{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:14:37Z","timestamp":1757618077008,"version":"3.44.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T00:00:00Z","timestamp":1749600000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T00:00:00Z","timestamp":1749600000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["101079043"],"award-info":[{"award-number":["101079043"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021856","name":"Ministero dell'Universit\u00e0 e della Ricerca","doi-asserted-by":"publisher","award":["PE0000013-FAIR"],"award-info":[{"award-number":["PE0000013-FAIR"]}],"id":[{"id":"10.13039\/501100021856","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100031478","name":"NextGenerationEU","doi-asserted-by":"publisher","award":["E63C22000980007"],"award-info":[{"award-number":["E63C22000980007"]}],"id":[{"id":"10.13039\/100031478","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004115","name":"Gottfried Wilhelm Leibniz Universit\u00e4t Hannover","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100004115","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Mach Learn"],"published-print":{"date-parts":[[2025,7]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>In the Intelligent Public Transportation Systems (IPTS) domain, predicting the number of commuters on-board, entering or leaving a metro train or a bus, i.e. the Passenger Flow (PF), is crucial for optimizing resource allocation and enhancing commuter satisfaction. In urban scenarios, the public transport system is often managed by distinct competing mobility providers. Traditional centralized machine learning models for PF prediction usually require data sharing among such competitors, leading to privacy and economic concerns. To overcome these issues, we propose exploiting Federated Learning (FL) in the PF predictions problem, as only model parameters must be shared among entities. Still, a straightforward application of FL can have some pitfalls. On one hand, it is widely recognized that FL can struggle with data heterogeneity, which is likely in the case of data acquired by distinct companies managing different public mobility services. Moreover, spatio-temporal features are not explicitly handled by classical FL. In this paper, we propose FedFlow: a personalized federated learning framework tailored for PF prediction. The proposed framework encompasses a personalized mechanism meant to refine local models based on client similarities, calculated by only leveraging publicly available domain-dependent information. The proposed framework has been experimentally validated on mobility data collected in a major Italian city, comparing FL predictions obtained by FedFlow against those obtained by LSTM models trained on local data, centralized data, FedAvg, and PerFedAvg. Results show that FedFlow outperforms all the considered adversary techniques. This work demonstrates that our proposal of personalized FL is effective in predicting PF while ensuring data privacy.<\/jats:p>","DOI":"10.1007\/s10994-025-06795-0","type":"journal-article","created":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T10:43:33Z","timestamp":1749638613000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Fedflow: a personalized federated learning framework for passenger flow prediction"],"prefix":"10.1007","volume":"114","author":[{"given":"Franca","family":"Rocco di Torrepadula","sequence":"first","affiliation":[]},{"given":"Marco","family":"Fisichella","sequence":"additional","affiliation":[]},{"given":"Sergio","family":"Di Martino","sequence":"additional","affiliation":[]},{"given":"Nicola","family":"Mazzocca","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,6,11]]},"reference":[{"key":"6795_CR1","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1016\/j.ins.2011.12.028","volume":"191","author":"C Bergmeir","year":"2012","unstructured":"Bergmeir, C., & Ben\u00edtez, J. M. (2012). On the use of cross-validation for time series predictor evaluation. Information Sciences, 191, 192\u2013213.","journal-title":"Information Sciences"},{"key":"6795_CR2","doi-asserted-by":"publisher","DOI":"10.1093\/oso\/9780198538493.001.0001","volume-title":"Neural networks for pattern recognition","author":"CM Bishop","year":"1995","unstructured":"Bishop, C. M. (1995). Neural networks for pattern recognition. Oxford University Press."},{"key":"6795_CR3","volume-title":"Time series analysis, forecasting and control","author":"GEP Box","year":"1990","unstructured":"Box, G. E. P., & Jenkins, G. (1990). Time series analysis, forecasting and control. Holden-Day, Inc."},{"key":"6795_CR4","doi-asserted-by":"crossref","unstructured":"Chen, T., & Guestrin, C. (2016) Xgboost: A scalable tree boosting system. In Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining (pp. 785\u2013794). ACM.","DOI":"10.1145\/2939672.2939785"},{"key":"6795_CR5","doi-asserted-by":"crossref","unstructured":"Cui, Y., Jin, B., Zhang, F., & Sun, X. (2019). A deep spatio-temporal attention-based neural network for passenger flow prediction. In Proceedings of the 16th EAI international conference on mobile and ubiquitous systems: Computing, networking and services (pp. 20\u201330). ACM.","DOI":"10.1145\/3360774.3360807"},{"key":"6795_CR6","unstructured":"European Parliament, Council of the European Union: Regulation (EU) 2016\/679 of the European Parliament and of the Council. https:\/\/data.europa.eu\/eli\/reg\/2016\/679\/oj. Accessed 13 Apr 2023."},{"key":"6795_CR7","first-page":"3557","volume":"33","author":"A Fallah","year":"2020","unstructured":"Fallah, A., Mokhtari, A., & Ozdaglar, A. (2020). Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach. Advances in Neural Information Processing Systems, 33, 3557\u20133568.","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"5","key":"6795_CR8","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1145\/3637868","volume":"56","author":"M Gecer","year":"2024","unstructured":"Gecer, M., & Garbinato, B. (2024). Federated learning for mobility applications. ACM Computing Surveys, 56(5), 133\u2013113328. https:\/\/doi.org\/10.1145\/3637868","journal-title":"ACM Computing Surveys"},{"key":"6795_CR9","doi-asserted-by":"crossref","unstructured":"Gummadi, R., & Edara, S. R. (2018). Analysis of passenger flow prediction of transit buses along a route based on time series. In Information and decision sciences: Proceedings of the 6th international conference on FICTA (pp. 31\u201337). Springer.","DOI":"10.1007\/978-981-10-7563-6_4"},{"issue":"10","key":"6795_CR10","doi-asserted-by":"publisher","first-page":"18155","DOI":"10.1109\/TITS.2022.3150600","volume":"23","author":"Y He","year":"2022","unstructured":"He, Y., Li, L., Zhu, X., & Tsui, K. L. (2022). Multi-graph convolutional-recurrent neural network (MGC-RNN) for short-term forecasting of transit passenger flow. IEEE Transactions on Intelligent Transportation Systems, 23(10), 18155\u201318174.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"8","key":"6795_CR11","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., & Schmidhuber, J. (1997). Long short-term memory. Neural Computation, 9(8), 1735\u20131780.","journal-title":"Neural Computation"},{"key":"6795_CR12","doi-asserted-by":"publisher","unstructured":"Hu, S., Ye, Y., Hu, Q., Liu, X., Cao, S., Yang, H. H., Shen, Y., Angeloudis, P., Parada, L., & Wu, C. (2023). A federated learning-based framework for ride-sourcing traffic demand prediction. IEEE Transactions on Vehicular Technology, 1\u201315. https:\/\/doi.org\/10.1109\/TVT.2023.3287221. Accessed 28 Feb 2024.","DOI":"10.1109\/TVT.2023.3287221"},{"key":"6795_CR13","doi-asserted-by":"crossref","unstructured":"Jiang, Q. (2022). GMM clustering based on WOA optimization and space\u2010time coupled urban rail traffic flow prediction by CEEMD\u2010SE\u2010BiGRU\u2010AM. Mobile Information Systems, 2022(1), 7846630.","DOI":"10.1155\/2022\/7846630"},{"issue":"6","key":"6795_CR14","doi-asserted-by":"publisher","first-page":"4813","DOI":"10.1007\/s00521-021-06669-1","volume":"34","author":"W Jiang","year":"2022","unstructured":"Jiang, W., Ma, Z., & Koutsopoulos, H. N. (2022). Deep learning for short-term origin-destination passenger flow prediction under partial observability in urban railway systems. Neural Computing and Applications, 34(6), 4813\u20134830.","journal-title":"Neural Computing and Applications"},{"key":"6795_CR15","unstructured":"Karimireddy, S. P., Kale, S., Mohri, M., Reddi, S., Stich, S., & Suresh, A. T. (2020). Scaffold: Stochastic controlled averaging for federated learning. In International conference on machine learning (pp. 5132\u20135143). PMLR."},{"key":"6795_CR16","doi-asserted-by":"publisher","unstructured":"Kulkarni, V., Kulkarni, M., & Pant, A. (2020). Survey of personalization techniques for federated learning. In 2020 Fourth world conference on smart trends in systems, security and sustainability (WorldS4) (pp. 794\u2013797). https:\/\/doi.org\/10.1109\/WorldS450073.2020.9210355. https:\/\/ieeexplore.ieee.org\/abstract\/document\/9210355. Accessed 19 Mar 2024.","DOI":"10.1109\/WorldS450073.2020.9210355"},{"key":"6795_CR17","doi-asserted-by":"publisher","unstructured":"Li, C., & Liu, W. (2023). Multimodal transport demand forecasting via federated learning. IEEE Transactions on Intelligent Transportation Systems, 1\u201312. https:\/\/doi.org\/10.1109\/TITS.2023.3325936. Conference Name: IEEE Transactions on Intelligent Transportation Systems. Accessed 08 Feb 2024.","DOI":"10.1109\/TITS.2023.3325936"},{"key":"6795_CR18","doi-asserted-by":"publisher","first-page":"19717","DOI":"10.1109\/ACCESS.2020.2967867","volume":"8","author":"C Li","year":"2020","unstructured":"Li, C., Wang, X., Cheng, Z., & Bai, Y. (2020a). Forecasting bus passenger flows by using a clustering-based support vector regression approach. IEEE Access, 8, 19717\u201319725.","journal-title":"IEEE Access"},{"key":"6795_CR19","doi-asserted-by":"crossref","unstructured":"Li, H.-L., Lin, M.-K., spsampsps Wang, Q.-C. (2020b). Passenger flow prediction model of intercity railway based on G-BP network. In Green, smart and connected transportation systems: Proceedings of the 9th international conference on green intelligent transportation systems and safety (pp. 859\u2013870). Springer.","DOI":"10.1007\/978-981-15-0644-4_67"},{"key":"6795_CR20","doi-asserted-by":"crossref","unstructured":"Li, L., Xu, J., Ng, S. T., Zhang, J., Zhou, S., & Yang, Y. (2020c). Attention-based graph neural network enabled method to predict short-term metro passenger flow. In 2020 5th International conference on universal village (UV) (pp. 1\u20136). IEEE.","DOI":"10.1109\/UV50937.2020.9426223"},{"key":"6795_CR21","doi-asserted-by":"publisher","unstructured":"Liu, Y., Zhang, S., Zhang, C., & Yu, J. J. Q. (2020). FedGRU: Privacy-preserving traffic flow prediction via federated learning. In 2020 IEEE 23rd international conference on intelligent transportation systems (ITSC) (pp. 1\u20136). https:\/\/doi.org\/10.1109\/ITSC45102.2020.9294453. https:\/\/ieeexplore.ieee.org\/abstract\/document\/9294453. Accessed 13 Feb 2024.","DOI":"10.1109\/ITSC45102.2020.9294453"},{"issue":"11","key":"6795_CR22","doi-asserted-by":"publisher","first-page":"7184","DOI":"10.1109\/TITS.2020.3002772","volume":"22","author":"D Luo","year":"2020","unstructured":"Luo, D., Zhao, D., Ke, Q., You, X., Liu, L., Zhang, D., Ma, H., & Zuo, X. (2020). Fine-grained service-level passenger flow prediction for bus transit systems based on multitask deep learning. IEEE Transactions on Intelligent Transportation Systems, 22(11), 7184\u20137199.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"3","key":"6795_CR23","doi-asserted-by":"publisher","first-page":"1644","DOI":"10.3390\/app12031644","volume":"12","author":"J Ma","year":"2022","unstructured":"Ma, J., Zeng, X., Xue, X., & Deng, R. (2022). Metro emergency passenger flow prediction on transfer learning and LSTM model. Applied Sciences, 12(3), 1644.","journal-title":"Applied Sciences"},{"key":"6795_CR24","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. (2017). Communication-efficient learning of deep networks from decentralized data. In Artificial intelligence and statistics (pp. 1273\u20131282). PMLR."},{"key":"6795_CR25","unstructured":"Milenkovi\u0107, M., \u0160vadlenka, L., Melichar, V., Bojovi\u0107, N., & Avramovi\u0107, Z. (2018). SARIMA modelling approach for railway passenger flow forecasting. Transport, 33(5), 1113\u20131120."},{"key":"6795_CR26","doi-asserted-by":"crossref","unstructured":"Nayak, A. M., spsampsps Chaubey, N. (2020). Predicting passenger flow in BTS and MTS using hybrid stacked auto-encoder and softmax regression. In International conference on computing science, communication and security (pp. 29\u201341). Springer.","DOI":"10.1007\/978-981-15-6648-6_3"},{"key":"6795_CR27","doi-asserted-by":"publisher","unstructured":"Rocco Di\u00a0Torrepadula, F., Di\u00a0Martino, S., Mazzocca, N., & Sannino, P. (2024a). A reference architecture for data-driven intelligent public transportation systems. IEEE Open Journal of Intelligent Transportation Systems, 1. https:\/\/doi.org\/10.1109\/OJITS.2024.3441048. Conference Name: IEEE Open Journal of Intelligent Transportation Systems. Accessed 16 Aug 2024.","DOI":"10.1109\/OJITS.2024.3441048"},{"key":"6795_CR28","doi-asserted-by":"publisher","unstructured":"Rocco Di\u00a0Torrepadula, F., Napolitano, E. V., Di\u00a0Martino, S., & Mazzocca, N. (2024b). Machine learning for public transportation demand prediction: A systematic literature review. Engineering Applications of Artificial Intelligence,137. https:\/\/doi.org\/10.1016\/j.engappai.2024.109166. Type: Short survey.","DOI":"10.1016\/j.engappai.2024.109166"},{"key":"6795_CR29","doi-asserted-by":"publisher","unstructured":"Shen, C., Zhu, L., Hua, G., Zhou, L., & Zhang, L. (2020). A blockchain based federal learning method for urban rail passenger flow prediction. In 2020 IEEE 23rd international conference on intelligent transportation systems (ITSC) (pp. 1\u20135). https:\/\/doi.org\/10.1109\/ITSC45102.2020.9294642. https:\/\/ieeexplore.ieee.org\/abstract\/document\/9294642. Accessed 16 Jan 2025.","DOI":"10.1109\/ITSC45102.2020.9294642"},{"key":"6795_CR30","doi-asserted-by":"publisher","unstructured":"Shen, X., Chen, J., Zhu, S., & Yan, R. (2024). A decentralized federated learning-based spatial-temporal model for freight traffic speed forecasting. Expert Systems with Applications,238, 122302. https:\/\/doi.org\/10.1016\/j.eswa.2023.122302. Accessed 25 Mar 2024.","DOI":"10.1016\/j.eswa.2023.122302"},{"key":"6795_CR31","doi-asserted-by":"publisher","unstructured":"Tan, A. Z., Yu, H., Cui, L., & Yang, Q. (2023) Towards personalized federated learning. IEEE Transactions on Neural Networks and Learning Systems,34(12), 9587\u20139603. https:\/\/doi.org\/10.1109\/TNNLS.2022.3160699. Conference Name: IEEE Transactions on Neural Networks and Learning Systems. Accessed 21 Mar 2024.","DOI":"10.1109\/TNNLS.2022.3160699"},{"key":"6795_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2020.103960","volume":"96","author":"T-H Tsai","year":"2020","unstructured":"Tsai, T.-H. (2020). Self-evolutionary sibling models to forecast railway arrivals using reservation data. Engineering Applications of Artificial Intelligence, 96, Article 103960.","journal-title":"Engineering Applications of Artificial Intelligence"},{"issue":"12","key":"6795_CR33","doi-asserted-by":"publisher","first-page":"7891","DOI":"10.1109\/TITS.2021.3072743","volume":"22","author":"J Wang","year":"2021","unstructured":"Wang, J., Zhang, Y., Wei, Y., Hu, Y., Piao, X., & Yin, B. (2021a). Metro passenger flow prediction via dynamic hypergraph convolution networks. IEEE Transactions on Intelligent Transportation Systems, 22(12), 7891\u20137903.","journal-title":"IEEE Transactions on Intelligent Transportation Systems"},{"issue":"12","key":"6795_CR34","doi-asserted-by":"publisher","first-page":"5523","DOI":"10.1007\/s00500-022-07025-8","volume":"26","author":"X Wang","year":"2022","unstructured":"Wang, X., Xu, X., Wu, Y., & Liu, J. (2022). An effective spatiotemporal deep learning framework model for short-term passenger flow prediction. Soft Computing, 26(12), 5523\u20135538.","journal-title":"Soft Computing"},{"issue":"1","key":"6795_CR35","first-page":"1","volume":"13","author":"Y Wang","year":"2021","unstructured":"Wang, Y., Yin, H., Chen, T., Liu, C., Wang, B., Wo, T., & Xu, J. (2021b). Passenger mobility prediction via representation learning for dynamic directed and weighted graphs. ACM Transactions on Intelligent Systems and Technology (TIST), 13(1), 1\u201325.","journal-title":"ACM Transactions on Intelligent Systems and Technology (TIST)"},{"key":"6795_CR36","doi-asserted-by":"publisher","unstructured":"Wu, Q., He, K., & Chen, X. (2020). Personalized federated learning for intelligent IoT applications: A cloud-edge based framework. IEEE Open Journal of the Computer Society,1, 35\u201344. https:\/\/doi.org\/10.1109\/OJCS.2020.2993259. Accessed 25 Mar 2024.","DOI":"10.1109\/OJCS.2020.2993259"},{"key":"6795_CR37","doi-asserted-by":"publisher","unstructured":"Xia, M., Jin, D., & Chen, J. (2023). Short-term traffic flow prediction based on graph convolutional networks and federated learning. IEEE Transactions on Intelligent Transportation Systems,24(1), 1191\u20131203. https:\/\/doi.org\/10.1109\/TITS.2022.3179391. Conference Name: IEEE Transactions on Intelligent Transportation Systems. Accessed 13 Feb 2024.","DOI":"10.1109\/TITS.2022.3179391"},{"key":"6795_CR38","doi-asserted-by":"crossref","unstructured":"Younis, R., & Fisichella, M. (2022). FLY-SMOTE: Re-balancing the non-IID IoT edge devices data in federated learning system. IEEE Access, 10, 65092\u201365102.","DOI":"10.1109\/ACCESS.2022.3184309"},{"key":"6795_CR39","doi-asserted-by":"publisher","unstructured":"Zhang, C., Zhang, S., Yu, J. J. Q., & Yu, S. (2021). FASTGNN: A topological information protected federated learning approach for traffic speed forecasting. IEEE Transactions on Industrial Informatics,17(12), 8464\u20138474. https:\/\/doi.org\/10.1109\/TII.2021.3055283. Conference Name: IEEE Transactions on Industrial Informatics. Accessed 21 Nov 2024.","DOI":"10.1109\/TII.2021.3055283"},{"key":"6795_CR40","doi-asserted-by":"publisher","unstructured":"Zhang, Y., Zeng, D., Luo, J., Fu, X., Chen, G., Xu, Z., & King, I. (2024). A survey of trustworthy federated learning: Issues, solutions, and challenges. ACM Transactions on Intelligent Systems and Technology,15(6), 112\u2013111247. https:\/\/doi.org\/10.1145\/3678181. Accessed 31 Jan 2025.","DOI":"10.1145\/3678181"}],"container-title":["Machine Learning"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06795-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10994-025-06795-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10994-025-06795-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T19:13:54Z","timestamp":1757186034000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10994-025-06795-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,11]]},"references-count":40,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2025,7]]}},"alternative-id":["6795"],"URL":"https:\/\/doi.org\/10.1007\/s10994-025-06795-0","relation":{},"ISSN":["0885-6125","1573-0565"],"issn-type":[{"type":"print","value":"0885-6125"},{"type":"electronic","value":"1573-0565"}],"subject":[],"published":{"date-parts":[[2025,6,11]]},"assertion":[{"value":"7 February 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 February 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"166"}}