NEXT:a neural network framework for next POI recommendation

作     者：Zhiqian ZHANG Chenliang LI Zhiyong WU Aixin SUN Dengpan YE Xiangyang LUO Zhiqian ZHANG;Chenliang LI;Zhiyong WU;Aixin SUN;Dengpan YE;Xiangyang LUO

作者机构：Key Laboratory of Aerospace Information Security and Trusted ComputingMinistry of EducationSchool of Cyber Science and EngineeringWuhan UniversityWuhan 430072China Department of Computer ScienceThe University of Hong KongPokfulam RoadHong Kong 999077China School of Computer Science and EngineeringNanyang Technological UniversitySingapore 639798Singapore State Key Lab of Mathematical Engineering and Advanced ComputingZhengzhou 450001China 

出 版 物：《Frontiers of Computer Science》 (中国计算机科学前沿（英文版）)

年 卷 期：2020年第14卷第2期

页      面：314-333页

核心收录：

学科分类：0810[工学-信息与通信工程] 12[管理学] 1201[管理学-管理科学与工程(可授管理学、工学学位)] 0808[工学-电气工程] 081104[工学-模式识别与智能系统] 08[工学] 0835[工学-软件工程] 0701[理学-数学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：the National Natural Science Foundation of China(Grant Nos.61872278,61502344,1636219,U1636101) Natural Science Foundation of Hubei Province(2017CFB502) Academic Team Building Plan for Young Scholars from Wuhan University(Whu2016012) Singapore Ministry of Education Academic Research Fund Tier 2(MOE2014-T2-2-066) 

主　　题：POI neural networks POI recommendation 

摘      要：The task of next POI recommendations has been studied extensively in recent ***,developing a unified recommendation framework to incorporate multiple factors associated with both POIs and users remains challenging,because of the heterogeneity nature of these ***,effective mechanisms to smoothly handle cold-start cases are also a difficult *** by the recent success of neural networks in many areas,in this paper,we propose a simple yet effective neural network framework,named NEXT,for next POI *** is a unified framework to learn the hidden intent regarding user s next move,by incorporating different factors in a unified ***,in NEXT,we incorporate meta-data information,e.g.,user friendship and textual descriptions of POIs,and two kinds of temporal contexts(i.e.,time interval and visit time).To leverage sequential relations and geographical influence,we propose to adopt DeepWalk,a network representation learning technique,to encode such *** evaluate the effectiveness of NEXT against other state-of-the-art alternatives and neural networks based *** results on three publicly available datasets demonstrate that NEXT significantly outperforms baselines in real-time next POI *** experiments show inherent ability of NEXT in handling cold-start.