南京大学学报(自然科学版) ›› 2023, Vol. 59 ›› Issue (3): 373–387.doi: 10.13232/j.cnki.jnju.2023.03.002
基于混合图神经网络的个性化POI推荐方法研究
刘志中(
), 李林霞, 孟令强
- 烟台大学计算机与控制工程学院，烟台，264005
An approach for personalized POI recommendation based on hybrid graph neural network
Zhizhong Liu(), Linxia Li, Lingqiang Meng
- School of Computer and Control Engineering，Yantai University，Yantai，264005，China
摘要：
随着基于位置的社交网络的快速发展，POI （Point of Interest）推荐已成为推荐领域的研究热点，然而已有的工作未能充分挖掘用户的POI交互偏好以及POI转移偏好，影响了POI推荐效果.提出一种基于混合图神经网络的个性化POI推荐方法.首先构建用户社交网络图，利用图注意力网络（Graph Attention Networks，GAT）学习含有社交关系的用户特征；其次，构建用户与POI的标号交互二部图，基于标号二部图神经网络（Signed Bipartite Graph Neural Networks，SBGNN）学习含有用户POI交互偏好的用户特征与POI特征；构建POI有向转移图，基于会话图神经网络（Session?Based Recommendation with Graph Neural Networks，SRGNN）学习含有用户POI转移偏好的POI特征；之后，融合含有社交关系的用户特征与含有POI交互偏好信息的用户特征得到最终的用户特征表示，融合含有用户POI交互偏好的POI特征与含有用户POI转移偏好的POI特征，得到最终的POI特征表示；最后，将用户特征表示与POI特征表示做乘积操作，通过Sigmoid函数得到用户对每个POI的预测评分，并以此向用户推荐Top?K POI序列.基于三个公共数据集（Gowalla，Foursquare和Yelp）开展了大量的实验，结果表明，与七种基线模型的推荐效果相比，提出的方法的准确率和召回率分别平均提升19.95%和1.35%.
中图分类号:
- TP3
| 1 | 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. Data Science and Engineering，2020，5(4)：433-447. |
| 2 | Zhong T， Zhang S M， Zhou F，et al. Hybrid graph convolutional networks with multi?head attention for location recommendation. World Wide Web，2020，23(6)：3125-3151. |
| 3 | Li C S， Li D M， Zhang Z Y，et al. MST?RNN：A multi?dimension spatiotemporal recurrent neural networks for recommending the next point of interest. Mathematics，2022，10(11)：1838. |
| 4 | Halder S， Lim K H， Chan J，et al. POI recommendation with queuing time and user interest awareness. Data Mining and Knowledge Discovery，2022，36(6)：2379-2409. |
| 5 | Liu X， Yang Y J， Xu Y B，et al. Real?time POI recommendation via modeling long? and short?term user preferences. Neurocomputing，2022(467)：454-464. |
| 6 | Xu Y Y， Li X F， Li J，et al. SSSER：Spatiotemporal sequential and social embedding rank for successive point?of?interest recommendation. IEEE Access，2019（7）：156804-156823. |
| 7 | 杨丽，王时绘，朱博. 基于动态和静态偏好的兴趣点推荐算法. 计算机应用，2021，41(2)：398-406. |
| Yang L， Wang S H， Zhu B. Point?of?interest recommendation algorithm combing dynamic and static preferences. Journal of Computer Applications，2021，41(2)：398-406. | |
| 8 | 李寒露，解庆，唐伶俐，等. 融合时空信息和兴趣点重要性的POI推荐算法. 计算机应用，2020，40(9)：2600-2605. |
| Li H L， Xie Q， Tang L L，et al. POI recommendation algorithm combining spatiotemporal information and POI importance. Journal of Compu?ter Applications，2020，40(9)：2600-2605. | |
| 9 | Liu Y， Wei W， Sun A X，et al. Exploiting geographical neighborhood characteristics for location recommendation∥Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge Management. Shanghai，China：ACM，2014：739-748. |
| 10 | Li X T， Cong G， Li X L，et al. Rank?GeoFM：A ranking based geographical factorization method for point of interest recommendation∥Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval. Santiago，Chile：ACM，2015：433-442. |
| 11 | Huang L W， Ma Y T， Wang S B，et al. An attention?based spatiotemporal LSTM network for next POI recommendation. IEEE Transactions on Services Computing，2021，14(6)：1585-1597. |
| 12 | Liu Q， Wu S， Wang L，et al. Predicting the next location：A recurrent model with spatial and temporal contexts∥Proceedings of the 30th AAAI Conference on Artificial Intelligence. Phoenix，AZ，USA：AAAI Press，2016：194-200. |
| 13 | Wang F J， Qu Y Z， Zheng L，et al. Deep and broad learning on content?aware POI recommendation∥2017 IEEE 3rd International Conference on Collaboration and Internet Computing. San Jose，CA，USA：IEEE，2017：369-378. |
| 14 | Yang C， Bai L X， Zhang C，et al. Bridging collaborative filtering and semi?supervised learning：A neural approach for POI recommendation∥Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. Halifax，Canada：ACM，2017：1245-1254. |
| 15 | Ying H C， Zhuang F Z， Zhang F Z，et al. Sequential recommender system based on hierarchical attention network∥Proceedings of the 27th International Joint Conference on Artificial Intelligence. Stockholm，Sweden：AAAI Press，2018：3926-3932. |
| 16 | Yin J J， Li Y， Liu Z，et al. ADPR：An attention?based deep learning point?of?interest recommendation framework∥2019 International Joint Conference on Neural Networks. Budapest，Hungary：IEEE，2019：1-8. |
| 17 | Lim N， Hooi B， Ng S K，et al. STP?UDGAT：Spatial?temporal?preference user dimensional graph attention network for next POI recommendation∥Proceedings of the 29th ACM International Conference on Information & Knowledge Management. Virtual Event，Ireland：ACM，2020：845-854. |
| 18 | Zhang J Y， Liu X， Zhou X F，et al. Leveraging graph neural networks for point?of?interest recommen?dations. Neurocomputing，2021(462)：1-13. |
| 19 | Tang J K， Jin J H， Miao Z J，et al. Region?aware POI recommendation with semantic spatial graph∥2021 IEEE 24th International Conference on Computer Supported Cooperative Work in Design. Dalian，China：IEEE，2021：214-219. |
| 20 | Yuan Q， Cong G， Ma Z Y，et al. Time?aware point?of?interest recommendation∥Proceedings of the 36th International ACM SIGIR Conference on Research and Development in Information Retrieval. Dublin，Ireland：ACM，2013：363-372. |
| 21 | Zhu Y， Li H， Liao Y K，et al. What to do next：Modeling user behaviors by time?LSTM∥Proceedings of the 26th International Joint Conference on Artificial Intelligence. Melbourne，Australia：AAAI Press，2017：3602-3608. |
| 22 | Chang B R， Jang G， Kim S，et al. Learning graph?based geographical latent representation for point?of?interest recommendation∥Proceedings of the 29th ACM International Conference on Information & Knowledge Management. Virtual Event，Ireland：ACM，2020：135-144. |
| 23 | Wang D J， Wang X L， Xiang Z Z，et al. Attentive sequential model based on graph neural network for next POI recommendation. World Wide Web，2021，24(6)：2161-2184. |
| 24 | Gao H J， Tang J L， Hu X，et al. Exploring temporal effects for location recommendation on location?based social networks∥Proceedings of the 7th ACM Conference on Recommender Systems. Hong Kong，China：ACM，2013：93-100. |
| 25 | Wang H， Terrovitis M， Mamoulis N. Location recommendation in location?based social networks using user check?in data∥Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. Orlando，FL，USA：ACM，2013：374-383. |
| 26 | Veli?kovi? P， Cucurull G， Casanova A，et al. Graph attention networks. 2018，arXiv:. |
| 27 | Huang J J， Shen H W， Cao Q，et al. Signed bipartite graph neural networks∥Proceedings of the 30th ACM International Conference on Information & Knowledge Management. Virtual Event，Australia：ACM，2021：740-749. |
| 28 | Wu S， Tang Y Y， Zhu Y Q，et al. Session?based recommendation with graph neural networks. Proceedings of the AAAI Conference on Artificial Intelligence，2019，33(1)：346-353. |
| 29 | Liu Y D， Pham T A N， Cong G，et al. An experimental evaluation of point?of?interest recom?mendation in location?based social networks. Proceedings of the VLDB Endowment，2017，10(10)：1010-1021. |
| 30 | Srivastava N， Hinton G， Krizhevsky A，et al. Dropout：A simple way to prevent neural networks from overfitting. The Journal of Machine Learning Research，2014，15(1)：1929-1958. |
| 31 | Cheng C， Yang H Q， King I，et al. Fused matrix factorization with geographical and social influence in location?based social networks. Proceedings of the AAAI Conference on Artificial Intelligence，2012，26(1)：17-23. |
| 32 | Yu D J， Yu T， Wang D J，et al. NGPR：A comprehensive personalized point?of?interest recommendation method based on heterogeneous graphs. Multimedia Tools and Applications，2022，81(27)：39207-39228. |
| 33 | Lang C， Wang Z， He K M，et al. POI recommendation based on a multiple bipartite graph network model. The Journal of Supercomputing，2022，78(7)：9782-9816. |
| 34 | Zhao P P， Luo A J， Liu Y C，et al. Where to go next：A spatio?temporal gated network for next POI recommendation. IEEE Transactions on Knowledge and Data Engineering，2022，34(5)：2512-2524. |
| 35 | Cai Z， Yuan G， Qiao S J，et al. FG?CF：Friends?aware graph collaborative filtering for POI recom?mendation. Neurocomputing，2022(488)：107-119. |
| 36 | Wang X， He X N， Wang M，et al. Neural graph collaborative filtering∥Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. Paris，France：ACM，2019：165-174. |
| [1] | 杨京虎, 段亮, 岳昆, 李忠斌. 基于子事件的对话长文本情感分析[J]. 南京大学学报(自然科学版), 2023, 59(3): 483-493. |
| [2] | 仲兆满, 熊玉龙, 黄贤波. 基于异构集成学习的多元文本情感分析研究[J]. 南京大学学报(自然科学版), 2023, 59(3): 471-482. |
| [3] | 程钦男, 莫志强, 曹斌, 范菁, 单宇翔. 基于多粒度信息编码和联合优化的篇章级服务事件序列抽取方法[J]. 南京大学学报(自然科学版), 2023, 59(3): 460-470. |
| [4] | 谭嘉辰, 董永权, 张国玺. SSM: 基于孪生网络的糖尿病视网膜眼底图像分类模型[J]. 南京大学学报(自然科学版), 2023, 59(3): 425-434. |
| [5] | 曲皓, 狄岚, 梁久祯, 刘昊. 双端输入型嵌套融合多尺度信息的织物瑕疵检测[J]. 南京大学学报(自然科学版), 2023, 59(3): 398-412. |
| [6] | 张绎凡, 李婷, 葛洪伟. 多样性诱导的潜在嵌入多视图聚类[J]. 南京大学学报(自然科学版), 2023, 59(3): 388-397. |
| [7] | 周业瀚, 沈子钰, 周清, 李云. 基于生成式对抗网络的自监督多元时间序列异常检测方法[J]. 南京大学学报(自然科学版), 2023, 59(2): 256-262. |
| [8] | 宋雨, 肖玉柱, 宋学力. 基于伪标签回归和流形正则化的无监督特征选择算法[J]. 南京大学学报(自然科学版), 2023, 59(2): 263-272. |
| [9] | 冯海, 马甲林, 许林杰, 杨宇, 谢乾. 融合标签嵌入和知识感知的多标签文本分类方法[J]. 南京大学学报(自然科学版), 2023, 59(2): 273-281. |
| [10] | 刘维, 杜宁宁, 陈崚, 洪青青. CIC模型下基于社区检测的谣言抑制最大化方法[J]. 南京大学学报(自然科学版), 2023, 59(2): 282-294. |
| [11] | 卞苏阳, 严云洋, 龚成张, 冷志超, 祝巧巧. 基于CXANet⁃YOLO的火焰检测方法[J]. 南京大学学报(自然科学版), 2023, 59(2): 295-301. |
| [12] | 崔凡, 强继朋, 朱毅, 李云. 基于ChineseBert的中文拼写纠错方法[J]. 南京大学学报(自然科学版), 2023, 59(2): 302-312. |
| [13] | 宋耀莲, 殷喜喆, 杨俊. 基于时空特征学习Transformer的运动想象脑电解码方法[J]. 南京大学学报(自然科学版), 2023, 59(2): 313-321. |
| [14] | 操东林, 崔超然, 杨潇. 基于深度强化学习的国内金融市场投资比较研究[J]. 南京大学学报(自然科学版), 2023, 59(2): 333-342. |
| [15] | 刘佳慧, 袁卫华, 曹家伟, 张涛, 张志军. 基于用户特征聚类与服务质量预测的推荐方法[J]. 南京大学学报(自然科学版), 2023, 59(1): 120-133. |
|
||