广西师范大学学报（自然科学版） ›› 2023, Vol. 41 ›› Issue (1): 87-101.doi: 10.16088/j.issn.1001-6600.2022021104

• 研究论文 • 上一篇    下一篇

POI推荐中的多源数据融合和隐私保护方法

王利娥1,2, 王艺汇1, 李先贤1,2*   

  1. 1.广西师范大学 计算机科学与工程学院, 广西 桂林 541004;
    2.广西多源信息挖掘与安全重点实验室(广西师范大学), 广西 桂林 541004
  • 收稿日期:2022-02-11 修回日期:2022-07-27 出版日期:2023-01-25 发布日期:2023-03-07
  • 通讯作者: 李先贤(1969—),男,广西桂林人,广西师范大学教授,博导。E-mail:lixx@gxnu.edu.cn
  • 基金资助:
    国家自然科学基金(U21A20474, 62262003); 广西科技计划项目(桂科AA22067070, 桂科AD21220114); 广西自然科学基金(2020GXNSFAA297075); “八桂学者”工程专项; 广西大数据智能与应用人才小高地项目; 广西应用数学中心(广西师范大学)项目; 广西区域多源信息集成与智能处理协同创新中心项目; 广西多源信息挖掘与安全重点实验室系统性研究课题基金(19-A-02-02)

A Multi-source Data Fusion and Privacy Protection Method of POI Recommendation

WANG Li’e1,2, WANG Yihui1, LI Xianxian1,2*   

  1. 1. School of Computer Science and Engineering, Guangxi Normal University, Guilin Guangxi 541004, China;
    2. Guangxi Key Lab of Multi-source Information Mining and Security (Guangxi Normal University), Guilin Guangxi 541004, China
  • Received:2022-02-11 Revised:2022-07-27 Online:2023-01-25 Published:2023-03-07

PDF (PC)

424

摘要： 随着移动定位技术的发展,兴趣点(point-of-interest,POI)推荐技术已经成为推荐领域中的研究热点之一。受限于用户的签到能力,POI推荐中存在严重的数据稀疏问题,而融合多源数据的POI推荐又面临着多重隐私挑战。涉及多来源的数据具有多样性、多元性等隐私特征,隐私泄漏机理更为复杂多样,其隐私保护问题更具挑战性。为此,本文提出一种基于注意力机制和隐私保护的多源POI推荐——MultiAM&PP_POI,能够在保护隐私的前提下有效提高POI推荐的精度。为了实现数据的有效融合,本文采用LDA主题模型提取用户在不同领域中的潜在特征,并利用注意力机制来自适应地训练,学习不同领域的潜在特征对POI推荐结果的影响,同时利用多层感知器来实现不同领域潜在特征的迁移。针对多源POI推荐中的隐私问题,本文利用联邦学习框架将原始数据保存在本地,各参与方只需交互加密后的潜在特征,并改进了注意力机制和多层感知器,使其可在密文状态下完成训练,以保护用户隐私的安全。最后通过实验验证,本文模型能够在保护用户隐私前提下,相比单源联邦模型和其他跨域模型,在推荐精度方面分别提升3.05和4.42个百分点。

关键词: 兴趣点推荐, 多源融合, 注意力机制, 隐私保护, 联邦学习

Abstract: With the development of mobile location technology, the point-of-Interest (POI) recommendation technology has become one of the research hotspots in the field of recommendation system. Limited by the check-in ability of users, there is a serious data sparsity problem in POI recommendation, what’s more, POI recommendations with combining multiple sources of data is faced with the challenges of multiple privacy. Because data from multiple sources have privacy characteristics of diversity and pluralism, the mechanism of privacy leakage is more complex and diverse, which makes the privacy problem more challenging. To solve this problem, a multi-source POI recommendation with attention mechanism and privacy protection, MultiAM&PP_POI, is proposed in this paper. In order to achieve effective data fusion, LDA topic model to extract users’ potential features in different domains is used in this paper, and an attention mechanism is used to adaptively train the influence of potential features in different domains on POI recommendation results. Meanwhile, multi-layer perceptron method is used to realize the transfer of potential features in different domains. As for the privacy problem in the recommendation of multi-source POI, the federated learning framework is used to save the original data locally without uploading, so each participant only needs to interact with the potential features after encryption. The attention mechanism is improved so multi-layer perceptron can finish training in ciphertext state to protect the security of user privacy. Finally, through experimental verification, the proposed model can effectively improve the recommendation accuracy by 3.05% and 4.42% compared with the single-source federated model and other cross-domain models on the premise of protecting users’ privacy.

Key words: point-of-interest recommendation, multi-source fusion, attention mechanism, privacy protection, federated learning

中图分类号: 

  • TP391
[1] ZHANG C Y,WANG K. POI recommendation through cross-region collaborative filtering[J]. Knowledge and Information Systems,2016,46(2):369-387,DOI:10.1007/s10115-015-0825-8.
[2]LI X,JIANG M M,HONG H T,et al. A time-aware personalized point-of-interest recommendation via high-order tensor factorization[J]. ACM Transactions on Information Systems,2017,35(4):31. DOI:10.1145/3057283.
[3]CHANG B,KOH Y,PARK D,et al. Content-aware successive point-of-interest recommendation[C]// Proceedings of the 2020 SIAM International Conference on Data Mining(SDM). Philadelphia,PA:Society for Industrial and Applied Mathematics,2020:100-108. DOI:10.1137/1.9781611976236.12.
[4]XU Y N,XU L,HUANG L,et al. Social and content based collaborative filtering for point-of-interest recommendations[C]// Neural Information Processing:LNTCS Volume 10638. Cham:Springer International Publishing AG,2017:46-56. DOI:10.1007/978-3-319-70139-4_5.
[5]XU Y Y,LI X F,LI J,et al. SSSER:Spatiotemporal sequential and social embedding bank for successive point-of-interest recommendation[J]. IEEE Access,2019,7:156804-156823. DOI:10.1109/ACCESS.2019.2950061.
[6]夏英,张金凤. 融合社交关系和局部地理因素的兴趣点推荐[J]. 计算机工程与应用,2021,57(15):133-139. DOI:10.3778/j.issn.1002-8331.2007-0172.
[7]王启正. 隐私保护下的数据处理[D]. 济南:山东师范大学,2019.
[8]LI L C,LU R X,CHOO K K R,et al. Privacy-preserving-outsourced association rule mining on vertically partitioned databases[J]. IEEE Transactions on Information Forensics and Security,2016,11(8):1847-1861. DOI:10.1109/TIFS.2016.2561241.
[9]PAN Z G,CUI L,WU X Y,et al. Deep potential geo-social relationship mining for point-of-interest recommendation[J]. IEEE Access,2019,7:99496-99507. DOI:10.1109/ACCESS.2019.2930311.
[10]STEFANCOVA E,SRBA I. POI recommendation based on locality-specific seasonality and long-term trends[C]// SOFSEM 2020:Theory and Practice of Computer Science:LNCS Volume 12011. Cham:Springer Nature Switzerland AG,2020:338-349. DOI:10.1007/978-3-030-38919-2_28.
[11]叶继华,杨思渝,左家莉,等. 基于时空上下文信息的POI推荐模型研究[J]. 电子与信息学报,2021,43(12):3546-3553. DOI:10.11999/JEIT200368.
[12]陈炯,张虎,曹付元. 融合多因素的兴趣点协同推荐方法研究[J]. 计算机科学,2019,46(10):77-83. DOI:10.11896/jsjkx.180901757.
[13]DA SILVA E D S,LANGSETH H,RAMAMPIARO H. Content-based social recommendation with poisson matrix factorization[C]// Machine Learning and Knowledge Discovery in Databases:LNCS Volume 10534. Cham:Springer International Publishing AG,2017:530-546. DOI:10.1007/978-3-319-71249-9_32.
[14]CHANG B,PARK Y,PARK D,et al. Content-aware hierarchical point-of-interest embedding model for successive POI recommendation[C]// Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence. Stockholm:IJCAI,2018:3301-3307. DOI:10.24963/ijcai.2018/458.
[15]陈劲松,孟祥武,纪威宇,等. 基于多维上下文感知图嵌入模型的兴趣点推荐[J]. 软件学报,2020,31(12):3700-3715. DOI:10.13328/j.cnki.jos.005855.
[16]刘真,王娜娜,王晓东,等. 位置社交网络中谱嵌入增强的兴趣点推荐算法[J]. 通信学报,2020,41(3):197-206. DOI:10.11959/j.issn.1000-436x.2020053.
[17]任星怡,宋美娜,宋俊德. 基于位置社交网络的上下文感知的兴趣点推荐[J]. 计算机学报,2017,40(4):824-841. DOI:10.11897/SP.J.1016.2017.00824.
[18]ZHANG Z Y,LIU Y,ZHANG Z J,et al. Fused matrix factorization with multi-tag,social and geographical influences for POI recommendation[J].World Wide Web,2019,22(3):1135-1150. DOI:10.1007/s11280-018-0579-9.
[19]ZENG J,LI F,HE X,et al. Fused collaborative filtering with user preference,geographical and social Influence for point of interest recommendation[J]. International Journal of Web Services Research,2019,16(4):40-52. DOI:10.4018/ijwsr. 2019100103.
[20]LI D C,GONG Z G,ZHANG D F. A common topic transfer learning model for crossing city POI recommendations[J].IEEE Transactions on Cybernetics,2019,49(12):4282-4295,DOI:10.1109/TCYB.2018.2861897.
[21]DING J T,YU G H,LI Y,et al.Learning from hometown and current city:cross-city POI recommendation via interest drift and transfer learning[J]. Proceedings of the ACM on Interactive,Mobile,Wearable and Ubiquitous Technologies,2019,3(4):131. DOI:10.1145/3369822.
[22]YIN H Z,SUN Y Z,CUI B,et al. LCARS:a location-content-aware recommender system[C]// Proceedings of the 19th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. New York,NY:Association for Computing Machinery,2013:221-229. DOI:10.1145/2487575.2487608.
[23]WEN Y,ZHANG J S,ZENG Q T,et al. Loc2Vec-based cluster-level transition behavior mining for successive POI recommendation[J]. IEEE Access,2019,7:109311-109319. DOI:10.1109/ACCESS.2019.2931075.
[24]郭旦怀,张鸣珂,贾楠,等. 融合深度学习技术的用户兴趣点推荐研究综述[J]. 武汉大学学报(信息科学版),2020,45(12):1890-1902. DOI:10.13203/j.whugis20200334.
[25]LI X X,SUI P P,BAI Y,et al. M-generalization for multipurpose transcational data publication[J]. Frontiers of Computer Science,2018,12(6):1241-1254. DOI:10.1007/s11704-016-6061-x.
[26]WADHWA S,AGRAWAL S,CHAUDHARI H,et al. Data poisoning attacks against differentially private recommender systems[C]// Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York,NY:Association for Computing Machinery,2020:1617-1620. DOI:10.1145/3397271.3401301.
[27]WANG W Q,LIU A,LI Z X,et al. Protecting multi-party privacy in location-aware social point-of-interest recommendation[J].World Wide Web, 2019,22(2):863-883. DOI:10.1007/s11280-018-0550-9.
[28]张青云,张兴,李万杰,等. 基于差分隐私保护的兴趣点推荐算法设计[J]. 计算机应用与软件,2019,36(9):243-248,269. DOI:10.3969/j.issn.1000-386x.2019.09.043.
[29]沈鑫娣,翟东君,张得天,等. 基于LSH的隐私保护POI推荐算法[J]. 计算机工程,2019,45(1):96-102. DOI:10.19678/j.issn.1000-3428.0049731.
[30]CHEN C C,LIU Z Q,ZHAO P L,et al. Privacy preserving point-of-interest recommendation using decentralized matrix factorization[C]// Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence. Palo Alto,CA:AAAI Press,2018:257-264.
[31]彭佳. 隐私保护的兴趣点推荐系统研究[D]. 苏州:苏州大学,2019. DOI:10.27351/d.cnki.gszhu.2019.000828.
[32]XING S N,LIU F A,WANG Q Q,et al. Content-aware point-of-interest recommendation based on convolutional neural network[J]. Applied Intelligence,2019,49(3):858-871. DOI:10.1007/s10489-018-1276-1.
[33]WU S W,ZHANG Y X,GAO C L,et al. GARG:anonymous recommendation of point-of-interest in mobile networks by graph convolution network[J]. Data Science and Engineering,2020,5(4):433-447. DOI:10.1007/s41019-020-00135-z.
[34]GAO H J,TANG J L,HU X,et al. Content-aware point of interest recommendation on location-based social networks[J]. Proceedings of the AAAI Conference on Artificial Intelligence,2015,29(1):1721-1727. DOI:10.1609/aaai.v29i1.9462.
[35]WANG L E,WANG Y H,BAI Y,et al. POI recommendation with federated learning and privacy preserving in cross domain recommendation[C]// IEEE INFOCOM 2021-IEEE Conference on Computer Communications Workshops(INFOCOM WKSHPS). Piscataway,NJ:IEEE,2021:1-6. DOI:10.1109/INFOCOMWKSHPS51825.2021.9484510.
[1] 王宇航, 张灿龙, 李志欣, 王智文. 体现用户意图和风格的图像描述生成[J]. 广西师范大学学报（自然科学版）, 2022, 40(4): 91-103.
[2] 李正光, 陈恒, 林鸿飞. 基于双向语言模型的社交媒体药物不良反应识别[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 40-48.
[3] 万黎明, 张小乾, 刘知贵, 宋林, 周莹, 李理. 基于高效通道注意力的UNet肺结节CT图像分割[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 66-75.
[4] 张萍, 徐巧枝. 基于多感受野与分组混合注意力机制的肺结节分割研究[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 76-87.
[5] 孔亚钰, 卢玉洁, 孙中天, 肖敬先, 侯昊辰, 陈廷伟. 面向强化当前兴趣的图神经网络推荐算法研究[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 151-160.
[6] 吴军, 欧阳艾嘉, 张琳. 基于多头注意力机制的磷酸化位点预测模型[J]. 广西师范大学学报（自然科学版）, 2022, 40(3): 161-171.
[7] 邓文轩, 杨航, 靳婷. 基于注意力机制的图像分类降维方法[J]. 广西师范大学学报（自然科学版）, 2021, 39(2): 32-40.
[8] 葛奕飞, 郑彦斌. 带有纠删或纠错性质的隐私保护信息检索方案[J]. 广西师范大学学报（自然科学版）, 2020, 38(3): 33-44.
[9] 王涵, 王绪安, 周能, 柳玉东. 基于区块链的可审计数据分享方案[J]. 广西师范大学学报（自然科学版）, 2020, 38(2): 1-7.
[10] 李维勇, 柳斌, 张伟, 陈云芳. 一种基于深度学习的中文生成式自动摘要方法[J]. 广西师范大学学报（自然科学版）, 2020, 38(2): 51-63.
[11] 王健, 郑七凡, 李超, 石晶. 基于ENCODER_ATT机制的远程监督关系抽取[J]. 广西师范大学学报（自然科学版）, 2019, 37(4): 53-60.
[12] 武文雅, 陈钰枫, 徐金安, 张玉洁. 基于高层语义注意力机制的中文实体关系抽取[J]. 广西师范大学学报（自然科学版）, 2019, 37(1): 32-41.
[13] 岳天驰, 张绍武, 杨亮, 林鸿飞, 于凯. 基于两阶段注意力机制的立场检测方法[J]. 广西师范大学学报（自然科学版）, 2019, 37(1): 42-49.
[14] 葛丽娜. 基于k-同构和局部随机化的隐私保护方法[J]. 广西师范大学学报（自然科学版）, 2016, 34(4): 1-8.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
[1] 林越,刘廷章,陈一凡,金勇,梁立新. 基于AP-HMM混合模型的充电桩故障诊断[J]. 广西师范大学学报（自然科学版）, 2018, 36(1): 25 -33 .
[2] 丁晓剑, 丁冉. 基于SVR-RFE的作战方案评估指标选择方法[J]. 广西师范大学学报（自然科学版）, 2015, 33(4): 43 -48 .
[3] 梁士楚, 田华丽, 田丰, 夏艺, 覃盈盈. 漓江湿地植被类型及其分布特点[J]. 广西师范大学学报（自然科学版）, 2015, 33(4): 115 -119 .
[4] 徐久成, 李晓艳, 李双群, 张灵均. 基于相容粒的多层次纹理特征图像检索方法[J]. 广西师范大学学报（自然科学版）, 2011, 29(1): 186 -187 .
[5] 陈美红, 杨翠红, 李传起. 人造地球卫星对地球自转的影响[J]. 广西师范大学学报（自然科学版）, 2011, 29(2): 6 -9 .
[6] 李梦, 曹庆先 , 胡宝清. 1960—2018年广西大陆海岸线时空变迁分析[J]. 广西师范大学学报（自然科学版）, 2021, 39(4): 99 -108 .
[7] 胡乐宁, 李双莉, 李杨, 韦奕庄, 周金玲, 苏以荣, 邓华. 改良过氧化钙对潜育性水稻土有机碳矿化的影响[J]. 广西师范大学学报（自然科学版）, 2021, 39(4): 158 -169 .
[8] 赵东江, 马松艳, 田喜强. CoSe2/C催化剂在电催化氧还原中的应用研究进展[J]. 广西师范大学学报（自然科学版）, 2021, 39(5): 30 -43 .
[9] 侯欠欠, 方志刚, 秦渝, 朱依文. 团簇Fe4P的成键及极化率探究[J]. 广西师范大学学报（自然科学版）, 2021, 39(6): 140 -146 .
[10] 白德发, 徐欣, 王国长. 函数型数据广义线性模型和分类问题综述[J]. 广西师范大学学报（自然科学版）, 2022, 40(1): 15 -29 .
版权所有 © 广西师范大学学报（自然科学版）编辑部
地址：广西桂林市三里店育才路15号　邮编：541004
电话：0773-5857325　E-mail: gxsdzkb@mailbox.gxnu.edu.cn
本系统由北京玛格泰克科技发展有限公司设计开发