{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:48:03Z","timestamp":1782841683134,"version":"3.54.5"},"reference-count":60,"publisher":"Association for Computing Machinery (ACM)","issue":"2","license":[{"start":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T00:00:00Z","timestamp":1782777600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/legalcode"}],"funder":[{"name":"Future Artificial Intelligence Research (FAIR) project","award":["PE0000013-FAIR"],"award-info":[{"award-number":["PE0000013-FAIR"]}]},{"DOI":"10.13039\/501100003196","name":"Italian Ministry of Health","doi-asserted-by":"crossref","award":["PNRR PNC-E3-2022-23683266 PNC-HLS-DA, INNOVA-CUP: E63C22003780001"],"award-info":[{"award-number":["PNRR PNC-E3-2022-23683266 PNC-HLS-DA, INNOVA-CUP: E63C22003780001"]}],"id":[{"id":"10.13039\/501100003196","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100000780","name":"European Union","doi-asserted-by":"crossref","award":["101071179"],"award-info":[{"award-number":["101071179"]}],"id":[{"id":"10.13039\/501100000780","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Evol. Learn. Optim."],"published-print":{"date-parts":[[2026,6,30]]},"abstract":"<jats:p>\n                    In the past few years, Federated Learning (FL) has emerged as an effective approach for training Neural Networks (NNs) over a computing network while preserving data privacy. Most existing FL approaches require defining\n                    <jats:italic toggle=\"yes\">a priori<\/jats:italic>\n                    (1) a predefined structure for all the NNs running on the clients and (2) an explicit aggregation procedure. These can be limiting factors in cases where predefining such algorithmic details is difficult. Recently, NEvoFed was proposed, an FL method that leverages Neuroevolution running on the clients, in which the NN structures are heterogeneous and the aggregation is implicitly accomplished on the client side. Here, we propose MFC-NEvoFed, a novel approach to FL that does not require learning models, i.e., neural network parameters, to be distributed over the networks, thus taking a step toward security improvement. The only information exchanged in client\/server communication is the performance of each model on local data, allowing the emergence of optimal NN architectures without needing any kind of model aggregation. Another appealing feature of our framework is that it can be used with any Machine Learning algorithm provided that, during the learning phase, the model updates do not depend on the input data. To assess the validity of MFC-NEvoFed, we test it on four datasets, showing that very compact NNs can be obtained without drops in performance compared to canonical FL. Finally, such compact structures allow for a step toward explainability, which is highly desirable in domains such as digital health, from which the tested datasets come.\n                  <\/jats:p>","DOI":"10.1145\/3745032","type":"journal-article","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T11:56:36Z","timestamp":1750679796000},"page":"1-34","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Model-Free-Communication Federated Neuroevolution"],"prefix":"10.1145","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1652-1690","authenticated-orcid":false,"given":"Leonardo Lucio","family":"Custode","sequence":"first","affiliation":[{"name":"Independent Researcher, Fisciano, SA, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9723-1830","authenticated-orcid":false,"given":"Giovanni","family":"Iacca","sequence":"additional","affiliation":[{"name":"University of Trento, Trento, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6127-1195","authenticated-orcid":false,"given":"Ivanoe","family":"De Falco","sequence":"additional","affiliation":[{"name":"Institute for High Performance Computing and Networking (ICAR), National Research Council of Italy (CNR), Naples, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6410-6404","authenticated-orcid":false,"given":"Umberto","family":"Scafuri","sequence":"additional","affiliation":[{"name":"Institute for High Performance Computing and Networking (ICAR), National Research Council of Italy (CNR), Naples, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4092-6102","authenticated-orcid":false,"given":"Antonio","family":"Della Cioppa","sequence":"additional","affiliation":[{"name":"NCLab, Department of Information Engineering, Electrical Engineering, and Applied Mathematics, University of Salerno, Fisciano, SA, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,30]]},"reference":[{"key":"e_1_3_2_2_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-96896-0_4"},{"key":"e_1_3_2_3_1","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2152"},{"key":"e_1_3_2_4_1","doi-asserted-by":"publisher","DOI":"10.12688\/wellcomeopenres.15191.2"},{"key":"e_1_3_2_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10710-018-9339-y"},{"key":"e_1_3_2_6_1","unstructured":"Mahdi Beitollahi Alex Bie Sobhan Hemati Leo Maxime Brunswic Xu Li Xi Chen and Guojun Zhang. 2024. Parametric feature transfer: One-shot federated learning with foundation models. arXiv:2402.01862. Retrieved from https:\/\/arxiv.org\/abs\/2402.01862"},{"issue":"2","key":"e_1_3_2_7_1","first-page":"281","article-title":"Random search for hyper-parameter optimization","volume":"13","author":"Bergstra James","year":"2012","unstructured":"James Bergstra and Yoshua Bengio. 2012. Random search for hyper-parameter optimization. Journal of Machine Learning Research 13, 2 (2012), 281\u2013305.","journal-title":"Journal of Machine Learning Research"},{"key":"e_1_3_2_8_1","unstructured":"Daniel J. Beutel Taner Topal Akhil Mathur Xinchi Qiu Javier Fernandez-Marques Yan Gao Lorenzo Sani Hei Li Kwing Titouan Parcollet Pedro PB de Gusm\u00e3o et al. 2020. Flower: A friendly federated learning research framework. arXiv:2007.14390. Retrieved from https:\/\/arxiv.org\/abs\/2007.14390"},{"key":"e_1_3_2_9_1","doi-asserted-by":"crossref","first-page":"119","DOI":"10.1007\/978-3-030-29933-0_10","volume-title":"Advances in Computational Intelligence Systems: Contributions Presented at the 19th UK Workshop on Computational Intelligence","author":"Byla Edvinas","year":"2020","unstructured":"Edvinas Byla and Wei Pang. 2020. Deepswarm: Optimising convolutional neural networks using swarm intelligence. In Advances in Computational Intelligence Systems: Contributions Presented at the 19th UK Workshop on Computational Intelligence. Springer, Cham, Switzerland, 119\u2013130."},{"key":"e_1_3_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12065-022-00718-x"},{"key":"e_1_3_2_11_1","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1145\/3638529.3654029","volume-title":"Genetic and Evolutionary Computation Conference","author":"Custode Leonardo Lucio","year":"2024","unstructured":"Leonardo Lucio Custode, Ivanoe De Falco, Antonio Della Cioppa, Giovanni Iacca, and Umberto Scafuri. 2024. NEvoFed: A decentralized approach to federated neuroevolution of heterogeneous neural networks. In Genetic and Evolutionary Computation Conference. ACM, New York, NY, 295\u2013303."},{"key":"e_1_3_2_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2023.105416"},{"key":"e_1_3_2_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23062957"},{"key":"e_1_3_2_14_1","doi-asserted-by":"publisher","DOI":"10.5555\/1248547.1248548"},{"key":"e_1_3_2_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2011.02.002"},{"key":"e_1_3_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01064"},{"key":"e_1_3_2_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2009.12.010"},{"key":"e_1_3_2_18_1","first-page":"19","article-title":"Privacy and security in federated learning: A survey","volume":"12","author":"Gosselin R\u00e9mi","year":"2022","unstructured":"R\u00e9mi Gosselin, Lo\u00efc Vieu, Faiza Loukil, and Alexandre Benoit. 2022. Privacy and security in federated learning: A survey. Applied Sciences 12, 19 (2022), 15 pages.","journal-title":"Applied Sciences"},{"key":"e_1_3_2_19_1","unstructured":"Neel Guha Ameet Talwalkar and Virginia Smith. 2019. One-shot federated learning. arXiv:1902.11175. Retrieved from https:\/\/arxiv.org\/abs\/1902.11175"},{"key":"e_1_3_2_20_1","unstructured":"Geoffrey Hinton Oriol Vinyals and Jeff Dean. 2015. Distilling the knowledge in a neural network. arXiv:1503.02531. Retrieved from https:\/\/arxiv.org\/abs\/1503.02531"},{"key":"e_1_3_2_21_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aac4520"},{"key":"e_1_3_2_22_1","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-013-1091-x"},{"key":"e_1_3_2_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02119-1"},{"key":"e_1_3_2_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2011.05.001"},{"key":"e_1_3_2_25_1","unstructured":"Jakub Kone\u010dn\u1ef3 Brendan McMahan and Daniel Ramage. 2015. Federated optimization: Distributed optimization beyond the datacenter. arXiv:1511.03575. Retrieved from https:\/\/arxiv.org\/abs\/1511.03575"},{"key":"e_1_3_2_26_1","unstructured":"Jakub Kone\u010dn\u1ef3 Brendan McMahan Daniel Ramage and Peter Richt\u00e1rik. 2016. Federated optimization: Distributed machine learning for on-device intelligence. arXiv:1610.02527. Retrieved from https:\/\/arxiv.org\/abs\/1610.02527"},{"key":"e_1_3_2_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2023.02.021"},{"key":"e_1_3_2_28_1","first-page":"367","volume-title":"Uncertainty in Artificial Intelligence","author":"Li Liam","year":"2020","unstructured":"Liam Li and Ameet Talwalkar. 2020. Random search and reproducibility for neural architecture search. In Uncertainty in Artificial Intelligence. PMLR, Tel Aviv, Israel, 367\u2013377."},{"key":"e_1_3_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/IOTM.001.2100179"},{"key":"e_1_3_2_30_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21237853"},{"key":"e_1_3_2_31_1","first-page":"1540","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Lorraine Jonathan","year":"2020","unstructured":"Jonathan Lorraine, Paul Vicol, and David Duvenaud. 2020. Optimizing millions of hyperparameters by implicit differentiation. In International Conference on Artificial Intelligence and Statistics. PMLR, Palermo, Italy, 1540\u20131552."},{"key":"e_1_3_2_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3321707.3321729"},{"key":"e_1_3_2_33_1","first-page":"10082","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ma Xiaosong","year":"2022","unstructured":"Xiaosong Ma, Jie Zhang, Song Guo, and Wenchao Xu. 2022. Layer-wised model aggregation for personalized federated learning. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, New York, NY, 10082\u201310091."},{"key":"e_1_3_2_34_1","first-page":"71","volume-title":"CEUR Workshop Proceedings","author":"Marling Cindy","year":"2020","unstructured":"Cindy Marling and Razvan Bunescu. 2020. The OhioT1DM dataset for blood glucose level prediction: Update 2020. In CEUR Workshop Proceedings, Vol. 2675. CEUR-WS.org, Aachen, Germany, 71."},{"key":"e_1_3_2_35_1","unstructured":"Alan McIntyre Matt Kallada Cesar G. Miguel and Carolina Feher da Silva. 2019. NEAT-Python. Retrieved from https:\/\/github.com\/CodeReclaimers\/neat-python"},{"key":"e_1_3_2_36_1","unstructured":"Alan McIntyre Matt Kallada Cesar G. Miguel and Carolina Feher da Silva. 2020. NEAT-Python Documentation: Configuration file description. Retrieved fromhttps:\/\/neat-python.readthedocs.io\/en\/latest\/config_file.html"},{"key":"e_1_3_2_37_1","first-page":"8188","volume-title":"International Joint Conference on Artificial Intelligence","author":"Mora Alessio","year":"2024","unstructured":"Alessio Mora, Irene Tenison, Paolo Bellavista, and Irina Rish. 2024. Knowledge distillation in federated learning: A practical guide. In International Joint Conference on Artificial Intelligence. International Joint Conferences on Artificial Intelligence Organization, Santa Clara, CA, 8188\u20138196."},{"key":"e_1_3_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-02462-7_21"},{"key":"e_1_3_2_39_1","doi-asserted-by":"publisher","DOI":"10.3390\/s21020600"},{"key":"e_1_3_2_40_1","first-page":"255","volume-title":"Computers in Cardiology","author":"Penzel Thomas","year":"2000","unstructured":"Thomas Penzel, George B. Moody, Roger G. Mark, Ary L. Goldberger, and J. Hermann Peter. 2000. The apnea-ECG database. In Computers in Cardiology, Vol. 27. IEEE, New York, NY, 255\u2013258."},{"key":"e_1_3_2_41_1","unstructured":"David M. W. Powers. 2020. Evaluation: From precision recall and F-measure to ROC informedness markedness and correlation. arXiv:2010.16061. Retrieved from https:\/\/arxiv.org\/abs\/2010.16061"},{"key":"e_1_3_2_42_1","first-page":"14","volume-title":"Advances in Neural Information Processing Systems","author":"Rahimi Mohammad Mahdi","year":"2023","unstructured":"Mohammad Mahdi Rahimi, Hasnain Irshad Bhatti, Younghyun Park, Humaira Kousar, Do-Yeon Kim, and Jaekyun Moon. 2023. EvoFed: Leveraging evolutionary strategies for communication-efficient federated learning. In Advances in Neural Information Processing Systems. Neural Information Processing Systems Foundation, San Diego, CA, 14 pages."},{"key":"e_1_3_2_43_1","first-page":"63","volume-title":"Summer School on Machine Learning","author":"Rasmussen Carl Edward","year":"2003","unstructured":"Carl Edward Rasmussen. 2003. Gaussian processes in machine learning. In Summer School on Machine Learning. Springer, Berlin, Germany, 63\u201371."},{"key":"e_1_3_2_44_1","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1007\/BFb0055930","volume-title":"Genetic Programming","author":"Ryan Conor","year":"1998","unstructured":"Conor Ryan, J. J. Collins, and Michael O. Neill. 1998. Grammatical evolution: Evolving programs for an arbitrary language. In Genetic Programming. Wolfgang Banzhaf, Riccardo Poli, Marc Schoenauer, and Terence C. Fogarty (Eds.). Springer, Berlin, 83\u201396."},{"key":"e_1_3_2_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbi.2014.02.015"},{"key":"e_1_3_2_46_1","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-018-0006-z"},{"key":"e_1_3_2_47_1","doi-asserted-by":"publisher","DOI":"10.1162\/106365602320169811"},{"key":"e_1_3_2_48_1","first-page":"1379","volume-title":"31st USENIX Security Symposium","author":"Stevens Timothy","year":"2022","unstructured":"Timothy Stevens, Christian Skalka, Christelle Vincent, John Ring, Samuel Clark, and Joseph Near. 2022. Efficient differentially private secure aggregation for federated learning via hardness of learning with errors. In 31st USENIX Security Symposium. USENIX, Berkeley, CA, 1379\u20131395."},{"key":"e_1_3_2_49_1","unstructured":"Kevin Swersky Jasper Snoek and Ryan Prescott Adams. 2014. Freeze-thaw Bayesian optimization. arXiv:1406.3896. Retrieved from https:\/\/arxiv.org\/abs\/1406.3896"},{"key":"e_1_3_2_50_1","first-page":"71","volume-title":"Information Technologies - Applications and Theory","author":"Szegedi G\u00e1bor","year":"2019","unstructured":"G\u00e1bor Szegedi, P\u00e9ter Kiss, and Tom\u00e1s Horv\u00e1th. 2019. Evolutionary federated learning on EEG-data. In Information Technologies - Applications and Theory. CEUR-WS.org, Aachen, Germany, 71\u201378."},{"key":"e_1_3_2_51_1","doi-asserted-by":"publisher","DOI":"10.3390\/s23052368"},{"key":"e_1_3_2_52_1","first-page":"12965","volume-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Wan Alvin","year":"2020","unstructured":"Alvin Wan, Xiaoliang Dai, Peizhao Zhang, Zijian He, Yuandong Tian, Saining Xie, Bichen Wu, Matthew Yu, Tao Xu, Kan Chen, et al. 2020. FBNetV2: Differentiable neural architecture search for spatial and channel dimensions. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition. IEEE, New York, NY, 12965\u201312974."},{"key":"e_1_3_2_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2988575"},{"key":"e_1_3_2_54_1","unstructured":"Timothy Yang Galen Andrew Hubert Eichner Haicheng Sun Wei Li Nicholas Kong Daniel Ramage and Fran\u00e7oise Beaufays. 2018. Applied federated learning: Improving Google keyboard query suggestions. arXiv:1812.02903. Retrieved from https:\/\/arxiv.org\/abs\/1812.02903"},{"key":"e_1_3_2_55_1","first-page":"21414","volume-title":"Advances in Neural Information Processing Systems","author":"Zhang Jie","year":"2022","unstructured":"Jie Zhang, Chen Chen, Bo Li, Lingjuan Lyu, Shuang Wu, Shouhong Ding, Chunhua Shen, and Chao Wu. 2022. DENSE: Data-free one-shot federated learning. In Advances in Neural Information Processing Systems. S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, and A. Oh (Eds.), Vol. 35. Curran Associates, Inc., New York, NY, 21414\u201321428."},{"key":"e_1_3_2_56_1","first-page":"1304","volume-title":"IEEE\/CVF International Conference on Computer Vision","author":"Zheng Xiawu","year":"2019","unstructured":"Xiawu Zheng, Rongrong Ji, Lang Tang, Baochang Zhang, Jianzhuang Liu, and Qi Tian. 2019. Multinomial distribution learning for effective neural architecture search. In IEEE\/CVF International Conference on Computer Vision. IEEE, New York, NY, 1304\u20131313."},{"issue":"7","key":"e_1_3_2_57_1","doi-asserted-by":"crossref","first-page":"2314","DOI":"10.1109\/TPAMI.2020.2969193","article-title":"BlockQNN: Efficient block-wise neural network architecture generation","volume":"43","author":"Zhong Zhao","year":"2020","unstructured":"Zhao Zhong, Zichen Yang, Boyang Deng, Junjie Yan, Wei Wu, Jing Shao, and Cheng-Lin Liu. 2020. BlockQNN: Efficient block-wise neural network architecture generation. IEEE Transactions on Pattern Analysis and Machine Intelligence 43, 7 (2020), 2314\u20132328.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"issue":"4","key":"e_1_3_2_58_1","first-page":"1310","article-title":"Multi-objective evolutionary federated learning","volume":"31","author":"Zhu Hangyu","year":"2019","unstructured":"Hangyu Zhu and Yaochu Jin. 2019. Multi-objective evolutionary federated learning. IEEE Transactions on Neural Networks and Learning Systems 31, 4 (2019), 1310\u20131322.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_2_59_1","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2021.3099448"},{"key":"e_1_3_2_60_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40747-020-00247-z"},{"key":"e_1_3_2_61_1","first-page":"16","volume-title":"International Conference on Learning Representations","author":"Zoph Barret","year":"2017","unstructured":"Barret Zoph and Quoc Le. 2017. Neural architecture search with reinforcement learning. In International Conference on Learning Representations, 16 pages."}],"container-title":["ACM Transactions on Evolutionary Learning and Optimization"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3745032","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T17:15:25Z","timestamp":1782839725000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3745032"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,30]]},"references-count":60,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6,30]]}},"alternative-id":["10.1145\/3745032"],"URL":"https:\/\/doi.org\/10.1145\/3745032","relation":{},"ISSN":["2688-299X","2688-3007"],"issn-type":[{"value":"2688-299X","type":"print"},{"value":"2688-3007","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,30]]},"assertion":[{"value":"2024-12-04","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2025-06-09","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}