基于图神经网络的兴趣点推荐方法研究进展
收稿日期: 2024-01-05
修回日期: 2024-07-19
网络出版日期: 2024-09-18
基金资助
辽宁省教育厅理工类项目（JYTQN2023211）
Research progress on point-of-interest recommendation methods based on graph neural networks
School of Electronic and Information Engineering, Liaoning Technical University, Huludao, Liaoning 125105, China
Received date: 2024-01-05
Revised date: 2024-07-19
Online published: 2024-09-18
交叉学科是新科学的生长点，是科学发展的必然趋势。基于位置服务的重要应用——兴趣点推荐，作为计算机学科与地理信息学科相交叉的研究课题，对于推动2个学科在时空数据分析等相关领域的交叉融合研究具有重要作用。分析了兴趣点推荐的影响因素，对不同类型的推荐算法进行总结归纳，在此基础上重点阐述了基于图神经网络的兴趣点推荐方法，以及其在推荐系统中的广泛应用，包括基于图注意力网络、图卷积网络、图自编码器的推荐，并对其特点进行对比；讨论了在兴趣点推荐中存在的一些关键挑战，如数据稀疏性、冷启动问题和用户动态偏好问题，并针对各项挑战提出相应的解决思路，展望了该领域未来的发展趋势。
方金凤, 陈祖颐 . 基于图神经网络的兴趣点推荐方法研究进展[J]. 科技导报, 0 : 1 . DOI: 10.3981/j.issn.1000-7857. 2024.01.00099
Cross-discipline is the growth point of new science and the inevitable trend of scientific development. The important application of location-based service, point-of-interest (POI) recommendation, as a research topic at the intersection of computer science and geographic information science, it plays an important role in promoting the cross-fertilization research of the two disciplines in the spatio-temporal data analysis and other related fields. This paper analyzes the influencing factors of POI recommendation, summarizes different types of recommendation algorithms, and focuses on POI recommendation methods based on graph neural networks and their widespread applications in recommendation systems, including recommendation based on graph attention network, graph convolution network, and graph auto-encoder, with a comparative analysis of their respective characteristics; discusses some key challenges encountered in POI recommendation, such as data sparsity, cold start issues, and user dynamic preference issues, and proposes potential solution ideas to these challenges, makes prospects for the future development trend of POI recommendation.
[1] 吴毅涛, 赵磊, 赵耀强. 基于用户关系的兴趣点推荐算法[J]. 测绘与空间地理信息, 2019, 42(7): 145-147, 150.
[2] 段宗涛, 蔡丹丹, 唐蕾, 等. 基于预测的LBSN兴趣点推荐算法[J]. 微电子学与计算机, 2019, 36(1): 66-69.
[3] 崔立真, 于福强, 郭伟, 等. 一种基于深度学习的用户兴趣点推荐方法与系统: CN112364238A[P]. 2021-02-12.
[4] 张景奇, 史文宝, 修春亮. POI数据在中国城市研究中的应用[J]. 地理科学, 2021, 41(1): 140-148.
[5] Dai S J, Yu Y W, Fan H, et al. Spatio-temporal representation learning with social Tie for personalized POI recommendation[J]. Data Science and Engineering, 2022, 7(1): 44-56.
[6] Liu Y D, Pham T A N, Cong G, et al. An experimental evaluation of point-of-interest recommendation in location-based social networks[J]. Proceedings of the VLDB Endowment, 2017, 10(10): 1010-1021.
[7] 郁雪, 李敏强. 一种有效缓解数据稀疏性的混合协同过滤算法[J]. 计算机应用, 2009, 29(6): 1590-1593.
[8] 王立军. 基于协同过滤推荐系统的数据稀疏性问题研究[D]. 长春: 东北师范大学, 2009.
[9] 于洪, 李俊华. 一种解决新项目冷启动问题的推荐算法[J]. 软件学报, 2015, 26(6): 1395-1408.
[10] 李改, 李磊. 一种解决协同过滤系统冷启动问题的新算法[J]. 山东大学学报(工学版), 2012, 42(2): 11-17, 44.
[11] 姜书浩, 张立毅, 周娜. 基于用户偏好动态变化的协同过滤推荐[J]. 计算机与现代化, 2020(1): 75-80.
[12] 钱忠胜, 涂宇, 俞情媛, 等. 一种融合用户动态偏好和注意力机制的跨领域推荐方法[J]. 小型微型计算机系统, 2022, 43(6): 1335-1344.
[13] 冯申, 於跃成, 张宗海. 结合动态多类信息的兴趣点推荐[J]. 计算机与现代化, 2022(8): 57-64.
[14] Zhao S L, King I, Lyu M R. A survey of point-of-interest recommendation in location-based social networks[EB/OL]. 2016: 1607.00647.https://arxiv.org/abs/1607.00647v1
[15] Guo Q. Graph-based point-of-interest recommendation on location-based social networks[D]. Nanyang: Nanyang Technological University, 2019.
[16] 谢林基, 赵铁柱, 柳毅. 兴趣点推荐研究综述[J]. 计算机应用与软件, 2022, 39(12): 1-12, 57.
[17] 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.
[18] 焦旭, 肖迎元, 郑文广, 等. 基于位置的社会化网络推荐技术研究进展[J]. 计算机研究与发展, 2018, 55(10): 2291-2306.
[19] 欧道源, 梁京章, 吴丽娟. 基于高斯分布建模的序列推荐算法[J]. 计算机应用研究, 2023, 40(4): 1108-1112.
[20] Kemp C D, Silverman B W. Density estimation for statistics and data analysis[J]. The Statistician, 1987, 36(4): 420.
[21] Rhee I, Shin M, Hong S, et al. On the levy-walk nature of human mobility[J]. ACM Transactions on Networking, 2011, 19(3): 630-643.
[22] Caron Y, Makris P, Vincent N. Use of power law models in detecting region of interest[J]. Pattern Recognition, 2007, 40(9): 2521-2529.
[23] Ye M, Yin P F, Lee W C, et al. Exploiting geographical influence for collaborative point-of-interest recommendation[C]//Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval. New York: ACM, 2011: 325-334.
[24] Cho E, Myers S A, Leskovec J. Friendship and mobility: User movement in location-based social networks[C]//Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining. New York: ACM, 2011: 1082-1090.
[25] Cheng C, Yang H Q, King I, et al. Fused matrix factorization with geographical and social influence in location-based social networks[J]. Proceedings of the AAAI Conference on Artificial Intelligence, 2021, 26(1): 17-23.
[26] Zhao S L, King I, Lyu M R. Capturing geographical influence in POI recommendations[M]//Lecture Notes in Computer Science. Berlin, Heidelberg: Springer Berlin Heidelberg, 2013: 530-537.
[27] 李卫疆, 罗潘虎. 融合核密度估计和奇异值分解的多样化推荐算法[J]. 小型微型计算机系统, 2020, 41(1): 56-60.
[28] Zhang J D, Chow C Y. iGSLR: Personalized geo-social location recommendation: A kernel density estimation approach[C]//Proceedings of the 21st ACM SIGSPATIAL International Conference on Advances in Geographic Information Systems. New York: ACM, 2013: 334-343.
[29] Huang F H, Qiao S J, Peng J, et al. STPR: A personalized next point-of-interest recommendation model with spatio-temporal effects based on purpose ranking[J]. IEEE Transactions on Emerging Topics in Computing, 2021, 9(2): 994-1005.
[30] Gao H J, Tang J L, Hu X, et al. Exploring temporal effects for location recommendation on location-based social networks[C]//Proceedings of the 7th ACM conference on Recommender systems. New York: ACM, 2013: 93-100.
[31] Wang H L, Li P Y, Liu Y, et al. Towards real-time demand-aware sequential POI recommendation[J]. Information Sciences, 2021, 547: 482-497.
[32] Yuan Q, Cong G, Ma Z Y, et al. Time-aware point-of-interest recommendation[C]//Proceedings of the 36th international ACM SIGIR conference on Research and development in information retrieval. New York: ACM, 2013: 363-372.
[33] Zhang J D, Chow C Y. TICRec: A probabilistic framework to utilize temporal influence correlations for time-aware location recommendations[J]. IEEE Transactions on Services Computing, 2016, 9(4): 633-646.
[34] Konstas I, Stathopoulos V, Jose J M. On social networks and collaborative recommendation[C]//Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval. New York: ACM, 2009: 195-202.
[35] 刘艳, 潘善亮. 基于LBSN好友关系的个性化景点推荐方法[J]. 计算机工程与应用, 2015, 51(8): 117-122.
[36] 张志绮. 基于用户关系的矩阵分解推荐算法研究[D]. 北京: 北京交通大学, 2016.
[37] Zhu J H, Wang C, Guo X, et al. Friend and POI recommendation based on social trust cluster in location-based social networks[J]. EURASIP Journal on Wireless Communications and Networking, 2019, 2019(1): 89.
[38] Yang Y, Duan Y Q, Wang X Z, et al. Hierarchical multi-clue modelling for POI popularity prediction with heterogeneous tourist information[J]. IEEE Transactions on Knowledge and Data Engineering, 2019, 31(4): 757-768.
[39] 司亚利, 李峰, 宋亚伟. 结合流行度特征和核密度估计的兴趣点推荐算法[J]. 小型微型计算机系统, 2016, 37(11): 2416-2420.
[40] Yao Z J, Fu Y J, Liu B, et al. POI recommendation: A temporal matching between POI popularity and user regularity[C]//Proceedings of IEEE 16th International Conference on Data Mining (ICDM). Piscataway, NJ: IEEE, 2016: 549-558.
[41] 李英华. 基于神经网络的兴趣地点推荐研究与应用[D]. 重庆: 重庆大学, 2019.
[42] Wang S H, Wang Y L, Tang J L, et al. What your images reveal: Exploiting visual contents for point-of-interest recommendation[C]//Proceedings of the 26th International Conference on World Wide Web. Republic and Canton of Geneva, Switzerland: International World Wide Web Conferences Steering Committee, 2017: 391–400.
[43] Jiao X, Xiao Y Y, Zheng W G, et al. R2SIGTP: A novel real-time recommendation system with integration of geography and temporal preference for next point-of-interest[C]//Proceedings of World Wide Web Conference. New York: ACM, 2019: 3560-3563.
[44] Zhang Z B, Zou C, Ding R F, et al. VCG: Exploiting visual contents and geographical influence for Point-of-Interest recommendation[J]. Neurocomputing, 2019, 357: 53-65.
[45] Soares M, Viana P. Tuning metadata for better movie content-based recommendation systems[J]. Multimedia Tools and Applications, 2015, 74(17): 7015-7036.
[46] 周波. 二分网络推荐算法与协同过滤算法的关系研究[J]. 计算机科学, 2019, 46(S2): 163-166, 177.
[47] 邢春晓, 高凤荣, 战思南, 等. 适应用户兴趣变化的协同过滤推荐算法[J]. 计算机研究与发展, 2007, 44(2): 296-301.
[48] Shih D H, Yen D C, Lin H C, et al. An implementation and evaluation of recommender systems for traveling abroad[J]. Expert Systems with Applications, 2011, 38(12): 15344-15355.
[49] 姜书浩, 薛福亮. 一种利用协同过滤预测和模糊相似性改进的基于内容的推荐方法[J]. 现代图书情报技术, 2014(2): 41-47.
[50] 郭艳红, 邓贵仕. 协同过滤系统项目冷启动的混合推荐算法[J]. 计算机工程, 2008, 34(23): 11-13.
[51] 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.
[52] 吴燕, 章韵, 陈双双. 混合时空和流行度特征的兴趣点推荐算法[J]. 计算机工程, 2018, 44(9): 59-63, 69.
[53] 刘志中, 李林霞, 孟令强. 基于混合图神经网络的个性化POI推荐方法研究[J]. 南京大学学报(自然科学), 2023, 59(3): 373-387.
[54] 李先贤, 刘天然, 王利娥, 等. 一种基于图神经网络的兴趣点推荐方法: CN114048380A[P]. 2022-02-15.
[55] 魏晓辉, 孙冰怡, 崔佳旭. 基于图神经网络的兴趣活动推荐算法[J]. 吉林大学学报(工学版), 2021, 51(1): 278-284.
[56] Velickovic P, Cucurull G, Casanova A , et al. Graph attention networks[C]//Proceedings of the 6th International Conference on Learning Representations, ICLR 2018 - Conference Track Proceedings. Vancouver, Canada: OpenReview.net, 2018: 2920-2931.
[57] Zhang J Y, Liu X, Zhou X F, et al. Leveraging graph neural networks for point-of-interest recommendations[J]. Neurocomputing, 2021, 462: 1-13.
[58] Wang X L, Wang D J, Yu D J, et al. Intent-aware Graph Neural Network for Point-of-Interest embedding and recommendation[J]. Neurocomputing, 2023, 557: 126734.
[59] Gong W H, Zheng K C, Zhang S B, et al. Deep pairwise learning for user preferences via dual graph attention model in location-based social networks[J]. Expert Systems with Applications, 2023, 227: 120222.
[60] Shi M H, Shen D R, Kou Y, et al. Attentional Memory Network with Correlation-based Embedding for time-aware POI recommendation[J]. Knowledge-Based Systems, 2021, 214: 106747.
[61] Zhang S Y, Cheng H. Exploiting context graph attention for POI recommendation in location-based social networks[M]//Lecture Notes in Computer Science. Cham: Springer International Publishing, 2018: 83-99.
[62] Wu Y S, Jin X, Huang H P. Muti-channel graph attention networks for POI recommendation[J]. Journal of Intelligent & Fuzzy Systems, 2023, 44(5): 8375-8385.
[63] Li Z Y, Cheng W, Xiao H Q, et al. You are what and where you are: Graph enhanced attention network for explainable POI recommendation[C]//Proceedings of the 30th ACM International Conference on Information & Knowledge Management. New York: ACM, 2021: 3945-3954.
[64] Zhang Z H, Zhu J H, Yue C B. Session-based graph attention POI recommendation network[J]. Wireless Communications and Mobile Computing, 2022, 2022: 6557936.
[65] Hossain M B, Arefin M S, Sarker I H, et al. CARAN: A context-aware recency-based attention network for point-of-interest recommendation[J]. IEEE Access, 2022, 10: 36299-36310.
[66] Fan X H, Hua Y X, Cao Y B, et al. Capturing dynamic interests of similar users for POI recommendation using self-attention mechanism[J]. Sustainability, 2023, 15(6): 5034.
[67] Fu J R, Gao R, Yu Y H, et al. Contrastive graph learning long and short-term interests for POI recommendation[J]. Expert Systems with Applications, 2024, 238: 121931.
[68] Meng L Q, Liu Z Z, Chu D H, et al. POI recommendation for occasional groups Based on hybrid graph neural networks[J]. Expert Systems with Applications, 2024, 237: 121583.
[69] Wu L, Sun P J, Fu Y J, et al. A neural influence diffusion model for social recommendation[C]//Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval. New York: ACM, 2019: 235-244.
[70] Li Y. A POI recommendation algorithm based on the heterogeneous graph convolution network[J]. Scientific Programming, 2022, 2022: 9154712.
[71] Zhong T, Zhang S M, Zhou F, et al. Hybrid graph convolutional networks with multi-head attention for location recommendation[J]. World Wide Web, 2020, 23(6): 3125-3151.
[72] Liu J T, Yi H W, Gao Y X, et al. Personalized point-of-interest recommendation using improved graph convolutional network in location-based social network[J]. Electronics, 2023, 12(16): 3495.
[73] Zhang S Z, Bai Z J, Li P, et al. Multi-graph convolutional network for fine-grained and personalized POI recommendation[J]. Electronics, 2022, 11(18): 2966.
[74] 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.
[75] Feng J P, Gan M X, Ma Y X. MIGNN: A multiple intention-aware graph convolutional neural network for POI recommendation[C]//Proceedings of the International Conference on Big Data Economy and Digital Management. SCITEPRESS - Science and Technology Publications, 2022: 256-261.
[76] Zhai F B, Li B Z. Point of interest recommendation based on graph convolutional neural network[J]. Journal of Physics: Conference Series, 2021, 1883(1): 012132.
[77] Bai Z J, Zhang S Z, Li P, et al. Personalized point-of-interest recommendation with relation-enhanced graph convolutional network[C]//Proceedings of the 2022 11th International Conference on Networks, Communication and Computing. New York: ACM, 2022: 254-260.
[78] Wu H. A POI recommendation model with temporal-regional based graph representation learning[C]//Proceedings of IEEE 5th International Conference on Information Systems and Computer Aided Education (ICISCAE). Piscataway, NJ: IEEE, 2022: 790-794.
[79] Gan Y, Hu Z Y. Fusion privacy protection of graph neural network points of interest recommendation[J]. International Journal of Advanced Computer Science and Applications, 2023, 14(4): 548-556..
[80] Wang X L, Sun G H, Fang X, et al. Modeling spatio-temporal neighbourhood for personalized point-of-interest recommendation[C]//Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2022: 3530-3536.
[81] Su C, Gong B, Xie X Z. Personalized point-of-interest recommendation based on social and geographical influence[C]//Proceedings of 2021 4th Artificial Intelligence and Cloud Computing Conference. New York: ACM, 2021: 130-137.
[82] Wu Z Y, Xu N. Point-of-interest recommendation model based on graph convolutional neural network[J]. Wireless Communications and Mobile Computing, 2022, 2022: 7638117.
[83] Kipf T N, Welling M. Variational graph auto-encoders[EB/OL]. [2023-11-03]. 2016: 1611.07308.https://arxiv.org/abs/1611.07308v1
[84] Wang W, Suo X Y, Wei X Y, et al. HGATE: Heterogeneous graph attention auto-encoders[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(4): 3938-3951.
[85] Chang B R, Jang G, Kim S, et al. Learning graph-based geographical latent representation for point-of-interest recommendation[C]//Proceedings of the 29th ACM International Conference on Information & Knowledge Management. New York: ACM, 2020: 135-144.
[86] 刘金鑫. 自编码器在推荐系统中的应用研究[D]. 天津: 天津理工大学, 2022.
[87] Xu Q D, Shen F M, Liu L, et al. GraphCAR: Content-aware multimedia recommendation with graph autoencoder[C]//Proceedings of 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. New York: ACM, 2018: 981-984.
[88] 吴国栋, 刘玉良, 李方, 等. 一种基于图自编码器的个性化推荐方法: CN112347362A[P]. 2021-02-09.
[89] Gan M X, Zhang H. VIGA: A variational graph autoencoder model to infer user interest representations for recommendation[J]. Information Sciences, 2023, 640: 119039.
[90] Ma C, Zhang Y X, Wang Q L, et al. Point-of-interest recommendation: Exploiting self-attentive autoencoders with neighbor-aware influence[C]//Proceedings of the 27th ACM International Conference on Information and Knowledge Management. New York: ACM, 2018: 697-706.
[91] 温雯, 邓峰颖, 郝志峰, 等. 时空邻域感知的时序兴趣点推荐[J]. 计算机科学与探索, 2024, 18(7): 1865-1878.
[92] Yu F Q, Cui L Z, Guo W, et al. A category-aware deep model for successive POI recommendation on sparse check-in data[C]//Proceedings of The Web Conference 2020. New York: ACM, 2020: 1264-1274.
[93] Abinaya S, Alphonse A S, Abirami S, et al. Enhancing context-aware recommendation using trust-based contextual attentive autoencoder[J]. Neural Processing Letters, 2023, 55(5): 6843-6864.
[94] Bayram F, Ahmed B S, Kassler A. From concept drift to model degradation: An overview on performance-aware drift detectors[J]. Knowledge-Based Systems, 2022, 245: 108632.
[95] Ni X L, Xiong F, Pan S R, et al. Community preserving social recommendation with cyclic transfer learning[J]. ACM Transactions on Information Systems, 2024, 42(3): 1-36.
/
| 〈 |
|
〉 |
