《计算机应用研究》|Application Research of Computers

基于图卷积与外积的协同过滤推荐模型

Collaborative filtering recommendation model based on graph convolution and cross product

免费全文下载 (已被下载 次)  
获取PDF全文
作者 苏静,许天琪,张贤坤,史艳翠,顾淑婷
机构 天津科技大学 人工智能学院,天津 300457
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2021)10-028-3044-05
DOI 10.19734/j.issn.1001-3695.2021.02.0053
摘要 推荐系统帮助用户主动找到满足其偏好的个性化物品并推荐给用户。协同过滤算法是推荐系统中较为经典的算法,但是其会受到数据冷启动和稀疏性的限制,具有可解释性差和模型泛化能力差等缺点。针对其缺点进行研究,通过将原始的评分矩阵以用户—项目二部图的形式作为输入,将图卷积神经网络设计为一种图自编码器的变体,通过迭代的聚合邻居节点信息得到用户和项目的潜在向量表示,并在其基础上结合卷积神经网络,提出了一种基于卷积矩阵分解的推荐算法,提升了模型的可解释性和泛化能力,同时融合辅助信息也解决了数据的稀疏性问题,并使推荐的性能分别得到了1.4%和1.7%的提升。为今后在基于图神经网络的推荐方向上提供了一种新的思路。
关键词 推荐系统; 协同过滤; 图神经网络; 卷积神经网络; 矩阵分解
基金项目 天津市自然科学基金资助项目(19JCYBJC15300)
天津市教委项目(2018KJ105)
本文URL http://www.arocmag.com/article/01-2021-10-028.html
英文标题 Collaborative filtering recommendation model based on graph convolution and cross product
作者英文名 Su Jing, Xu Tianqi, Zhang Xiankun, Shi Yancui, Gu Shuting
机构英文名 School of Artificial Intelligence,Tianjin University of Science & Technology,Tianjin 300457,China
英文摘要 The function of recommendation system is to help users actively finding personalized items that meet theirs preferences and recommend them to users. Collaborative filtering algorithm is a classic algorithm in recommender system, but it is limited by cold start of data and sparsity and has disadvantages such as poor interpretability and poor model generalization ability. This paper studied its shortcomings. By taking the original score matrix in the form of user-project bipartite graph as input, designing the figure convolution neural network as a variant of graph autoencoder, which was obtained by the latent vector of user and item by iteratively aggregating neighbor node information, and combining CNN, this paper proposed a recommendation algorithm based on convolution matrix decomposition to improve the interpretability of the model and generalization ability. And also solved the auxiliary information fusion the data sparseness, and made recommendation performance improved by 1.4% and 1.7%. It provides a new idea for recommendation direction based on graph neural network in the future.
英文关键词 recommended system; collaborative filtering; graph neural network(GNN); convolutional neural network(CNN); matrix factorization
参考文献 查看稿件参考文献
 
收稿日期 2021/2/7
修回日期 2021/4/3
页码 3044-3048
中图分类号 TP399
文献标志码 A