基于深度学习的多交互混合推荐模型  

Multi-interaction Hybrid Recommendation Model Based on Deep Learning

作　　者：李同欢 唐雁 刘冰[1,2] LI Tonghuan;TANG Yan;LIU Bing(School of Computer and Information Science,Southwest University,Chongqing 400715,China;Dazhou Vocational and Technical College,Dazhou,Sichuan 635001,China)

机构地区：[1]西南大学计算机与信息科学学院,重庆400715 [2]达州职业技术学院,四川达州635001

出　　处：《计算机工程与应用》2019年第1期135-141,共7页Computer Engineering and Applications

基　　金：四川省教育厅自然科学重点项目(No.18ZA0217);中央高校基本科研业务费专项资金(No.XDJK2015C110);重庆市2017年度中小学创新人才工程项目(No.CY170217);教育部"春晖计划"资助项目(No.Z2011149)

摘　　要：传统的推荐系统中,基于矩阵分解的协同过滤方法只考虑单一的评分信息,而且作为浅层模型无法学习到更深层次的特征信息。提出一种基于深度学习的多交互混合推荐模型,通过深度学习模型融合更多的辅助信息作为输入,能够缓解数据的稀疏性问题;利用多层交互的非线性网络结构去学习更抽象、稠密的深层次特征表示;通过对用户和项目的隐表示进行多次内积交互获得不同层次的特征表示结果;聚合所有的交互结果进行预测。在Movieles latest 100K数据集上进行实验,采用RMSE指标进行评估,结果表明所提模型在推荐效果上有所提升。In the traditional recommendation systems, the approach of matrix factorization collaborative filtering only just considers the single information of rating, as a shallow model, it can hardly learn deeper feature information. This paper proposes a multi-interaction deep matrix factorization model based on auxiliary information, firstly through deep learning model and merge more auxiliary information as input, effectively alleviates the problem of data sparsity. Then, the structure of multi-interactive non-linear network is leveraged to learn the deep feature representation of more abstract and dense;through inner product interactions on the latent features of users and items repeatedly, it obtains the different layers of feature representation results; finally it aggregates all the interaction results to predict. The experiment results on the Movielens latest 100 K dataset show that the proposed model is over the state-of-the-art methods in RMSE.

关 键 词：协同过滤 深度学习 辅助信息 多层交互 神经网络 推荐系统 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]