorization for document context-aware recommendation[C]//Proceedings of the 10th ACM Conference on Recommender Systems. Boston, MA, USA, 2016:233-240.
[29] Zhang R C, Mao Y I. Movie recommendation viamarkovian factorization of matrix processes[J].IEEE Access, 2019(7): 13189-13199.
[30] He X N, Liao L Z, Hang H W, et al. Neural collaborative filtering[C]//Proceedings of the 26th International World Wide Web Conference. Perth, Australia, 2017:173-182.
{{custom_fnGroup.title_cn}}
脚注
{{custom_fn.content}}
基金
国家自然科学基金(61966025);内蒙古自然科学基金(2019MS06010);内蒙古自治区高等学校科学研究项目(NJZY19011)
{{custom_fund}}
PDF(2370 KB)
