{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T15:09:47Z","timestamp":1767625787975,"version":"3.40.4"},"reference-count":110,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"FAIR - Future Artificial Intelligence Research and received funding from the European Union Next-GenerationEU (PIANO NAZIONALE DI RIPRESA E RESILIENZA"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3556587","type":"journal-article","created":{"date-parts":[[2025,3,31]],"date-time":"2025-03-31T23:45:26Z","timestamp":1743464726000},"page":"61928-61957","source":"Crossref","is-referenced-by-count":2,"title":["Resource-Efficient Personalization in Federated Learning With Closed-Form Classifiers"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4486-1086","authenticated-orcid":false,"given":"Eros","family":"Fan\u00ec","sequence":"first","affiliation":[{"name":"Department of Control and Computer Engineering, Polytechnic University of Turin, Turin, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8890-2732","authenticated-orcid":false,"given":"Raffaello","family":"Camoriano","sequence":"additional","affiliation":[{"name":"Department of Control and Computer Engineering, Polytechnic University of Turin, Turin, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7169-0158","authenticated-orcid":false,"given":"Barbara","family":"Caputo","sequence":"additional","affiliation":[{"name":"Department of Control and Computer Engineering, Polytechnic University of Turin, Turin, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3306-1323","authenticated-orcid":false,"given":"Marco","family":"Ciccone","sequence":"additional","affiliation":[{"name":"Vector Institute, Toronto, ON, Canada"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. Artif. Intell. Statist.","author":"McMahan"},{"doi-asserted-by":"publisher","key":"ref2","DOI":"10.1561\/2200000083"},{"doi-asserted-by":"publisher","key":"ref3","DOI":"10.1109\/TNNLS.2022.3160699"},{"key":"ref4","article-title":"Applied federated learning: Improving Google keyboard query suggestions","author":"Yang","year":"2018","journal-title":"arXiv:1812.02903"},{"key":"ref5","first-page":"3557","article-title":"Personalized federated learning with theoretical guarantees: A model-agnostic meta-learning approach","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Fallah"},{"key":"ref6","first-page":"5132","article-title":"SCAFFOLD: Stochastic controlled averaging for federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Karimireddy"},{"key":"ref7","article-title":"Federated learning based on dynamic regularization","author":"Acar","year":"2021","journal-title":"arXiv:2111.04263"},{"key":"ref8","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Li"},{"doi-asserted-by":"publisher","key":"ref9","DOI":"10.1109\/ISIT45174.2021.9517850"},{"key":"ref10","article-title":"Enhance local consistency in federated learning: A multi-step inertial momentum approach","author":"Liu","year":"2023","journal-title":"arXiv:2302.05726"},{"key":"ref11","article-title":"FedCM: Federated learning with client-level momentum","author":"Xu","year":"2021","journal-title":"arXiv:2106.10874"},{"key":"ref12","article-title":"Federated learning with personalization layers","author":"Arivazhagan","year":"2019","journal-title":"arXiv:1912.00818"},{"key":"ref13","first-page":"4427","article-title":"Federated multitask learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Smith"},{"key":"ref14","article-title":"Three approaches for personalization with applications to federated learning","author":"Mansour","year":"2020","journal-title":"arXiv:2002.10619"},{"key":"ref15","first-page":"1","article-title":"Where to begin? Exploring the impact of pre-training and initialization in federated learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Nguyen"},{"key":"ref16","article-title":"Where to begin? On the impact of pre-training and initialization in federated learning","author":"Nguyen","year":"2022","journal-title":"arXiv:2206.15387"},{"doi-asserted-by":"publisher","key":"ref17","DOI":"10.1109\/TMC.2023.3325366"},{"doi-asserted-by":"publisher","key":"ref18","DOI":"10.1109\/ICCV51070.2023.00490"},{"key":"ref19","first-page":"25475","article-title":"Overcoming recency bias of normalization statistics in continual learning: Balance and adaptation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Lyu"},{"doi-asserted-by":"publisher","key":"ref20","DOI":"10.1109\/CVPR.2019.00046"},{"doi-asserted-by":"publisher","key":"ref21","DOI":"10.1109\/TPAMI.2022.3213473"},{"doi-asserted-by":"publisher","key":"ref22","DOI":"10.1109\/CVPRW53098.2021.00398"},{"doi-asserted-by":"publisher","key":"ref23","DOI":"10.1073\/pnas.1611835114"},{"key":"ref24","first-page":"764","article-title":"Re-weighted softmax crossentropy to control forgetting in federated learning","volume-title":"Proc. Conf. Lifelong Learn. Agents","author":"Legate"},{"doi-asserted-by":"publisher","key":"ref25","DOI":"10.1007\/978-3-031-20050-2_38"},{"key":"ref26","first-page":"3403","article-title":"Towards flexible device participation in federated learning","volume-title":"Proc. Int. Conf. Artif. Intell. Statist. (AISTATS)","volume":"130","author":"Ruan"},{"doi-asserted-by":"publisher","key":"ref27","DOI":"10.1109\/CVPR42600.2020.00265"},{"doi-asserted-by":"publisher","key":"ref28","DOI":"10.1109\/CVPR.2018.00914"},{"doi-asserted-by":"publisher","key":"ref29","DOI":"10.1007\/978-3-030-58607-2_5"},{"key":"ref30","first-page":"5972","article-title":"No fear of heterogeneity: Classifier calibration for federated learning with non- IID data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Luo"},{"key":"ref31","first-page":"1","article-title":"Accelerating heterogeneous federated learning with closed-form classifiers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Fan\u00ec"},{"key":"ref32","first-page":"17716","article-title":"Federated learning with partial model personalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Pillutla"},{"key":"ref33","first-page":"1","article-title":"On the convergence of FedAvg on non-IID data","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref34","first-page":"314","article-title":"Stochastic variance reduction for nonconvex optimization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Reddi"},{"key":"ref35","first-page":"1","article-title":"Measuring the effects of non-identical data distribution for federated visual classification","volume-title":"Proc. Neurips Workshop Federated Learn.","author":"Hsu"},{"key":"ref36","first-page":"1","article-title":"SlowMo: Improving communication-efficient distributed SGD with slow momentum","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref37","first-page":"1","article-title":"Adaptive federated optimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Reddi"},{"key":"ref38","article-title":"Mime: Mimicking centralized stochastic algorithms in federated learning","author":"Praneeth Karimireddy","year":"2020","journal-title":"arXiv:2008.03606"},{"key":"ref39","article-title":"Communication-efficient heterogeneous federated learning with generalized heavy-ball momentum","author":"Zaccone","year":"2023","journal-title":"arXiv:2311.18578"},{"key":"ref40","first-page":"30882","article-title":"TCT: Convexifying federated learning using bootstrapped neural tangent kernels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Yu"},{"key":"ref41","article-title":"Schedule-robust online continual learning","author":"Wang","year":"2022","journal-title":"arXiv:2210.05561"},{"key":"ref42","first-page":"1","article-title":"Decoupling representation and classifier for long-tailed recognition","volume-title":"Proc. 8th Int. Conf. Learn. Represent. (ICLR)","author":"Kang"},{"doi-asserted-by":"publisher","key":"ref43","DOI":"10.1109\/CVPR52729.2023.00386"},{"doi-asserted-by":"publisher","key":"ref44","DOI":"10.1609\/aaai.v38i14.29468"},{"doi-asserted-by":"publisher","key":"ref45","DOI":"10.1609\/aaai.v38i15.29617"},{"doi-asserted-by":"publisher","key":"ref46","DOI":"10.1109\/TIFS.2024.3402361"},{"doi-asserted-by":"publisher","key":"ref47","DOI":"10.1109\/CVPR52733.2024.01189"},{"doi-asserted-by":"publisher","key":"ref48","DOI":"10.24963\/ijcai.2022\/308"},{"key":"ref49","first-page":"1","article-title":"FedBABU: Towards enhanced representation for federated image classification","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Oh"},{"doi-asserted-by":"publisher","key":"ref50","DOI":"10.1073\/pnas.2015509117"},{"doi-asserted-by":"publisher","key":"ref51","DOI":"10.1109\/IJCNN52387.2021.9534035"},{"key":"ref52","first-page":"69832","article-title":"Guiding the last layer in federated learning with pre-trained models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Legate"},{"key":"ref53","first-page":"1","article-title":"Towards model agnostic federated learning using knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Afonin"},{"doi-asserted-by":"publisher","key":"ref54","DOI":"10.1109\/TETC.2022.3215986"},{"key":"ref55","first-page":"29566","article-title":"Coresets for vertical federated learning: Regularized linear regression and k-means clustering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Huang"},{"doi-asserted-by":"publisher","key":"ref56","DOI":"10.1145\/3298981"},{"doi-asserted-by":"publisher","key":"ref57","DOI":"10.1109\/cdc.2012.6426691"},{"issue":"1","key":"ref58","first-page":"3299","article-title":"Divide and conquer kernel ridge regression: A distributed algorithm with minimax optimal rates","volume":"16","author":"Zhang","year":"2015","journal-title":"J. Mach. Learn. Res."},{"issue":"1","key":"ref59","first-page":"2657","article-title":"Distributed coordinate descent method for learning with big data","volume":"17","author":"Richt\u00e1rik","year":"2016","journal-title":"J. Mach. Learn. Res."},{"doi-asserted-by":"publisher","key":"ref60","DOI":"10.1109\/TMC.2023.3302410"},{"key":"ref61","article-title":"FedTune: A deep dive into efficient federated fine-tuning with pre-trained transformers","author":"Chen","year":"2022","journal-title":"arXiv:2211.08025"},{"doi-asserted-by":"publisher","key":"ref62","DOI":"10.1109\/ICASSP48485.2024.10447454"},{"key":"ref63","article-title":"GPT-FL: Generative pre-trained model-assisted federated learning","author":"Zhang","year":"2023","journal-title":"arXiv:2306.02210"},{"key":"ref64","article-title":"SLoRA: Federated parameter efficient fine-tuning of language models","author":"Babakniya","year":"2023","journal-title":"arXiv:2308. 06522"},{"doi-asserted-by":"publisher","key":"ref65","DOI":"10.18653\/v1\/2024.emnlp-main.717"},{"key":"ref66","article-title":"PFedLoRA: Modelheterogeneous personalized federated learning with LoRa tuning","author":"Yi","year":"2023","journal-title":"arXiv:2310.13283"},{"doi-asserted-by":"publisher","key":"ref67","DOI":"10.1109\/TKDE.2021.3070203"},{"key":"ref68","first-page":"5917","article-title":"Adaptive gradient-based meta-learning methods","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Khodak"},{"doi-asserted-by":"publisher","key":"ref69","DOI":"10.1109\/TNNLS.2020.3015958"},{"doi-asserted-by":"publisher","key":"ref70","DOI":"10.1109\/TMC.2022.3194198"},{"doi-asserted-by":"publisher","key":"ref71","DOI":"10.1109\/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00042"},{"doi-asserted-by":"publisher","key":"ref72","DOI":"10.1109\/CVPRW53098.2021.00309"},{"key":"ref73","first-page":"21394","article-title":"Personalized federated learning with Moreau envelopes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Dinh"},{"key":"ref74","first-page":"6357","article-title":"Ditto: Fair and robust federated learning through personalization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref75","article-title":"Adaptive personalized federated learning","author":"Deng","year":"2020","journal-title":"arXiv:2003.13461"},{"key":"ref76","article-title":"Federated mutual learning","author":"Shen","year":"2020","journal-title":"arXiv:2006.16765"},{"key":"ref77","article-title":"Personalized federated learning: A unified framework and universal optimization techniques","author":"Hanzely","year":"2021","journal-title":"arXiv:2102.09743"},{"key":"ref78","article-title":"Think locally, act globally: Federated learning with local and global representations","author":"Pu Liang","year":"2020","journal-title":"arXiv:2001.01523"},{"key":"ref79","first-page":"11220","article-title":"Federated reconstruction: Partially local federated learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Singhal"},{"key":"ref80","first-page":"2089","article-title":"Exploiting shared representations for personalized federated learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Collins"},{"doi-asserted-by":"publisher","key":"ref81","DOI":"10.1214\/aos\/1176345451"},{"key":"ref82","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611971484","volume-title":"Numerical Methods for Least Squares Problems","author":"Bj\u00f6rck","year":"1996"},{"key":"ref83","first-page":"131","article-title":"Regularized least-squares classification","volume":"190","author":"Rifkin","year":"2003","journal-title":"Nato Sci. Ser. Sub Comput. Syst. Sci."},{"key":"ref84","first-page":"531","volume-title":"Pattern Recognition and Machine Learning","volume":"2","author":"Bishop","year":"2006"},{"doi-asserted-by":"publisher","key":"ref85","DOI":"10.1017\/CBO9780511804441"},{"volume-title":"Support Vector Machines","year":"2008","author":"Steinwart","key":"ref86"},{"doi-asserted-by":"publisher","key":"ref87","DOI":"10.1198\/016214505000000907"},{"doi-asserted-by":"publisher","key":"ref88","DOI":"10.1017\/CBO9780511809682"},{"doi-asserted-by":"publisher","key":"ref89","DOI":"10.1109\/ICRA.2017.7989364"},{"volume-title":"Linear Estimation","year":"2000","author":"Kailath","key":"ref90"},{"doi-asserted-by":"publisher","key":"ref91","DOI":"10.1214\/aoms\/1177729893"},{"doi-asserted-by":"publisher","key":"ref92","DOI":"10.1137\/1031049"},{"doi-asserted-by":"publisher","key":"ref93","DOI":"10.1002\/9780470374122"},{"key":"ref94","first-page":"1177","article-title":"Random features for large-scale kernel machines","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"20","author":"Rahimi"},{"doi-asserted-by":"publisher","key":"ref95","DOI":"10.1109\/CVPR.2018.00474"},{"doi-asserted-by":"publisher","key":"ref96","DOI":"10.1109\/CVPR.2009.5206848"},{"year":"2009","author":"Krizhevsky","article-title":"Learning multiple layers of features from tiny images","key":"ref97"},{"key":"ref98","article-title":"Non-IID data in federated learning: A survey with taxonomy, metrics, methods, frameworks and future directions","author":"G","year":"2024","journal-title":"arXiv:2411.12377"},{"doi-asserted-by":"publisher","key":"ref99","DOI":"10.1016\/j.future.2024.01.005"},{"key":"ref100","first-page":"12073","article-title":"Federated continual learning with weighted inter-client transfer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yoon"},{"doi-asserted-by":"publisher","key":"ref101","DOI":"10.1007\/978-0-387-84858-7"},{"doi-asserted-by":"publisher","key":"ref102","DOI":"10.1609\/aaai.v36i8.20819"},{"doi-asserted-by":"publisher","key":"ref103","DOI":"10.1016\/j.future.2020.10.007"},{"doi-asserted-by":"publisher","key":"ref104","DOI":"10.1109\/TKDE.2021.3124599"},{"key":"ref105","article-title":"Practical secure aggregation for federated learning on user-held data","author":"Bonawitz","year":"2016","journal-title":"arXiv:1611.04482"},{"doi-asserted-by":"publisher","key":"ref106","DOI":"10.1007\/11681878_14"},{"doi-asserted-by":"publisher","key":"ref107","DOI":"10.1109\/ACCESS.2022.3151670"},{"doi-asserted-by":"publisher","key":"ref108","DOI":"10.3390\/fi13040094"},{"key":"ref109","first-page":"1","article-title":"SMPAi: Secure multi-party computation for federated learning","volume-title":"Proc. NeurIPS Workshop Robust AI Financial Services","volume":"21","author":"Mugunthan"},{"key":"ref110","first-page":"8074","article-title":"A simple data augmentation for feature distribution skewed federated learning","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Yan"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10946159.pdf?arnumber=10946159","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T17:40:26Z","timestamp":1744652426000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10946159\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":110,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3556587","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}