{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T00:13:22Z","timestamp":1768004002985,"version":"3.49.0"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T00:00:00Z","timestamp":1698451200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T00:00:00Z","timestamp":1698451200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100009093","name":"Scuola Normale Superiore","doi-asserted-by":"crossref","id":[{"id":"10.13039\/100009093","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SN COMPUT. SCI."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Federated learning (FL) is a framework for training machine learning models in a distributed and collaborative manner. During training, a set of participating clients process their data stored locally, sharing only updates of the statistical model\u2019s parameters obtained by minimizing a cost function over their local inputs. FL was proposed as a stepping-stone towards privacy-preserving machine learning, but it has been shown to expose clients to issues such as leakage of private information, lack of personalization of the model, and the possibility of having a trained model that is fairer to some groups of clients than to others. In this paper, the focus is on addressing the triadic interaction among personalization, privacy guarantees, and fairness attained by trained models within the FL framework. Differential privacy and its variants have been studied and applied as cutting-edge standards for providing formal privacy guarantees. However, clients in FL often hold very diverse datasets representing heterogeneous communities, making it important to protect their sensitive and personal information while still ensuring that the trained model upholds the aspect of fairness for the users. To attain this objective, a method is put forth that introduces group privacy assurances through the utilization of<jats:italic>d<\/jats:italic>-privacy (aka metric privacy).<jats:italic>d<\/jats:italic>-privacy represents a localized form of differential privacy that relies on a metric-oriented obfuscation approach to maintain the original data\u2019s topological distribution. This method, besides enabling personalized model training in a federated approach and providing formal privacy guarantees, possesses significantly better group fairness measured under a variety of standard metrics than a global model trained within a classical FL template. Theoretical justifications for the applicability are provided, as well as experimental validation on real-world datasets to illustrate the working of the proposed method.<\/jats:p>","DOI":"10.1007\/s42979-023-02292-0","type":"journal-article","created":{"date-parts":[[2023,10,28]],"date-time":"2023-10-28T06:02:28Z","timestamp":1698472948000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["Advancing Personalized Federated Learning: Group Privacy, Fairness, and Beyond"],"prefix":"10.1007","volume":"4","author":[{"given":"Filippo","family":"Galli","sequence":"first","affiliation":[]},{"given":"Kangsoo","family":"Jung","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2115-1495","authenticated-orcid":false,"given":"Sayan","family":"Biswas","sequence":"additional","affiliation":[]},{"given":"Catuscia","family":"Palamidessi","sequence":"additional","affiliation":[]},{"given":"Tommaso","family":"Cucinotta","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,28]]},"reference":[{"key":"2292_CR1","unstructured":"Le\u00a0M\u00e9tayer D, De S.J. PRIAM: a Privacy Risk Analysis Methodology. In: Livraga, G., Torra, V., Aldini, A., Martinelli, F., Suri, N. (eds.) Data Privacy Management and Security Assurance. Springer, Heraklion, Greece 2016. https:\/\/hal.inria.fr\/hal-01420983"},{"key":"2292_CR2","unstructured":"NIST: NIST Privacy Framework Core 2021. https:\/\/www.nist.gov\/system\/files\/documents\/2021\/05\/05\/NIST-Privacy-Framework-V1.0-Core-PDF.pdf"},{"key":"2292_CR3","unstructured":"McMahan B, Moore E, Ramage D, Hampson S, Arcas B.A. Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, 2017;pp. 1273\u20131282. PMLR"},{"key":"2292_CR4","first-page":"19586","volume":"33","author":"A Ghosh","year":"2020","unstructured":"Ghosh A, Chung J, Yin D, Ramchandran K. An efficient framework for clustered federated learning. Adv Neural Inf Process Syst. 2020;33:19586\u201397.","journal-title":"Adv Neural Inf Process Syst"},{"key":"2292_CR5","unstructured":"Mansour Y, Mohri M, Ro J, Suresh A.T. Three approaches for personalization with applications to federated learning. arXiv preprint arXiv:2002.10619 2020."},{"issue":"8","key":"2292_CR6","doi-asserted-by":"publisher","first-page":"3710","DOI":"10.1109\/TNNLS.2020.3015958","volume":"32","author":"F Sattler","year":"2020","unstructured":"Sattler F, M\u00fcller K-R, Samek W. Clustered federated learning: Model-agnostic distributed multitask optimization under privacy constraints. IEEE transactions on neural networks and learning systems. 2020;32(8):3710\u201322.","journal-title":"IEEE transactions on neural networks and learning systems"},{"key":"2292_CR7","doi-asserted-by":"crossref","unstructured":"Hitaj B, Ateniese G, Perez-Cruz F. Deep models under the gan: information leakage from collaborative deep learning. In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, 2017;pp. 603\u2013618.","DOI":"10.1145\/3133956.3134012"},{"key":"2292_CR8","doi-asserted-by":"crossref","unstructured":"Nasr M, Shokri R, Houmansadr A. Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning. In: 2019 IEEE Symposium on Security and Privacy (SP), 2019;pp. 739\u2013753. IEEE","DOI":"10.1109\/SP.2019.00065"},{"key":"2292_CR9","unstructured":"Zhu L, Liu Z, Han S. Deep leakage from gradients. Advances in Neural Information Processing Systems 2019;32."},{"key":"2292_CR10","doi-asserted-by":"publisher","first-page":"265","DOI":"10.1007\/11681878_14","volume-title":"Theory of Cryptography","author":"C Dwork","year":"2006","unstructured":"Dwork C, McSherry F, Nissim K, Smith A. Calibrating noise to sensitivity in private data analysis. In: Halevi S, Rabin T, editors. Theory of Cryptography. Berlin, Heidelberg: Springer; 2006. p. 265\u201384."},{"key":"2292_CR11","doi-asserted-by":"publisher","first-page":"486","DOI":"10.1007\/11761679_29","volume-title":"Advances in Cryptology - EUROCRYPT 2006","author":"C Dwork","year":"2006","unstructured":"Dwork C, Kenthapadi K, McSherry F, Mironov I, Naor M. Our data, ourselves: Privacy via distributed noise generation. In: Vaudenay S, editor. Advances in Cryptology - EUROCRYPT 2006. Berlin, Heidelberg: Springer; 2006. p. 486\u2013503."},{"key":"2292_CR12","unstructured":"Andrew G, Thakkar O, McMahan B, Ramaswamy S. Differentially private learning with adaptive clipping. Advances in Neural Information Processing Systems 2021; 34."},{"key":"2292_CR13","unstructured":"McMahan H.B, Ramage D, Talwar K, Zhang L. Learning differentially private recurrent language models. In: International Conference on Learning Representations 2018. https:\/\/openreview.net\/forum?id=BJ0hF1Z0b"},{"key":"2292_CR14","doi-asserted-by":"crossref","unstructured":"Truex S, Liu L, Chow K.-H, Gursoy M.E, Wei W. Ldp-fed: Federated learning with local differential privacy. In: Proceedings of the Third ACM International Workshop on Edge Systems, Analytics and Networking, 2020; pp. 61\u201366.","DOI":"10.1145\/3378679.3394533"},{"issue":"11","key":"2292_CR15","doi-asserted-by":"publisher","first-page":"8836","DOI":"10.1109\/JIOT.2020.3037194","volume":"8","author":"Y Zhao","year":"2020","unstructured":"Zhao Y, Zhao J, Yang M, Wang T, Wang N, Lyu L, Niyato D, Lam K-Y. Local differential privacy-based federated learning for internet of things. IEEE Internet Things J. 2020;8(11):8836\u201353.","journal-title":"IEEE Internet Things J"},{"key":"2292_CR16","doi-asserted-by":"crossref","unstructured":"Chatzikokolakis K, Andr\u00e9s M.E, Bordenabe N.E, Palamidessi C. Broadening the scope of differential privacy using metrics. In: International Symposium on Privacy Enhancing Technologies Symposium, 2013; pp. 82\u2013102. Springer","DOI":"10.1007\/978-3-642-39077-7_5"},{"key":"2292_CR17","doi-asserted-by":"crossref","unstructured":"Biswas S, Palamidessi C. PRIVIC: A privacy-preserving method for incremental collection of location data 2023.","DOI":"10.56553\/popets-2024-0033"},{"key":"2292_CR18","doi-asserted-by":"publisher","unstructured":"Fernandes N, McIver A, Palamidessi C, Ding M. Universal optimality and robust utility bounds for metric differential privacy. In: 2022 IEEE 35th Computer Security Foundations Symposium (CSF), 2022; pp. 348\u2013363 . https:\/\/doi.org\/10.1109\/CSF54842.2022.9919647","DOI":"10.1109\/CSF54842.2022.9919647"},{"key":"2292_CR19","unstructured":"Atmaca U.I, Biswas S, Maple C, Palamidessi C. A privacy preserving querying mechanism with high utility for electric vehicles 2022."},{"key":"2292_CR20","doi-asserted-by":"publisher","unstructured":"Galli F, Biswas S, Jung K, Cucinotta T, Palamidessi C. Group Privacy for Personalized Federated Learning. In: Proceedings of the 9th International Conference on Information Systems Security and Privacy - ICISSP, 2023; pp. 252\u2013263 . https:\/\/doi.org\/10.5220\/0011885000003405 . SciTePress - INSTICC","DOI":"10.5220\/0011885000003405"},{"issue":"1","key":"2292_CR21","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1177\/0049124118782533","volume":"50","author":"R Berk","year":"2021","unstructured":"Berk R, Heidari H, Jabbari S, Kearns M, Roth A. Fairness in criminal justice risk assessments: The state of the art. Sociological Methods & Research. 2021;50(1):3\u201344.","journal-title":"Sociological Methods & Research"},{"issue":"2","key":"2292_CR22","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1089\/big.2016.0047","volume":"5","author":"A Chouldechova","year":"2017","unstructured":"Chouldechova A. Fair prediction with disparate impact: A study of bias in recidivism prediction instruments. Big data. 2017;5(2):153\u201363.","journal-title":"Big data"},{"key":"2292_CR23","unstructured":"Agarwal S. Trade-Offs between fairness and privacy in machine learning. IJCAI 2021 Workshop on AI for Social Good. 2022; 2021."},{"key":"2292_CR24","doi-asserted-by":"crossref","unstructured":"Verma S, Rubin J. Fairness definitions explained. In: Proceedings of the International Workshop on Software Fairness, 2018; pp. 1\u20137.","DOI":"10.1145\/3194770.3194776"},{"key":"2292_CR25","doi-asserted-by":"publisher","DOI":"10.3386\/w15057","volume-title":"Measuring discrimination in education","author":"R Hanna","year":"2009","unstructured":"Hanna R, Linden L. Measuring discrimination in education. National Bureau of Economic Research: Technical report; 2009."},{"issue":"1","key":"2292_CR26","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1145\/3468507.3468511","volume":"23","author":"K Makhlouf","year":"2021","unstructured":"Makhlouf K, Zhioua S, Palamidessi C. On the applicability of machine learning fairness notions. ACM SIGKDD Explorations Newsl. 2021;23(1):14\u201323.","journal-title":"ACM SIGKDD Explorations Newsl"},{"key":"2292_CR27","doi-asserted-by":"crossref","unstructured":"Dwork C, Hardt M, Pitassi T, Reingold O, Zemel R. Fairness through awareness. In: Proceedings of the 3rd Innovations in Theoretical Computer Science Conference, 2012; pp. 214\u2013226.","DOI":"10.1145\/2090236.2090255"},{"key":"2292_CR28","unstructured":"Hardt M, Price E, Srebro N. Equality of opportunity in supervised learning. Advances in neural information processing systems 2016; 29."},{"key":"2292_CR29","doi-asserted-by":"crossref","unstructured":"Abadi M, Chu A, Goodfellow I, McMahan H.B, Mironov I, Talwar K, Zhang L. Deep learning with differential privacy. In: Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, 2016; pp. 308\u2013318.","DOI":"10.1145\/2976749.2978318"},{"key":"2292_CR30","unstructured":"Geyer R.C, Klein T, Nabi M. Differentially private federated learning: A client level perspective. arXiv preprint arXiv:1712.07557 2017."},{"key":"2292_CR31","unstructured":"Bonawitz K.A, Ivanov V, Kreuter B, Marcedone A, McMahan H.B, Patel S, Ramage D, Segal A, Seth K. Practical secure aggregation for federated learning on user-held data. In: NIPS Workshop on Private Multi-Party Machine Learning 2016 . https:\/\/arxiv.org\/abs\/1611.04482"},{"key":"2292_CR32","unstructured":"Agarwal N, Suresh A.T, Yu F.X.X, Kumar S, McMahan B. cpsgd: Communication-efficient and differentially-private distributed sgd. Advances in Neural Information Processing Systems 2018; 31."},{"issue":"10","key":"2292_CR33","doi-asserted-by":"publisher","first-page":"9530","DOI":"10.1109\/JIOT.2020.2991416","volume":"7","author":"R Hu","year":"2020","unstructured":"Hu R, Guo Y, Li H, Pei Q, Gong Y. Personalized federated learning with differential privacy. IEEE Internet Things J. 2020;7(10):9530\u20139.","journal-title":"IEEE Internet Things J"},{"key":"2292_CR34","unstructured":"Bonawitz K.A, Ivanov V, Kreuter B, Marcedone A, McMahan H.B, Patel S, Ramage D, Segal A, Seth K. Practical secure aggregation for federated learning on user-held data. In: NIPS Workshop on Private Multi-Party Machine Learning 2016. https:\/\/arxiv.org\/abs\/1611.04482"},{"key":"2292_CR35","doi-asserted-by":"crossref","unstructured":"Chhabra S, Solihin Y, Lal R, Hoekstra M. An analysis of secure processor architectures. Transactions on computational science VII, 2010; 101\u2013121.","DOI":"10.1007\/978-3-642-11389-5_6"},{"key":"2292_CR36","doi-asserted-by":"crossref","unstructured":"Cucinotta T, Cherubini D, Jul E. Confidential execution of cloud services. In: CLOSER, 2014; pp. 616\u2013621.","DOI":"10.5220\/0004962406160621"},{"key":"2292_CR37","doi-asserted-by":"publisher","first-page":"130698","DOI":"10.1109\/ACCESS.2021.3114099","volume":"9","author":"A Chhabra","year":"2021","unstructured":"Chhabra A, Masalkovait\u0117 K, Mohapatra P. An overview of fairness in clustering. IEEE Access. 2021;9:130698\u2013720.","journal-title":"IEEE Access"},{"key":"2292_CR38","unstructured":"Ezzeldin Y.H, Yan S, He C, Ferrara E, Avestimehr S. Fairfed: Enabling group fairness in federated learning. In: 1st NeurIPS Workshop on New Frontiers in Federated Learning 2021. https:\/\/arxiv.org\/abs\/1611.04482"},{"key":"2292_CR39","unstructured":"Chu L, Wang L, Dong Y, Pei J, Zhou Z, Zhang Y. Fedfair: Training fair models in cross-silo federated learning. arXiv preprint arXiv:2109.05662 2021."},{"key":"2292_CR40","unstructured":"Menon A.K, Williamson R.C. The cost of fairness in binary classification. In: Conference on Fairness, Accountability and Transparency, 2018; pp. 107\u2013118 . PMLR"},{"key":"2292_CR41","unstructured":"Wick M, Tristan J.-B, et al. Unlocking fairness: a trade-off revisited. Advances in neural information processing systems 2019; 32."},{"issue":"6","key":"2292_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3457607","volume":"54","author":"N Mehrabi","year":"2021","unstructured":"Mehrabi N, Morstatter F, Saxena N, Lerman K, Galstyan A. A survey on bias and fairness in machine learning. ACM Computing Surveys (CSUR). 2021;54(6):1\u201335.","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"2292_CR43","doi-asserted-by":"crossref","unstructured":"Biswas S, Rajan H. Fair preprocessing: towards understanding compositional fairness of data transformers in machine learning pipeline. In: Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, 2021; pp. 981\u2013993.","DOI":"10.1145\/3468264.3468536"},{"issue":"1","key":"2292_CR44","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10115-011-0463-8","volume":"33","author":"F Kamiran","year":"2012","unstructured":"Kamiran F, Calders T. Data preprocessing techniques for classification without discrimination. Knowl Inf Syst. 2012;33(1):1\u201333.","journal-title":"Knowl Inf Syst"},{"issue":"3","key":"2292_CR45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3551390","volume":"17","author":"M Wan","year":"2023","unstructured":"Wan M, Zha D, Liu N, Zou N. In-processing modeling techniques for machine learning fairness: A survey. ACM Trans Knowl Discov Data. 2023;17(3):1\u201327.","journal-title":"ACM Trans Knowl Discov Data"},{"key":"2292_CR46","unstructured":"Hashimoto T, Srivastava M, Namkoong H, Liang P. Fairness without demographics in repeated loss minimization. In: International Conference on Machine Learning, 2018; pp. 1929\u20131938 . PMLR"},{"key":"2292_CR47","first-page":"25944","volume":"34","author":"F Petersen","year":"2021","unstructured":"Petersen F, Mukherjee D, Sun Y, Yurochkin M. Post-processing for individual fairness. Adv Neural Inf Process Syst. 2021;34:25944\u201355.","journal-title":"Adv Neural Inf Process Syst"},{"key":"2292_CR48","doi-asserted-by":"crossref","unstructured":"Noriega-Campero A, Bakker M.A, Garcia-Bulle B, Pentland A. Active fairness in algorithmic decision making. In: Proceedings of the 2019 AAAI\/ACM Conference on AI, Ethics, and Society, 2019; pp. 77\u201383.","DOI":"10.1145\/3306618.3314277"},{"key":"2292_CR49","doi-asserted-by":"crossref","unstructured":"Cummings R, Gupta V, Kimpara D, Morgenstern J. On the compatibility of privacy and fairness. In: Adjunct Publication of the 27th Conference on User Modeling, Adaptation and Personalization, 2019; pp. 309\u2013315.","DOI":"10.1145\/3314183.3323847"},{"key":"2292_CR50","doi-asserted-by":"crossref","unstructured":"Andr\u00e9s M.E, Bordenabe N.E, Chatzikokolakis K, Palamidessi C. Geo-indistinguishability: Differential privacy for location-based systems. In: Proceedings of the 2013 ACM SIGSAC Conference on Computer & Communications Security, 2013; pp. 901\u2013914.","DOI":"10.1145\/2508859.2516735"},{"key":"2292_CR51","unstructured":"Kone\u010dn\u00fd J, McMahan H.B, Yu F.X, Richtarik P, Suresh A.T, Bacon D. Federated learning: Strategies for improving communication efficiency. In: NIPS Workshop on Private Multi-Party Machine Learning 2016. https:\/\/arxiv.org\/abs\/1610.05492"},{"key":"2292_CR52","unstructured":"CMMS: Centers for Medicare and Medicaid Services. Accessed: 2021; 2022-09-21 . https:\/\/www.cms.gov\/mmrr\/News\/mmrr-news-2013-03-hosp-chg-data.html"},{"key":"2292_CR53","unstructured":"Caldas S, Duddu S.M.K, Wu P, Li T, Kone\u010dn\u1ef3 J, McMahan H.B, Smith V, Talwalkar A. Leaf: A benchmark for federated settings. Workshop on Federated Learning for Data Privacy and Confidentiality 2019."},{"key":"2292_CR54","unstructured":"Bassily R, Nissim K, Stemmer U, Guha\u00a0Thakurta A. Practical locally private heavy hitters. In: Guyon, I., Luxburg, U.V., Bengio, S., Wallach, H., Fergus, R., Vishwanathan, S., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 30. Curran Associates, Inc., Red Hook, NY, USA 2017. https:\/\/proceedings.neurips.cc\/paper\/2017\/file\/3d779cae2d46cf6a8a99a35ba4167977-Paper.pdf"},{"issue":"1","key":"2292_CR55","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.jfineco.2021.05.047","volume":"143","author":"R Bartlett","year":"2022","unstructured":"Bartlett R, Morse A, Stanton R, Wallace N. Consumer-lending discrimination in the fintech era. J Financ Econ. 2022;143(1):30\u201356.","journal-title":"J Financ Econ"}],"container-title":["SN Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-023-02292-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42979-023-02292-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42979-023-02292-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:29Z","timestamp":1730419229000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42979-023-02292-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,28]]},"references-count":55,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2023,11]]}},"alternative-id":["2292"],"URL":"https:\/\/doi.org\/10.1007\/s42979-023-02292-0","relation":{},"ISSN":["2661-8907"],"issn-type":[{"value":"2661-8907","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,10,28]]},"assertion":[{"value":"30 June 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 August 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 October 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"831"}}