基于知识图谱融入注意力机制商品推荐的可解释性方法
An Interpretability Method for Commodity Recommendation Based on Knowledge Graph Incorporating Attention Mechanism
DOI: 10.12677/CSA.2022.126150, PDF,  被引量   
作者: 陆倩平, 王红斌：昆明理工大学信息工程与自动化学院，云南 昆明;昆明理工大学云南省人工智能重点实验室，云南 昆明
关键词: 知识图谱；可解释推荐；注意力机制；Knowledge Graph； Explainable Recommendation； Attention Mechanism
摘要: 近年来，知识图谱与推荐系统相结合已经被证明是提高推荐准确率以及为推荐带来可解释性的有效方法，知识图谱中项目之间的连接为用户–项目交互提供了丰富的信息。但现有利用知识图谱的推荐算法中没有考虑到实体之间的相关性。针对这一问题，我们提出了基于知识图谱融入注意力机制商品推荐的可解释性方法。该方法利用注意力机制来区分出邻居节点的重要性，并通过该重要性将实体的邻居节点嵌入实体中，来获取更有效的用户实体表示，提高了推荐的准确性也为推荐项目带来了可解释性。我们将所提出的方法应用于Clothing和Cell_Phones两个数据集，实验结果表明，本文提出的方法通过注意力机制在一定程度上解决了在探索用户偏好时实体间的不相关性问题。
Abstract: In recent years, the combination of knowledge graphs and recommender systems has been proven to be an effective method to improve recommendation accuracy and bring interpretability to recommendations, and the connections between items in knowledge graphs provide rich information for user-item interactions. However, the existing recommendation algorithms using knowledge graphs do not consider the correlation between entities. In response to this problem, we propose an interpretability method for product recommendation based on knowledge graph with attention mechanism. This method uses the attention mechanism to distinguish the importance of neighbor nodes, and embeds the neighbor nodes of the entity into the entity through the importance to obtain a more effective user entity representation, which improves the accuracy of the recommendation and brings interpretability to the recommended items. We apply the proposed method to the Clothing and Cell_Phones datasets, and the experimental results show that the method proposed in this paper solves the problem of irrelevance between entities when exploring user preferences through the attention mechanism to a certain extent.
文章引用：陆倩平, 王红斌. 基于知识图谱融入注意力机制商品推荐的可解释性方法[J]. 计算机科学与应用, 2022, 12(6): 1506-1517. https://doi.org/10.12677/CSA.2022.126150

参考文献

[1] 顾犇. 信息过载问题及其研究[J]. 中国图书馆学报, 2000, 26(5): 42-45+76.
[2] Zhao, H., Yao, Q., Li, J., Song, Y. and Lee, D.L. (2017) Meta-Graph Based Recommendation Fusion over Heterogeneous Information Networks. Proceed-ings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Halifax, 13-17 August 2017, 635-644. [Google Scholar] [CrossRef] 
[3] Yi, F., Jiang, B. and Wu, J. (2020) Hetero-geneous Information Network Embedding for Mention Recommendation. IEEE Access, 8, 91394-91404. [Google Scholar] [CrossRef] 
[4] Rendle, S. (2010) Factorization Machines. 2010 IEEE Inter-national Conference on Data Mining, Sydney, 13-17 December 2010, 995-1000. [Google Scholar] [CrossRef] 
[5] Zhang, Y., Ai, Q., Chen, X. and Wang, P. (2018) Learning over Knowledge-Base Embeddings for Recommendation. Algorithms, 11, Article No. 137. [Google Scholar] [CrossRef] 
[6] Dadoun, A., Troncy, R., Ratier, O. and Petitti, R. (2019) Location Embed-dings for Next Trip Recommendation. Companion Proceedings of the 2019 World Wide Web Conference, San Francisco, 13-17 May 2019, 896-903. [Google Scholar] [CrossRef] 
[7] Wang, H., Zhang, F., Wang, J., Zhao, M., Li, W., Xie, X., et al. (2018) Ripplenet: Propagating User Preferences on the Knowledge Graph for Recommender Systems. Proceedings of the 27th ACM International Conference on Information and Knowledge Management, Torino, 22-26 October 2018, 417-426. [Google Scholar] [CrossRef] 
[8] Tang, X., Wang, T., Yang, H. and Song, H. (2019) AKUPM: At-tention-Enhanced Knowledge-Aware User Preference Model for Recommendation. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, 4-8 July 2019, 1891-1899. [Google Scholar] [CrossRef] 
[9] Kipf, T.N. and Welling, M. (2016) Semi-Supervised Classification with Graph Convolutional Networks. arXiv preprint arXiv:1609.02907.
[10] Wang, H., Zhao, M., Xie, X., Li, W. and Guo, M. (2019) Knowledge Graph Convolutional Networks for Recommender Systems. The World Wide Web Confer-ence, San Francisco, 13-17 May 2019, 3307-3313. [Google Scholar] [CrossRef] 
[11] Veličković, P., Cucurull, G., Casanova, A., Romero, A., Lio, P. and Bengio, Y. (2017) Graph Attention Networks. arXiv preprint arXiv:1710.10903.
[12] Wang, X., He, X., Cao, Y., Liu, M. and Chua, T. (2019) Kgat: Knowledge Graph Attention Network for Recommendation. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, 4-8 July 2019, 950-958. [Google Scholar] [CrossRef] 
[13] Sha, X., Sun, Z. and Zhang, J. (2021) Hierarchical Attentive Knowledge Graph Embedding for Personalized Recommendation. Electronic Commerce Research and Applications, 48, Article ID: 101071. [Google Scholar] [CrossRef] 
[14] Nathani, D., Chauhan, J., Sharma, C. and Kaul, M. (2019) Learning Attention-Based Embeddings for Relation Prediction in Knowledge Graphs. Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, July 2019, 1710-4723. [Google Scholar] [CrossRef] 
[15] Devlin, J., Chang, M.-W., Lee, K. and Toutanova, K. (2018) BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding. arXiv:1810.04805.
[16] Rendle, S., Freudenthaler, C., Gantner, Z. and Schmidt-Thieme, L. (2012) BPR: Bayesian Personalized Ranking from Implicit Feed-back. arXiv preprint arXiv:1205.2618.
[17] Wang, H., Zhang, F., Xie, X. and Guo, M. (2018) DKN: Deep Knowledge-Aware Network for News Recommendation. Proceedings of the 2018 World Wide Web Conference, Lyon, 23-27 April 2018, 1835-1844. [Google Scholar] [CrossRef] 
[18] Ma, W., Zhang, M., Cao, Y., Jin, W., Wang, C. and Liu, Y. (2019) Jointly Learning Explainable Rules for Recommendation with Knowledge Graph. Proceedings of the 2019 World Wide Web Conference, San Francisco, 3-17 May 2019, 1210-1221. [Google Scholar] [CrossRef]