基于知识图谱用户偏好传播的实体推荐模型  

Entity recommendation model based on user preference propagation of knowledge graph

作　　者：刘勤 陈世平[1] 霍欢[1,2,3] Liu Qin;Chen Shiping;Huo Huan(School of Optical-Electrical&Computer Engineering,University of Shanghai for Science&Technology,Shanghai 200093,China;Shanghai Key Laboratory of Data Science,Fudan University,Shanghai 201203,China;School of Computer Science,University of Technology Sydney,Sydney NSW2007,Australia)

机构地区：[1]上海理工大学光电信息与计算机工程学院,上海200093 [2]复旦大学上海市数据科学重点实验室,上海201203 [3]悉尼科技大学计算机科学学院,悉尼NSW2007

出　　处：《计算机应用研究》2020年第10期2926-2931,共6页Application Research of Computers

基　　金：国家自然科学基金资助项目(61472256,61170277,61003031);上海重点科技攻关项目(14511107902);上海市工程中心建设项目(GCZX14014);上海市一流学科建设项目(S1201YLXK,XTKX2012);上海市数据科学重点实验室开放课题资助项目(201609060003);沪江基金资助项目(A14006);沪江基金研究基地专项资助项目(C14001)。

摘　　要：将知识图谱作为辅助信息引入到推荐系统中,可以有效地增强推荐系统的学习能力,提高推荐系统的精准度和用户满意度。针对知识图谱上的偏好传播问题,提出一种基于知识图谱用户偏好传播的实体推荐模型,目的是在传播偏好的同时兼顾传播强度,提高推荐效果。通过提取不同特定属性的基本特征控制用户偏好在知识图谱上的传播强度,然后根据每个用户的历史偏好传播强度在知识图谱上迭代计算,得到用户—项目对的偏好传播模型,最终通过排序学习进行top N推荐。最后,在三个不同类型数据集上的对比实验验证该模型算法的有效性。实验证明,在偏好传播的同时控制传播强度可以很好地提升推荐系统的准确率、召回率以及F 1值,同时具有很强的灵活性和可解释性。Knowledge graph is a useful tool when introducing it into the recommendation system as auxiliary information.It can effectively enhance the learning ability of the recommendation system,improving the system’s accuracy and user’s satisfaction.Aiming at the problem of the preference propagation on the knowledge graph,this paper proposed an entity recommendation model based on the user preference propagation of the knowledge graph.This model took the transmission intensity into consideration,while propagated the preference at the same time,thus improved the final effect of recommendation.It controlled the propagation intensity of user’s preference on the knowledge graph by extracting the basic characteristics of different speci-fic attributes,and iteratively calculated the historical preference data of each user to obtain the preference propagation model of user-item pair.Later,employing the sorting learning algorithm to get the top N recommendations.In the end,comparison experiments on three different kinds of datasets verified the effectiveness of the proposed model.This study shows that controlling the propagation intensity during the propagating process can significantly improve the accuracy rate,recall rate,as well as the F 1 value of the recommendation system,and this method also has strong flexibility and interpretability.

关 键 词：知识图谱 偏好传播 top N推荐 特征提取 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]