KNCR: Knowledge-Aware Neural Collaborative Ranking for Recommender Systems
KNCR: Knowledge-Aware Neural Collaborative Ranking for Recommender Systems
复制标题
DOI：
10.1109/dasc-picom-cbdcom-cyberscitech49142.2020.00066
复制
发表时间：
2020-08
期刊：
影响因子：
--
通讯作者：
Chen Huang;Zhongyuan Gan;Feng Ye;Pan Wang;Moxuan Zhang
中科院分区：
文献类型：
--
作者：
Chen Huang;Zhongyuan Gan;Feng Ye;Pan Wang;Moxuan Zhang
推荐系统旨在生成用户可能感兴趣的物品的个性化排序列表。随着深度学习在计算机视觉和语音识别领域取得空前的成功，如何合理地将深度学习引入到推荐系统中也引起了研究人员的思考。知识图谱作为一个新的研究热点，蕴含着丰富的实体语义关联的新辅助信息。研究人员发现，当知识图谱被引入到推荐系统中时，可以减少数据稀疏性和冷启动问题，是神经网络在推荐系统中的好助手。在传统推荐系统中，由于依赖矩阵分解和协同过滤算法进行推荐，因此不可避免地会存在冷启动和数据稀疏性问题。数据稀疏问题往往是指大型电商等平台中用户和商品数量较多，但在得到的用户-商品矩阵中，平均与项目交互的用户数量较少，会导致用户-商品矩阵稀疏。冷启动问题是指在没有大量用户数据的情况下如何对新用户进行个性化推荐。数据的稀疏性最终会导致无法捕捉不同用户和不同物品之间的关系，从而降低推荐系统的准确性。隐式反馈作为一种隐式表达，可以通过多种方式获取用户的偏好，而不是局限于表达偏好的展示，从而丰富用户-项目矩阵，缓解数据稀疏问题。神经网络可以从更高的维度分析事物之间的关系，改善数据的稀疏性。知识图谱包含了现实世界中事物的事实关系，相当于为数据提供了额外的信息维度，从而在一定程度上解决了冷启动问题。本文提出一种基于知识图谱隐式反馈和表示学习结合神经网络（KNCR）的增强协同过滤推荐算法。 KNCR可以弥合传统协同过滤算法未考虑的项目之间的内在关系，有效解决评分矩阵稀疏和冷启动问题。现实世界公共数据集的实验结果表明，KNCR 可以提高个性化推荐的性能。
The recommendation system is designed to generate a personalized sorting list of items that users may be interested in. With the unprecedented success of deep learning in the field of Computer Vision and Voice recognition, how to reasonably introduce deep learning into the recommendation system has also aroused the thinking of researchers. Knowledge graph, as a new research hotspot, contains abundant new auxiliary information of entity semantic association. The researchers found that when the knowledge map is introduced into the recommendation system, it can reduce the data sparsity and cold start problem, and it is a good assistant for neural network in the recommendation system.In the traditional recommendation system, because it relies on the matrix decomposition and collaborative filtering algorithm for recommendation, there will inevitably be problems of cold start and data sparsity. The problem of data sparsity often refers to the large number of users and items in platforms such as large-scale e-commerce, but in the user-item matrix obtained, the average number of users interacting with the project is small, which will cause the user-item matrix to be sparse. The cold start problem refers to how to make personalized recommendation for new users without a large number of user data. The sparsity of data will eventually lead to the inability to capture the relationship between different users and different items, thus reducing the accuracy of the recommendation system. As an implicit expression, implicit feedback can get users’ preferences in many ways, rather than limited to the display of expression preferences, so as to enrich the user-item matrix and alleviate the problem of data sparsity. Neural network can analyze the relationship between things from a higher dimension, and improve the data sparsity. The knowledge graph contains the fact relationship of a thing in the real world, which is equivalent to providing additional information dimension for the data, so as to solve the cold start problem to a certain extent.In this paper, we propose an enhanced collaborative filtering recommendation algorithm based on implicit feedback and representation learning of the knowledge graph combined with neural network (KNCR). KNCR can bridge intrinsic relationship between items that are not considered by the traditional collaborative filtering algorithm, and effectively solve the problems of sparse scoring matrix and cold start. The experimental results from the real-world public dataset demonstrate that KNCR can improve the performance of personalized recommendations.