This paper proposes a long-tail-aware POI recommendation method using a global frequency hypergraph network and a multi-span HiLo (high/low) attention mechanism. First, a global frequency hypergraph network is constructed to separately model the subsequent trajectories of head and tail POIs, thus mining higher-order frequency signals across sessions and capturing complex interaction features. Then, a HiLo attention mechanism with multiple temporal spans is used to capture high- and low-frequency features within the hidden sequences. Finally, a long-tail enhancement module is introduced to improve the propagation ability of tail POIs through adaptive edge deletion and enhanced graph construction. Experimental results on multiple real-world datasets show that the proposed method outperforms existing baseline models and demonstrates significant advantages, particularly in long-tail POI recommendation tasks.
[1] Zheng Y S, Zhou X. Modeling multi-factor user preferences based on transformer for next point of interest recommendation [J]. Expert Systems with Applications, 2024, 255: 124894.
[2] Zhang Y S, Liu Y. Point-of-interest recommendation based on LSBN with multi-aspect fusion of social and individual features [J]. Neural Computing and Applications, 2024, 36(20): 12163- 12184.
[3] Rao X, Chen L, Liu Y, et al. Graph-flashback network for next location recommendation [C]// 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022: 1463-1471.
[4] Zhang L, Sun Z, Wu Z, et al. Next point-of-interest recommendation with inferring multi-step future preferences [C]// Thirty-First International Joint Conference on Artificial Intelligence, 2022: 3751-3757.
[5] Wu Y X, Li K, Zhao G S, et al. Personalized long-and short-term preference learning for next POI recommendation [J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 34(4): 1944-1957.
[6] Guo Q, Sun Z, Zhang J, et al. An attentional recurrent neural network for personalized next location recommendation [C]// AAAI Conference on Artificial Intelligence, 2020, 34(1): 83-90.
[7] Vaswani A, Shazeer N, Parmar N, et al. Attention is all you need [C]// Advances in Neural Information Processing Systems, 2017: 5998-6008.
[8] Ni J C, Zhao P P, Xu J J, et al. Spatio-temporal self-attention network for next POI recommendation [C]// Web and Big Data: 4th International Joint Conference, 2020, 12317: 409-423.
[9] Luo Y T, Liu Q, Liu Z C. STAN: spatio-temporal attention network for next location recommendation [C]// Web Conference, 2021: 2177-2185.
[10] Shafiloo R, Kaedi M, Pourmiri A. Considering user dynamic preferences for mitigating negative effects of long-tail in recommender systems [J]. Information Sciences, 2024, 669: 120558.
[11] Velickovic P, Cucurull G, Casanova A, et al. Graph attention networks [PP/OL]. V3(2018-02-04) [2025-10-29]. https://doi.org/10.48550/arXiv.1710.10903.
[12] Wang J K, Yang B, Liu H D, et al. Global spatio-temporal aware graph neural network for next point-of-interest recommendation [J]. Applied Intelligence, 2023, 53(13): 16762-16775.
[13] Zhou W, Fu C, Sang C, et al. Next POI recommendation based on graph convolutional networks and multiple context-awareness [J]. IEEE Transactions on Services Computing, 2025, 18(1): 302- 313.
[14] Rong Y, Huang W, Xu T, et al. DropEdge: towards deep graph convolutional networks on node classification [PP/OL]. V4(2020-03-12) [2025-10-29]. https://doi.org/10.48550/arXiv.1907.10903.
[15] Yan X D, Song T, Jiao Y F, et al. Spatio-temporal hypergraph learning for next POI recommendation [C]// 46th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2023: 403-412.
[16] Zeng J, Tao H L, Tang H R, et al. Global and local hypergraph learning method with semantic enhancement for POI recommendation [J]. Information Processing & Management, 2025, 62(1): 103868.
[17] Zhao Z Y, Wang Y L, Liu D M. Self-supervised learning recommendation with enhanced long-tail nodes [C]// 5th International Conference on Artificial Intelligence and Computer Engineering, 2024: 850-856.
[18] Pan Z Z, Cai J F, Zhuang B H. Fast vision transformers with HiLo attention [C]// Advances in Neural Information Processing Systems, 2022: 14541-14554.
[19] Feng Y F, You H X, Zhang Z Z, et al. Hypergraph neural networks [C]// 33rd AAAI Conference on Artificial Intelligence, 2019, 33(1): 3558-3565.
[20] Luo S C, Ma C, Xiao Y Z, et al. Improving long-tail item recommendation with graph augmentation [C]// 32nd ACM International Conference on Information and Knowledge Management, 2023: 1707-1716.
[21] Zhao T, Liu Y Z, Neves L, et al. Data augmentation for graph neural networks [C]// 35th AAAI Conference on Artificial Intelligence, 2021, 35(12): 11015-11023.
[22] Yang D Q, Zhang D Q, Zheng V W, et al. Modeling user activity preference by leveraging user spatial temporal characteristics in LBSNs [J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2015, 45(1): 129-142.
[23] Yin H Z, Cui B, Chen L, et al. Modeling location-based user rating profiles for personalized recommendation [J]. ACM Transactions on Knowledge Discovery from Data, 2015, 9(3): 1-41.
[24] Duan C H, Fan W, Zhou W, et al. CLSPRec: contrastive learning of long and short-term preferences for next poi recommendation [C]// 32nd ACM International Conference on Information and Knowledge Management, 2023: 473-482.
[25] He X N, Deng K, Wang X, et al. LightGCN: simplifying and powering graph convolution network for recommendation [C]// 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval, 2020: 639-648.
[26] Yang S, Liu J M, Zhao K Q. GETNext: trajectory flow map enhanced transformer for next POI recommendation [C]// 45th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2022: 1144-1153.
[27] Sun X X, Huang B Y, Wang X F, et al. MARAN: supporting awareness of users’ routines and preferences for next POI recommendation based on spatial aggregation [J]. Expert Systems with Applications, 2024, 238: 121961.
[28] Lai Y T, Su Y J, Wei L W, et al. Multi-view spatial-temporal enhanced hypergraph network for next POI recommendation [C]// Database Systems for Advanced Applications: 28th International Conference, 2023: 237-252.
[29] Lai Y T, Su Y J, Wei L W, et al. Adaptive spatial-temporal hypergraph fusion learning for next POI recommendation [C]// 2024 IEEE International Conference on Acoustics, Speech and Signal Processing, 2024: 7320-324.