{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T10:29:13Z","timestamp":1786357753229,"version":"build-2736575974"},"reference-count":30,"publisher":"MDPI AG","issue":"16","license":[{"start":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T00:00:00Z","timestamp":1786320000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Natural Science Foundation of Zhejiang University of Science and Technology, Zhejiang","award":["2025QN022"],"award-info":[{"award-number":["2025QN022"]}]},{"award":["2025QN022"],"award-info":[{"award-number":["2025QN022"]}],"id":[{"id":"https:\/\/ror.org\/05mx0wr29","id-type":"ROR","asserted-by":"publisher"}]},{"name":"Scientific Research Fund of Zhejiang Provincial Education Department, Zhejiang","award":["Y202454344"],"award-info":[{"award-number":["Y202454344"]}]},{"name":"Natural Science Foundation of Zhejiang Province of Zhejiang","award":["LMS26F020034"],"award-info":[{"award-number":["LMS26F020034"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In some federated learning (FL) scenarios, discrepancies in local client devices result in inconsistent image resolutions, which motivates clients to adopt models with different depths and widths. Existing heterogeneous federated learning methods struggle to maintain model accuracy while preserving computational efficiency. To tackle this issue, this paper proposes a heterogeneous federated learning framework based on optimal transport (OT) and cross-layer alignment. The framework addresses the inconsistency of model depth via cross-layer alignment, fuses parameters of layers with different widths using optimal transport, and develops an aggregation strategy for multiple heterogeneous models. Experiments demonstrate that our method can improve model accuracy by up to 1.65% while maintaining satisfactory efficiency.<\/jats:p>","DOI":"10.3390\/s26165059","type":"journal-article","created":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T09:24:53Z","timestamp":1786353893000},"page":"5059","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimal Transport-Based Heterogeneous Federated Learning for Chest X-Rays"],"prefix":"10.3390","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-3274-3988","authenticated-orcid":false,"given":"Yi","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou 310023, China"},{"name":"Zhejiang Key Laboratory of Biomedical Intelligent Computing Technology, Hangzhou 310023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9386-2536","authenticated-orcid":false,"given":"Haijiang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou 310023, China"},{"name":"Zhejiang Key Laboratory of Biomedical Intelligent Computing Technology, Hangzhou 310023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohong","family":"Qian","sequence":"additional","affiliation":[{"name":"Zhejiang Key Laboratory of Biomedical Intelligent Computing Technology, Hangzhou 310023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9882-3029","authenticated-orcid":false,"given":"Jian","family":"Wan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang Institute of Water Resources and Hydropower Hangzhou, Hangzhou 310018, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou 310023, China"},{"name":"Zhejiang Key Laboratory of Biomedical Intelligent Computing Technology, Hangzhou 310023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9717-8355","authenticated-orcid":false,"given":"Jie","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou 310023, China"},{"name":"Zhejiang Key Laboratory of Biomedical Intelligent Computing Technology, Hangzhou 310023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8786-1910","authenticated-orcid":false,"given":"Yexin","family":"Dou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Zhejiang University of Science and Technology, Hangzhou 310023, China"},{"name":"Zhejiang Key Laboratory of Biomedical Intelligent Computing Technology, Hangzhou 310023, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,8,10]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"128019","DOI":"10.1016\/j.neucom.2024.128019","article-title":"Recent advances on federated learning: A systematic survey","volume":"597","author":"Liu","year":"2024","journal-title":"Neurocomputing"},{"key":"ref_2","unstructured":"(2025, March 23). General Data Protection Regulation. Available online: https:\/\/eur-lex.europa.eu\/legal-content\/EN\/TXT\/?uri=CELEX:32016R0679."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"19188","DOI":"10.1109\/JIOT.2024.3376548","article-title":"Federated learning with non-iid data: A survey","volume":"11","author":"Lu","year":"2024","journal-title":"IEEE Internet Things J."},{"key":"ref_4","unstructured":"McMahan, B. (2017, January 20\u201322). Communication-efficient learning of deep networks from decentralized data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics Artificial Intelligence and Statistics, Lauderdale, FL, USA."},{"key":"ref_5","first-page":"153","article-title":"Federated learning for medical image analysis: Privacy-preserving paradigms and clinical challenges","volume":"1","author":"Hu","year":"2025","journal-title":"Innov. Water Treat."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Dritsas, E., and Trigka, M. (2025). Federated learning for IoT: A survey of techniques, challenges, and applications. J. Sens. Actuator Netw., 14.","DOI":"10.3390\/jsan14010009"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Alhawas, S., and Rassam, M.A. (2026). Federated learning in edge computing: Vulnerabilities, attacks, and defenses\u2014A survey. Sensors, 26.","DOI":"10.3390\/s26041275"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Sampathkumar, V., Pathak, I.P., Ramaraj, D.K., Kotha, R., and Patel, D.P. (2026, January 5\u20137). Federated Explainable AI for Fair and Inclusive Credit Scoring: A Comprehensive Review. Proceedings of the 2026 IEEE 16th Annual Computing and Communication Workshop and Conference (CCWC), Las Vegas, NV, USA.","DOI":"10.1109\/CCWC67433.2026.11393798"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Alterkawi, L., and Dib, F.K. (2025). Federated Learning for Smart Cities: A Thematic Review of Challenges and Approaches. Future Internet, 17.","DOI":"10.3390\/fi17120545"},{"key":"ref_10","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"key":"ref_11","first-page":"5132","article-title":"Scaffold: Stochastic controlled averaging for federated learning","volume":"119","author":"Karimireddy","year":"2020","journal-title":"Int. Conf. Mach. Learn."},{"key":"ref_12","unstructured":"Reddi, S. (2020). Adaptive federated optimization. arXiv."},{"key":"ref_13","unstructured":"Yao, Y., Wang, L., Wu, J., Song, J., Chen, S., Wang, Z., Tian, Z., Chen, W., Li, H., and Li, X. (2025). FedRE: A Representation Entanglement Framework for Model-Heterogeneous Federated Learning. arXiv."},{"key":"ref_14","unstructured":"Li, D. (2019). Fedmd: Heterogenous federated learning via model distillation. arXiv."},{"key":"ref_15","first-page":"23256","article-title":"FedCD: Towards Consolidated Distillation for Heterogeneous Federated Learning","volume":"40","author":"Li","year":"2026","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Zhang, J. (2022). Dense: Data-free one-shot federated learning. arXiv.","DOI":"10.52202\/068431-1556"},{"key":"ref_17","unstructured":"Niu, Z., Dong, H., and Qin, A.K. (2026, January 23). Bridging generalization gap of heterogeneous federated clients using generative models. Proceedings of the Fourteenth International Conference on Learning Representations, Rio de Janeiro, Brazil."},{"key":"ref_18","unstructured":"Cuturi, M. (2013, January 5\u20138). Sinkhorn distances: Lightspeed computation of optimal transport. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1853","DOI":"10.1109\/TPAMI.2016.2615921","article-title":"Optimal transport for domain adaptation","volume":"39","author":"Courty","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Yan, Y. (2018, January 13\u201319). Semi-Supervised Optimal Transport for Heterogeneous Domain Adaptation. Proceedings of the IJCAI, Stockholm, Sweden.","DOI":"10.24963\/ijcai.2018\/412"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"1667","DOI":"10.1109\/JAS.2024.124344","article-title":"Low-rank optimal transport for robust domain adaptation","volume":"11","author":"Xu","year":"2024","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"4159","DOI":"10.1007\/s10994-022-06231-7","article-title":"Hierarchical optimal transport for unsupervised domain adaptation","volume":"111","author":"Hamri","year":"2022","journal-title":"Mach. Learn."},{"key":"ref_23","unstructured":"Singh, S.P. (2020, January 6\u201312). Model fusion via optimal transport. Proceedings of the Advances in Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2166","DOI":"10.1109\/JIOT.2023.3293230","article-title":"Optimal transport-based one-shot federated learning for Artificial Intelligence of Things","volume":"11","author":"Chiang","year":"2023","journal-title":"IEEE Internet Things J."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Zhou, M. (2024). FedSKF: Selective Knowledge Fusion via Optimal Transport in Federated Class Incremental Learning. Electronics, 13.","DOI":"10.3390\/electronics13091772"},{"key":"ref_26","unstructured":"Imfeld, M. (2023). Transformer fusion with optimal transport. arXiv."},{"key":"ref_27","first-page":"3519","article-title":"Similarity of Neural Network Representations","volume":"97","author":"Kornblith","year":"2019","journal-title":"Proc. Mach. Learn. Res."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Khoiriyah, S.A. (2020, January 29\u201330). Convolutional neural network for automatic pneumonia detection in chest radiography. Proceedings of the 2020 International Electronics Symposium (IES), Surabaya, Indonesia.","DOI":"10.1109\/IES50839.2020.9231540"},{"key":"ref_29","unstructured":"Simonyan, K. (2014). Very deep convolutional networks for large-scale image recognition. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Ahmed, R., Maddikunta, P.K.R., Gadekallu, T.R., Alshammari, N.K., and Hendaoui, F.A. (2024). Efficient differential privacy enabled federated learning model for detecting COVID-19 disease using chest X-ray images. Front. Med., 11.","DOI":"10.3389\/fmed.2024.1409314"}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5059\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,10]],"date-time":"2026-08-10T09:38:01Z","timestamp":1786354681000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/16\/5059"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,10]]},"references-count":30,"journal-issue":{"issue":"16","published-online":{"date-parts":[[2026,8]]}},"alternative-id":["s26165059"],"URL":"https:\/\/doi.org\/10.3390\/s26165059","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,10]]}}}