{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T01:50:50Z","timestamp":1773971450188,"version":"3.50.1"},"reference-count":64,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,3,1]],"date-time":"2026-03-01T00:00:00Z","timestamp":1772323200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,1,7]],"date-time":"2026-01-07T00:00:00Z","timestamp":1767744000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004359","name":"Vetenskapsr\u00e5det","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004359","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100030800","name":"Excellence Center at Link\u00f6ping \u2013 Lund in Information Technology","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100030800","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001665","name":"Agence Nationale de la Recherche","doi-asserted-by":"publisher","award":["ANR-19-P3IA-0002"],"award-info":[{"award-number":["ANR-19-P3IA-0002"]}],"id":[{"id":"10.13039\/501100001665","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004063","name":"Knut och Alice Wallenbergs Stiftelse","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004063","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Performance Evaluation"],"published-print":{"date-parts":[[2026,3]]},"DOI":"10.1016\/j.peva.2025.102538","type":"journal-article","created":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T15:47:21Z","timestamp":1767109641000},"page":"102538","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Federated Learning for Collaborative Inference Systems: The case of early exit networks"],"prefix":"10.1016","volume":"171","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0696-9224","authenticated-orcid":false,"given":"Chuan","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3039-3805","authenticated-orcid":false,"given":"Caelin","family":"Kaplan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8395-4536","authenticated-orcid":false,"given":"Angelo","family":"Rodio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2158-0126","authenticated-orcid":false,"given":"Tareq","family":"Si Salem","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8779-0620","authenticated-orcid":false,"given":"Giovanni","family":"Neglia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.peva.2025.102538_b1","doi-asserted-by":"crossref","first-page":"370","DOI":"10.1007\/s11633-022-1391-7","article-title":"A survey on collaborative DNN inference for edge intelligence","volume":"20","author":"Ren","year":"2023","journal-title":"Mach. Intell. Res."},{"key":"10.1016\/j.peva.2025.102538_b2","first-page":"52840","article-title":"Network for distributed intelligence: A survey and future perspectives","volume":"11","author":"Campolo","year":"2023","journal-title":"IEEE Access"},{"issue":"3","key":"10.1016\/j.peva.2025.102538_b3","doi-asserted-by":"crossref","first-page":"2031","DOI":"10.1109\/COMST.2020.2986024","article-title":"Federated learning in mobile edge networks: A comprehensive survey","volume":"22","author":"Lim","year":"2020","journal-title":"IEEE Commun. Surv. Tutor."},{"issue":"1\u20132","key":"10.1016\/j.peva.2025.102538_b4","first-page":"1","article-title":"Advances and open problems in federated learning","volume":"14","author":"Kairouz","year":"2021","journal-title":"Found. Trends\u00ae Mach. Learn."},{"issue":"12","key":"10.1016\/j.peva.2025.102538_b5","doi-asserted-by":"crossref","first-page":"9706","DOI":"10.1109\/JIOT.2020.3022358","article-title":"Attacking and protecting data privacy in edge\u2013cloud collaborative inference systems","volume":"8","author":"He","year":"2021","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.peva.2025.102538_b6","series-title":"Advances in Neural Information Processing Systems","first-page":"12855","article-title":"Measuring data reconstruction defenses in collaborative inference systems","volume":"Vol. 35","author":"Yang","year":"2022"},{"key":"10.1016\/j.peva.2025.102538_b7","article-title":"Toward inference delivery networks: Distributing machine learning with optimality guarantees","author":"Salem","year":"2023","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"10.1016\/j.peva.2025.102538_b8","doi-asserted-by":"crossref","unstructured":"Nathan Ng, Abel Souza, Suhas Diggavi, Niranjan Suri, Tarek Abdelzaher, Don Towsley, Prashant Shenoy, Collaborative Inference in Resource-Constrained Edge Networks: Challenges and Opportunities, in: MILCOM 2024 - 2024 IEEE Military Communications Conference, MILCOM, 2024, pp. 1\u20136.","DOI":"10.1109\/MILCOM61039.2024.10773876"},{"issue":"18","key":"10.1016\/j.peva.2025.102538_b9","doi-asserted-by":"crossref","first-page":"37456","DOI":"10.1109\/JIOT.2025.3583477","article-title":"Exploring the boundaries of on-device inference: When tiny falls short, go hierarchical","volume":"12","author":"Behera","year":"2025","journal-title":"IEEE Internet Things J."},{"issue":"1","key":"10.1016\/j.peva.2025.102538_b10","doi-asserted-by":"crossref","first-page":"447","DOI":"10.1109\/TWC.2019.2946140","article-title":"Edge AI: On-demand accelerating deep neural network inference via edge computing","volume":"19","author":"Li","year":"2020","journal-title":"IEEE Trans. Wirel. Commun."},{"issue":"5","key":"10.1016\/j.peva.2025.102538_b11","doi-asserted-by":"crossref","first-page":"96","DOI":"10.1109\/MNET.001.1800506","article-title":"Boomerang: On-demand cooperative deep neural network inference for edge intelligence on the industrial internet of things","volume":"33","author":"Zeng","year":"2019","journal-title":"IEEE Netw."},{"key":"10.1016\/j.peva.2025.102538_b12","doi-asserted-by":"crossref","unstructured":"Mikolaj Jankowski, Deniz G\u00fcnd\u00fcz, Krystian Mikolajczyk, Adaptive Early Exiting for Collaborative Inference over Noisy Wireless Channels, in: 2024 IEEE International Conference on Machine Learning for Communication and Networking, ICMLCN, 2024, pp. 126\u2013131.","DOI":"10.1109\/ICMLCN59089.2024.10624796"},{"key":"10.1016\/j.peva.2025.102538_b13","doi-asserted-by":"crossref","unstructured":"Surat Teerapittayanon, Bradley McDanel, H.T. Kung, Distributed Deep Neural Networks Over the Cloud, the Edge and End Devices, in: 2017 IEEE 37th International Conference on Distributed Computing Systems, ICDCS, 2017, pp. 328\u2013339.","DOI":"10.1109\/ICDCS.2017.226"},{"key":"10.1016\/j.peva.2025.102538_b14","unstructured":"Gao Huang, Danlu Chen, Tianhong Li, Felix Wu, Laurens van der Maaten, Kilian Weinberger, Multi-Scale Dense Networks for Resource Efficient Image Classification, in: International Conference on Learning Representations, 2018."},{"key":"10.1016\/j.peva.2025.102538_b15","series-title":"Proceedings of the 36th International Conference on Machine Learning","first-page":"3301","article-title":"Shallow-deep networks: Understanding and mitigating network overthinking","author":"Kaya","year":"2019"},{"key":"10.1016\/j.peva.2025.102538_b16","series-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"issue":"3","key":"10.1016\/j.peva.2025.102538_b17","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1109\/MSP.2020.2975749","article-title":"Federated learning: Challenges, methods, and future directions","volume":"37","author":"Li","year":"2020","journal-title":"IEEE Signal Process. Mag."},{"key":"10.1016\/j.peva.2025.102538_b18","series-title":"Advances in Neural Information Processing Systems","first-page":"2351","article-title":"Ensemble distillation for robust model fusion in federated learning","volume":"Vol. 33","author":"Lin","year":"2020"},{"key":"10.1016\/j.peva.2025.102538_b19","unstructured":"Alessio Mora, Irene Tenison, Paolo Bellavista, Irina Rish, Knowledge Distillation in Federated Learning: A Practical Guide, in: Thirty-Third International Joint Conference on Artificial Intelligence, Vol. 9, 2024, pp. 8188\u20138196."},{"key":"10.1016\/j.peva.2025.102538_b20","unstructured":"Enmao Diao, Jie Ding, Vahid Tarokh, HeteroFL: Computation and Communication Efficient Federated Learning for Heterogeneous Clients, in: International Conference on Learning Representations, 2020."},{"key":"10.1016\/j.peva.2025.102538_b21","series-title":"Advances in Neural Information Processing Systems","first-page":"12876","article-title":"FjORD: Fair and accurate federated learning under heterogeneous targets with ordered dropout","volume":"Vol. 34","author":"Horv\u00e1th","year":"2021"},{"key":"10.1016\/j.peva.2025.102538_b22","doi-asserted-by":"crossref","unstructured":"Surat Teerapittayanon, Bradley McDanel, H.T. Kung, BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks, in: 2016 23rd International Conference on Pattern Recognition, ICPR, 2016, pp. 2464\u20132469.","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"10.1016\/j.peva.2025.102538_b23","unstructured":"Mohamed Nabih Ali Mohamed Nawar, Daniele Falavigna, Alessio Brutti, Fed-EE: Federating Heterogeneous ASR Models Using Early-Exit Architectures, in: Proceedings of 3rd Neurips Workshop on Efficient Natural Language and Speech Processing, 2023."},{"key":"10.1016\/j.peva.2025.102538_b24","doi-asserted-by":"crossref","unstructured":"Fatih Ilhan, Gong Su, Ling Liu, ScaleFL: Resource-Adaptive Federated Learning With Heterogeneous Clients, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 24532\u201324541.","DOI":"10.1109\/CVPR52729.2023.02350"},{"issue":"01","key":"10.1016\/j.peva.2025.102538_b25","first-page":"3812","article-title":"Learning anytime predictions in neural networks via adaptive loss balancing","volume":"33","author":"Hu","year":"2019","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"1","key":"10.1016\/j.peva.2025.102538_b26","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1145\/3093337.3037698","article-title":"Neurosurgeon: Collaborative intelligence between the cloud and mobile edge","volume":"45","author":"Kang","year":"2017","journal-title":"ACM SIGARCH Comput. Archit. News"},{"issue":"5","key":"10.1016\/j.peva.2025.102538_b27","first-page":"90:1","article-title":"Split computing and early exiting for deep learning applications: Survey and research challenges","volume":"55","author":"Matsubara","year":"2022","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.peva.2025.102538_b28","doi-asserted-by":"crossref","unstructured":"Selim F. Yilmaz, Burak Has\u0131rc\u0131o\u011flu, Deniz G\u00fcnd\u00fcz, Over-the-Air Ensemble Inference with Model Privacy, in: 2022 IEEE International Symposium on Information Theory, ISIT, 2022, pp. 1265\u20131270.","DOI":"10.1109\/ISIT50566.2022.9834591"},{"issue":"1","key":"10.1016\/j.peva.2025.102538_b29","doi-asserted-by":"crossref","first-page":"598","DOI":"10.1109\/TWC.2024.3497167","article-title":"Decentralized low-latency collaborative inference via ensembles on the edge","volume":"24","author":"Malka","year":"2025","journal-title":"IEEE Trans. Wirel. Commun."},{"key":"10.1016\/j.peva.2025.102538_b30","first-page":"429","article-title":"Federated optimization in heterogeneous networks","volume":"2","author":"Li","year":"2020","journal-title":"Proc. Mach. Learn. Syst."},{"key":"10.1016\/j.peva.2025.102538_b31","unstructured":"Sean Augenstein, H. Brendan McMahan, Daniel Ramage, Swaroop Ramaswamy, Peter Kairouz, Mingqing Chen, Rajiv Mathews, Blaise Aguera y Arcas, Generative Models for Effective ML on Private, Decentralized Datasets, in: Eighth International Conference on Learning Representations, 2020."},{"issue":"1","key":"10.1016\/j.peva.2025.102538_b32","doi-asserted-by":"crossref","first-page":"18","DOI":"10.58970\/IJSB.2402","article-title":"Enhancing corporate innovation through artificial intelligence adoption: A study of Chinese telecommunications companies","volume":"38","author":"Dai","year":"2024","journal-title":"Int. J. Sci. Bus."},{"key":"10.1016\/j.peva.2025.102538_b33","doi-asserted-by":"crossref","DOI":"10.2478\/popets-2019-0008","article-title":"LOGAN: Membership inference attacks against generative models","author":"Hayes","year":"2019","journal-title":"Proc. Priv. Enhancing Technol."},{"issue":"3\u20134","key":"10.1016\/j.peva.2025.102538_b34","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1561\/0400000042","article-title":"The algorithmic foundations of differential privacy","volume":"9","author":"Dwork","year":"2014","journal-title":"Found. Trends\u00ae Theor. Comput. Sci."},{"key":"10.1016\/j.peva.2025.102538_b35","series-title":"The Tenth International Conference on Learning Representations, ICLR 2022, Virtual Event, April 25-29, 2022","article-title":"Efficient split-mix federated learning for on-demand and in-situ customization","author":"Hong","year":"2022"},{"key":"10.1016\/j.peva.2025.102538_b36","series-title":"Forty-First International Conference on Machine Learning, ICML 2024, Vienna, Austria, July 21-27, 2024","article-title":"Recurrent early exits for federated learning with heterogeneous clients","author":"Lee","year":"2024"},{"key":"10.1016\/j.peva.2025.102538_b37","doi-asserted-by":"crossref","unstructured":"Ruixuan Liu, Fangzhao Wu, Chuhan Wu, Yanlin Wang, Lingjuan Lyu, Hong Chen, Xing Xie, No One Left Behind: Inclusive Federated Learning over Heterogeneous Devices, in: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, 2022, pp. 3398\u20133406.","DOI":"10.1145\/3534678.3539086"},{"key":"10.1016\/j.peva.2025.102538_b38","doi-asserted-by":"crossref","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun, Deep Residual Learning for Image Recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.peva.2025.102538_b39","doi-asserted-by":"crossref","unstructured":"Hao Li, Hong Zhang, Xiaojuan Qi, Ruigang Yang, Gao Huang, Improved Techniques for Training Adaptive Deep Networks, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 1891\u20131900.","DOI":"10.1109\/ICCV.2019.00198"},{"key":"10.1016\/j.peva.2025.102538_b40","doi-asserted-by":"crossref","first-page":"29677","DOI":"10.52202\/068431-2152","article-title":"FedRolex: Model-heterogeneous federated learning with rolling sub-model extraction","volume":"35","author":"Alam","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.peva.2025.102538_b41","series-title":"Proceedings of the 26th Annual International Conference on Mobile Computing and Networking","article-title":"SPINN: synergistic progressive inference of neural networks over device and cloud","author":"Laskaridis","year":"2020"},{"key":"10.1016\/j.peva.2025.102538_b42","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1016\/j.ins.2020.02.041","article-title":"Optimized training and scalable implementation of conditional deep neural networks with early exits for fog-supported IoT applications","volume":"521","author":"Baccarelli","year":"2020","journal-title":"Inform. Sci."},{"key":"10.1016\/j.peva.2025.102538_b43","series-title":"Understanding Machine Learning - From Theory to Algorithms","first-page":"I","author":"Shalev-Shwartz","year":"2014"},{"key":"10.1016\/j.peva.2025.102538_b44","series-title":"Foundations of Machine Learning","author":"Mohri","year":"2018"},{"key":"10.1016\/j.peva.2025.102538_b45","unstructured":"Xiang Li, Kaixuan Huang, Wenhao Yang, Shusen Wang, Zhihua Zhang, On the Convergence of FedAvg on Non-IID Data, in: International Conference on Learning Representations, 2020."},{"key":"10.1016\/j.peva.2025.102538_b46","series-title":"A field guide to federated optimization","author":"Wang","year":"2021"},{"key":"10.1016\/j.peva.2025.102538_b47","first-page":"1","article-title":"Federated learning under heterogeneous and correlated client availability","author":"Rodio","year":"2023","journal-title":"IEEE\/ACM Trans. Netw."},{"issue":"4","key":"10.1016\/j.peva.2025.102538_b48","doi-asserted-by":"crossref","first-page":"1898","DOI":"10.1109\/TCCN.2021.3101239","article-title":"Edge device identification based on federated learning and network traffic feature engineering","volume":"8","author":"He","year":"2022","journal-title":"IEEE Trans. Cogn. Commun. Netw."},{"issue":"2","key":"10.1016\/j.peva.2025.102538_b49","doi-asserted-by":"crossref","first-page":"426","DOI":"10.1145\/276305.276342","article-title":"Approximate medians and other quantiles in one pass and with limited memory","volume":"27","author":"Manku","year":"1998","journal-title":"ACM SIGMOD Rec."},{"issue":"2","key":"10.1016\/j.peva.2025.102538_b50","doi-asserted-by":"crossref","first-page":"58","DOI":"10.1145\/376284.375670","article-title":"Space-efficient online computation of quantile summaries","volume":"30","author":"Greenwald","year":"2001","journal-title":"SIGMOD Rec."},{"key":"10.1016\/j.peva.2025.102538_b51","series-title":"2016 Ieee 57th Annual Symposium on Foundations of Computer Science","first-page":"71","article-title":"Optimal quantile approximation in streams","author":"Karnin","year":"2016"},{"key":"10.1016\/j.peva.2025.102538_b52","unstructured":"Peva Blanchard, El Mahdi El Mhamdi, Rachid Guerraoui, Julien Stainer, Machine Learning with Adversaries: Byzantine Tolerant Gradient Descent, in: Advances in Neural Information Processing Systems, NeurIPS, 2017, pp. 119\u2013129."},{"key":"10.1016\/j.peva.2025.102538_b53","series-title":"Proceedings of the 35th International Conference on Machine Learning","first-page":"5650","article-title":"Byzantine-robust distributed learning: Towards optimal statistical rates","volume":"vol. 80","author":"Yin","year":"2018"},{"key":"10.1016\/j.peva.2025.102538_b54","unstructured":"Moran Baruch, Gilad Baruch, Yoav Goldberg, A Little Is Enough: Circumventing Defenses for Distributed Learning, in: Advances in Neural Information Processing Systems, NeurIPS, 2019."},{"key":"10.1016\/j.peva.2025.102538_b55","unstructured":"Eugene Bagdasaryan, Andreas Veit, Yiqing Hua, Deborah Estrin, Vitaly Shmatikov, How to Backdoor Federated Learning, in: Proceedings of the International Conference on Artificial Intelligence and Statistics, AISTATS, 2020, pp. 2938\u20132948."},{"key":"10.1016\/j.peva.2025.102538_b56","series-title":"Robust aggregation for federated learning","author":"Pillutla","year":"2019"},{"key":"10.1016\/j.peva.2025.102538_b57","series-title":"Advances in Neural Information Processing Systems","article-title":"Fair resource allocation in federated learning","author":"Li","year":"2019"},{"key":"10.1016\/j.peva.2025.102538_b58","doi-asserted-by":"crossref","unstructured":"Zhiyuan Zhao, Gauri Joshi, A Dynamic Reweighting Strategy For Fair Federated Learning, in: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, 2022, pp. 8772\u20138776.","DOI":"10.1109\/ICASSP43922.2022.9746300"},{"key":"10.1016\/j.peva.2025.102538_b59","series-title":"Proceedings of the 26th International Conference on Artificial Intelligence and Statistics","first-page":"8889","article-title":"Federated learning for data streams","author":"Marfoq","year":"2023"},{"key":"10.1016\/j.peva.2025.102538_b60","series-title":"Advanced Lectures on Machine Learning, Revised Lectures","first-page":"169","article-title":"Introduction to statistical learning theory","author":"Bousquet","year":"2004"},{"key":"10.1016\/j.peva.2025.102538_b61","series-title":"Chaining method to improve rademacher bound","author":"Livesay","year":"2017"},{"issue":"8","key":"10.1016\/j.peva.2025.102538_b62","doi-asserted-by":"crossref","first-page":"5136","DOI":"10.1109\/TCOMM.2021.3081746","article-title":"Federated learning in unreliable and resource-constrained cellular wireless networks","volume":"69","author":"Salehi","year":"2021","journal-title":"IEEE Trans.Commun."},{"key":"10.1016\/j.peva.2025.102538_b63","doi-asserted-by":"crossref","unstructured":"Angelo Rodio, Giovanni Neglia, Fabio Busacca, Stefano Mangione, Sergio Palazzo, Francesco Restuccia, Ilenia Tinnirello, Federated Learning with Packet Losses, in: 2023 26th International Symposium on Wireless Personal Multimedia Communications, WPMC, 2023, pp. 1\u20136.","DOI":"10.1109\/WPMC59531.2023.10338845"},{"key":"10.1016\/j.peva.2025.102538_b64","series-title":"Advances in Neural Information Processing Systems","first-page":"7611","article-title":"Tackling the objective inconsistency problem in heterogeneous federated optimization","volume":"Vol. 33","author":"Wang","year":"2020"}],"container-title":["Performance Evaluation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0166531625000720?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0166531625000720?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T00:36:34Z","timestamp":1773966994000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0166531625000720"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3]]},"references-count":64,"alternative-id":["S0166531625000720"],"URL":"https:\/\/doi.org\/10.1016\/j.peva.2025.102538","relation":{},"ISSN":["0166-5316"],"issn-type":[{"value":"0166-5316","type":"print"}],"subject":[],"published":{"date-parts":[[2026,3]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Federated Learning for Collaborative Inference Systems: The case of early exit networks","name":"articletitle","label":"Article Title"},{"value":"Performance Evaluation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.peva.2025.102538","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"102538"}}