{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,14]],"date-time":"2025-10-14T19:34:00Z","timestamp":1760470440790,"version":"3.44.0"},"reference-count":56,"publisher":"Association for Computing Machinery (ACM)","issue":"8","funder":[{"DOI":"10.13039\/501100018537","name":"National Science and Technology Major Project","doi-asserted-by":"crossref","award":["2024ZD1300200"],"award-info":[{"award-number":["2024ZD1300200"]}],"id":[{"id":"10.13039\/501100018537","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["2242023R40005"],"award-info":[{"award-number":["2242023R40005"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:p>Knowledge discovered from telecom data can facilitate proactive understanding of network dynamics and user behaviors, which in turn empowers service providers to optimize cellular traffic scheduling and resource allocation. Nevertheless, the telecom industry still heavily relies on manual expert intervention. Existing studies have been focused on exhaustively exploring the spatial-temporal correlations. However, they often overlook the underlying characteristics of cellular traffic, which are shaped by the sporadic and bursty nature of telecom services. Additionally, concept drift creates substantial obstacles to maintaining satisfactory accuracy in continuous cellular forecasting tasks. To resolve these problems, we put forward an online cellular traffic prediction method grounded in Multi-Grained Spatial-Temporal feature Complementarity (MGSTC). The proposed method is devised to achieve high-precision predictions in practical continuous forecasting scenarios. Concretely, MGSTC segments historical data into chunks and employs the coarse-grained temporal attention to offer a trend reference for the prediction horizon. Subsequently, fine-grained spatial attention is utilized to capture detailed correlations among network elements, which enables localized refinement of the established trend. The complementarity of these multi-grained spatial-temporal features facilitates the efficient transmission of valuable information. To accommodate continuous forecasting needs, we implement an online learning strategy that can detect concept drift in real-time and promptly switch to the appropriate parameter update stage. Experiments carried out on four real-world datasets demonstrate that MGSTC outperforms eleven state-of-the-art baselines consistently.<\/jats:p>","DOI":"10.1145\/3758099","type":"journal-article","created":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T15:23:27Z","timestamp":1754407407000},"page":"1-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Multi-Grained Spatial-Temporal Feature Complementarity for Accurate Online Cellular Traffic Prediction"],"prefix":"10.1145","volume":"19","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-7407-6597","authenticated-orcid":false,"given":"Ningning","family":"Fu","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6579-9798","authenticated-orcid":false,"given":"Shengheng","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Southeast University, Nanjing, China and Purple Mountain Laboratories, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-2542-8050","authenticated-orcid":false,"given":"Weiliang","family":"Xie","sequence":"additional","affiliation":[{"name":"China Telecom Corporation Limited Technology Innovation Center, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3616-4616","authenticated-orcid":false,"given":"Yongming","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Information Science and Engineering, Southeast University, Nanjing, China and Purple Mountain Laboratories, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,9,8]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_3_2_2","DOI":"10.1109\/MWC.004.2200482"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_2","DOI":"10.1145\/3703447"},{"doi-asserted-by":"publisher","key":"e_1_3_3_4_2","DOI":"10.1016\/j.eswa.2022.117163"},{"doi-asserted-by":"publisher","key":"e_1_3_3_5_2","DOI":"10.1109\/TWC.2023.3254903"},{"doi-asserted-by":"publisher","key":"e_1_3_3_6_2","DOI":"10.1016\/j.sysarc.2022.102775"},{"issue":"4","key":"e_1_3_3_7_2","first-page":"3728","article-title":"A novel STFSA-CNN-GRU hybrid model for short-term traffic speed prediction","volume":"24","author":"Ma Changxi","year":"2023","unstructured":"Changxi Ma, Yongpeng Zhao, Guowen Dai, Xuecai Xu, and Sze-Chun Wong. 2023. A novel STFSA-CNN-GRU hybrid model for short-term traffic speed prediction. IEEE Transactions on Intelligent Transportation Systems 24, 4 (Apr. 2023), 3728\u20133737.","journal-title":"IEEE"},{"doi-asserted-by":"publisher","key":"e_1_3_3_8_2","DOI":"10.1109\/TASE.2021.3077537"},{"doi-asserted-by":"crossref","unstructured":"Haoyi Zhou Shanghang Zhang Jieqi Peng Shuai Zhang Jianxin Li Hui Xiong and Wancai Zhang. 2021. Informer: Beyond efficient transformer for long sequence time-series forecasting. In Proceedings of the AAAI Conference on Artificial Intelligence Vol. 35 11106\u201311115.","key":"e_1_3_3_9_2","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"e_1_3_3_10_2","first-page":"27268","volume-title":"(ICML)","volume":"16","author":"Zhou Tian","year":"2022","unstructured":"Tian Zhou, Ziqing Ma, Qingsong Wen, Xue Wang, Liang Sun, and Rong Jin. 2022. FEDformer: Frequency enhanced decomposed transformer for long-term series forecasting. In Proceedings of Machine Learning Research (ICML), Vol. 16, 27268\u201327286."},{"key":"e_1_3_3_11_2","first-page":"1","volume-title":"(ICLR)","author":"Nie Yuqi","year":"2023","unstructured":"Yuqi Nie, Nam H. Nguyen, Phanwadee Sinthong, and Jayant Kalagnanam. 2023. A time series is worth 64 words: Long-term forecasting with transformers. In Proceedings of the International Conference on Learning Representations (ICLR), 1\u201324."},{"key":"e_1_3_3_12_2","first-page":"1","volume-title":"(ICLR)","author":"Zhang Yunhao","year":"2023","unstructured":"Yunhao Zhang and Junchi Yan. 2023. Crossformer: Transformer utilizing cross-dimension dependency for multivariate time series forecasting. In Proceedings of the International Conference on Learning Representations (ICLR), 1\u201321."},{"doi-asserted-by":"publisher","key":"e_1_3_3_13_2","DOI":"10.1145\/3439346"},{"doi-asserted-by":"publisher","key":"e_1_3_3_14_2","DOI":"10.1109\/LWC.2021.3078745"},{"doi-asserted-by":"publisher","key":"e_1_3_3_15_2","DOI":"10.1109\/LCOMM.2021.3138075"},{"doi-asserted-by":"publisher","key":"e_1_3_3_16_2","DOI":"10.1109\/TITS.2021.3136287"},{"doi-asserted-by":"publisher","key":"e_1_3_3_17_2","DOI":"10.1016\/j.inffus.2023.102079"},{"doi-asserted-by":"publisher","key":"e_1_3_3_18_2","DOI":"10.1109\/TITS.2022.3173689"},{"doi-asserted-by":"publisher","key":"e_1_3_3_19_2","DOI":"10.1145\/3459637.3482152"},{"doi-asserted-by":"publisher","key":"e_1_3_3_20_2","DOI":"10.1109\/TII.2022.3182768"},{"issue":"125","key":"e_1_3_3_21_2","first-page":"1","article-title":"A cellular traffic prediction method based on diffusion convolutional GRU and multi-head attention mechanism","volume":"28","author":"Xiao Junbi","year":"2025","unstructured":"Junbi Xiao, Yunhuan Cong, Wenjing Zhang, and Wenchao Weng. 2025. A cellular traffic prediction method based on diffusion convolutional GRU and multi-head attention mechanism. Cluster Computing 28, 125 (2025), 1\u201317.","journal-title":"Cluster Computing"},{"doi-asserted-by":"publisher","key":"e_1_3_3_22_2","DOI":"10.1109\/TKDE.2023.3272911"},{"unstructured":"YiFan Zhang Weiqi Chen Zhaoyang Zhu Dalin Qin Liang Sun Xue Wang Qingsong Wen Zhang Zhang Liang Wang and Rong Jin. 2024. Addressing concept shift in online time series forecasting: Detect-then-adapt. arXiv:2403.14949. Retrieved from https:\/\/arxiv.org\/abs\/2403.14949","key":"e_1_3_3_23_2"},{"doi-asserted-by":"crossref","unstructured":"Hao Miao Yan Zhao Chenjuan Guo Bin Yang Kai Zheng Feiteng Huang Jiandong Xie and Christian S. Jensen. 2024. A unified replay-based continuous learning framework for spatio-temporal prediction on streaming data. arXiv:2404.14999. Retrieved from https:\/\/arxiv.org\/abs\/2404.14999","key":"e_1_3_3_24_2","DOI":"10.1109\/ICDE60146.2024.00085"},{"unstructured":"Arslan Chaudhry Marcus Rohrbach Mohamed Elhoseiny Thalaiyasingam Ajanthan Puneet K. Dokania Philip H. S. Torr and Marc\u2019Aurelio Ranzato. 2019. On tiny episodic memories in continual learning. arXiv:1902.10486. Retrieved from https:\/\/arxiv.org\/abs\/1902.10486","key":"e_1_3_3_25_2"},{"key":"e_1_3_3_26_2","first-page":"15920","article-title":"Dark experience for general continual learning: A strong, simple baseline","volume":"33","author":"Buzzega Pietro","year":"2020","unstructured":"Pietro Buzzega, Matteo Boschini, Angelo Porrello, Davide Abati, and Simone Calderara. 2020. Dark experience for general continual learning: A strong, simple baseline. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Vol. 33, 15920\u201315930.","journal-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)"},{"doi-asserted-by":"publisher","key":"e_1_3_3_27_2","DOI":"10.24963\/ijcai.2021\/498"},{"doi-asserted-by":"publisher","key":"e_1_3_3_28_2","DOI":"10.1109\/TVT.2023.3330661"},{"doi-asserted-by":"publisher","key":"e_1_3_3_29_2","DOI":"10.1109\/TNSM.2024.3454217"},{"doi-asserted-by":"publisher","key":"e_1_3_3_30_2","DOI":"10.1109\/JSAC.2020.3000408"},{"doi-asserted-by":"publisher","key":"e_1_3_3_31_2","DOI":"10.1109\/TII.2020.3009159"},{"doi-asserted-by":"publisher","key":"e_1_3_3_32_2","DOI":"10.1109\/JSAC.2019.2904363"},{"doi-asserted-by":"publisher","key":"e_1_3_3_33_2","DOI":"10.1109\/TMC.2020.3001225"},{"doi-asserted-by":"publisher","key":"e_1_3_3_34_2","DOI":"10.1109\/TMC.2020.3020582"},{"doi-asserted-by":"publisher","key":"e_1_3_3_35_2","DOI":"10.1109\/TMC.2021.3079117"},{"doi-asserted-by":"publisher","key":"e_1_3_3_36_2","DOI":"10.1145\/3679017"},{"doi-asserted-by":"publisher","key":"e_1_3_3_37_2","DOI":"10.1145\/3511808.3557540"},{"key":"e_1_3_3_38_2","first-page":"3415","volume-title":"(CIKM)","author":"Zheng Yuhao","year":"2024","unstructured":"Yuhao Zheng, Yishuo Cai, Zihao Cai, Changjun Fan, Senzhang Wang, and Jianxin Wang. 2024. FGITrans: Cross-city transformer for fine-grained urban flow inference. In Proceedings of the International Conference on Information and Knowledge Management (CIKM), 3415\u20133423."},{"key":"e_1_3_3_39_2","first-page":"1481","volume-title":"(CIKM)","author":"Ma Yihong","year":"2022","unstructured":"Yihong Ma, Patrick Gerard, Yijun Tian, Zhichun Guo, and Nitesh V. Chawla. 2022. Hierarchical spatio-temporal graph neural networks for pandemic forecasting. In Proceedings of the International Conference on Information and Knowledge Management (CIKM), 1481\u20131490."},{"doi-asserted-by":"publisher","key":"e_1_3_3_40_2","DOI":"10.1109\/TKDE.2022.3175094"},{"doi-asserted-by":"publisher","key":"e_1_3_3_41_2","DOI":"10.1109\/LCOMM.2020.3012279"},{"doi-asserted-by":"publisher","key":"e_1_3_3_42_2","DOI":"10.1109\/LCOMM.2021.3098557"},{"doi-asserted-by":"publisher","key":"e_1_3_3_43_2","DOI":"10.1109\/TMC.2021.3129796"},{"doi-asserted-by":"publisher","key":"e_1_3_3_44_2","DOI":"10.1109\/TWC.2023.3270441"},{"key":"e_1_3_3_45_2","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1007\/978-981-97-5552-3_16","volume-title":"Proceedings of the International Conference on Database Systems for Advanced Applications","author":"Zhao Zhengyang","year":"2024","unstructured":"Zhengyang Zhao, Haitao Yuan, Nan Jiang, Minxiao Chen, Ning Liu, and Zengxiang Li. 2024. STMGF: An effective spatial-temporal multi-granularity framework for traffic forecasting. In Proceedings of the International Conference on Database Systems for Advanced Applications, 235\u2013245."},{"doi-asserted-by":"publisher","key":"e_1_3_3_46_2","DOI":"10.1016\/j.ins.2024.120230"},{"doi-asserted-by":"publisher","key":"e_1_3_3_47_2","DOI":"10.1145\/3563947"},{"key":"e_1_3_3_48_2","first-page":"11849","article-title":"Online continual learning with maximal interfered retrieval","volume":"32","author":"Aljundi Rahaf","year":"2019","unstructured":"Rahaf Aljundi, Eugene Belilovsky, Tinne Tuytelaars, Laurent Charlin, Massimo Caccia, Min Lin, and Lucas Page-Caccia. 2019. Online continual learning with maximal interfered retrieval. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Vol. 32, 11849\u201311860.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_3_49_2","first-page":"69949","volume-title":"Advances in Neural Information Processing Systems (NeurIPS)","author":"Zhang Yifan","year":"2023","unstructured":"Yifan Zhang, Qingsong Wen, Xue Wang, Weiqi Chen, Liang Sun, Zhang Zhang, Liang Wang, Rong Jin, and Tieniu Tan. 2023. OneNet: Enhancing time series forecasting models under concept drift by online ensembling. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS). A. Oh, T. Naumann, A. Globerson, K. Saenko, M. Hardt, and S. Levine (Eds.), Vol. 36, 69949\u201369980."},{"doi-asserted-by":"publisher","key":"e_1_3_3_50_2","DOI":"10.1109\/MNET.011.1900647"},{"doi-asserted-by":"publisher","key":"e_1_3_3_51_2","DOI":"10.1038\/sdata.2015.55"},{"key":"e_1_3_3_52_2","doi-asserted-by":"crossref","first-page":"134","DOI":"10.1016\/j.procs.2021.04.043","article-title":"Dynamic modification neural network model for short-term traffic prediction","volume":"187","author":"Guo Da","year":"2021","unstructured":"Da Guo, Xingwen Xia, Lin Zhu, and Yong Zhang. 2021. Dynamic modification neural network model for short-term traffic prediction. Procedia Computer Science 187 (Jun. 2023), 134\u2013139.","journal-title":"Procedia Computer Science"},{"doi-asserted-by":"publisher","key":"e_1_3_3_53_2","DOI":"10.1109\/JIOT.2023.3283611"},{"key":"e_1_3_3_54_2","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141. Ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS), Vol. 30, 1\u201311.","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"e_1_3_3_55_2","first-page":"4026","volume-title":"Proceedings of the IEEE International Conference Communications (ICC)","author":"Wang Xing","year":"2023","unstructured":"Xing Wang, Kexin Yang, Zhendong Wang, Junlan Feng, Lin Zhu, Juan Zhao, and Chao Deng. 2023. Adaptive hybrid spatial-temporal graph neural network for cellular traffic prediction. In Proceedings of the IEEE International Conference Communications (ICC), 4026\u20134032."},{"doi-asserted-by":"publisher","key":"e_1_3_3_56_2","DOI":"10.1609\/aaai.v38i8.28759"},{"doi-asserted-by":"publisher","key":"e_1_3_3_57_2","DOI":"10.1109\/MWC.006.2200407"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3758099","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T15:48:16Z","timestamp":1757346496000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3758099"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,8]]},"references-count":56,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2025,9,30]]}},"alternative-id":["10.1145\/3758099"],"URL":"https:\/\/doi.org\/10.1145\/3758099","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"type":"print","value":"1556-4681"},{"type":"electronic","value":"1556-472X"}],"subject":[],"published":{"date-parts":[[2025,9,8]]},"assertion":[{"value":"2025-01-27","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-07-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-09-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}