MKR模型在电影推荐系统中的应用研究
Research on the Application of MKR Model in Movie Recommendation System
摘要: 针对电影推荐系统中推荐结果的准确性和可解释性不高的问题，研究了基于多任务特征学习的知识图谱增强推荐(multi-task learning for knowledge graph enhanced recommendation, MKR)。通过构建知识图谱，将其作为辅助信息构建了MKR模型，并将其应用到电影推荐系统中。采用预测用户满意度评分的方法根据评分结果来判定用户对电影的喜好程度，并将合适的电影类型推荐给用户。最后将MKR模型与几种常见的推荐模型进行比较，使用不同的评价指标进行预测，并在top-K场景中比较了不同K值下各个模型的推荐性能。实验结果表明，MKR模型在电影推荐系统中有良好的表现，在准确率和推荐结果上均优于其他模型，显著提升了推荐的性能。
Abstract: Aiming at the low accuracy and interpretability of recommendation results in movie recommen-dation system, a multi task learning for knowledge graph enhanced recommendation (MKR) based on multi task feature learning is studied. By constructing a knowledge graph, and using it as auxil-iary information to construct a MKR model, and applied to the movie recommendation system. Using the method of predicting user satisfaction score, according to the score results to determine the user’s preference for movies, and recommend the appropriate movie types to users. Finally, MKR model is compared with several common recommendation models, and different evaluation indexes are used for prediction. The recommendation performance of each model under different K values is compared in the Top-k scenario. The experimental results show that MKR model has a good performance in the movie recommendation system, and is superior to other models in accu-racy and recommendation results, which significantly improves the performance of the recom-mendation.
文章引用：操淑敏, 秦学, 鲜翠琼. MKR模型在电影推荐系统中的应用研究[J]. 软件工程与应用, 2021, 10(2): 104-112. https://doi.org/10.12677/SEA.2021.102013

参考文献

[1] Adomavicius, G. and Tuzhilin, A. (2005) Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions. IEEE Transactions on Knowledge and Data Engineering, 17, 734-749. [Google Scholar] [CrossRef] 
[2] Gao, Y., Li, Y.F., Lin, Y., Gao, H. and Khan, L. (2020) Deep Learn-ing on Knowledge Graph for Recommender System: A Survey. Information Retrieval, arXiv:2004.00387.
[3] Zhao, H., Yao, Q.M., Li, J.D., Song, Y.Q. and Lee, D.L. (2017) Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks. Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 635-644. [Google Scholar] [CrossRef] 
[4] 宋瑞平. 混合推荐算法的研究[D]: [硕士学位论文]. 兰州: 兰州大学, 2014.
[5] Koren, Y., Bell, R. and Volinsky, C. (2009) Matrix Factorization Techniques for Recommender Systems. Computer, 42, 30-37. [Google Scholar] [CrossRef] 
[6] Guo, Q., Zhuang, F., Qin, C., et al. (2020) A Survey on Knowledge Graph-Based Recommender Systems. Scientia Sinica Informationis, 50, 937. [Google Scholar] [CrossRef] 
[7] Wang, H., Zhang, F., Zhao, M., et al. (2019) Multi-Task Feature Learning for Knowledge Graph Enhanced Recommendation. The World Wide Web Conference, 2000-2010. [Google Scholar] [CrossRef] 
[8] 涂存超, 杨成, 刘知远, 等. 网络表示学习综述[J]. 中国科学: 信息科学, 2017, 47(8): 980-996.
[9] Rendle, S. (2012) Factorization Machines with libFM. ACM Transactions on In-telligent Systems and Technology (TIST), 3. [Google Scholar] [CrossRef] 
[10] Xiao, Y., Xiang, R., Sun, Y., et al. (2014) Personalized Entity Recommendation: a Heterogeneous Information Network Approach. Pro-ceedings of the 7th ACM International Conference on Web Search and Data Mining.
[11] Wang, H., Zhang, F., Xie, X., et al. (2018) DKN: Deep Knowledge-Aware Network for News Recommendation. Proceedings of the 2018 World Wide Web Conference on World Wide Web. International World Wide Web Conferences Steering Committee, 1835-1844. [Google Scholar] [CrossRef] 
[12] Zhang, F.Z., Yuan, N.J., Lian, D.F., Xie, X. and Ma, W.Y. (2016) Collaborative Knowledge Base Embedding for Recommender Systems. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 353-362. [Google Scholar] [CrossRef] 
[13] Cheng, H.T., Koc, L., Harmsen, J., et al. (2016) Wide & Deep Learning for Recommender Systems. Wide & Deep Learning for Recommender Systems.

为你推荐