{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T17:58:19Z","timestamp":1776448699680,"version":"3.51.2"},"reference-count":55,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["12301578"],"award-info":[{"award-number":["12301578"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["XJ2025012301"],"award-info":[{"award-number":["XJ2025012301"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Communications"],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1016\/j.comcom.2026.108497","type":"journal-article","created":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T18:00:14Z","timestamp":1774461614000},"page":"108497","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Enhancing federated unlearning using catastrophic forgetting in heterogeneous Industrial Internet of Things"],"prefix":"10.1016","volume":"252","author":[{"given":"Zhenguo","family":"Ma","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixuan","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanjing","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hongli","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianchun","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Xu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yafei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"78","reference":[{"key":"10.1016\/j.comcom.2026.108497_b1","series-title":"Artificial Intelligence and Statistics","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"issue":"5","key":"10.1016\/j.comcom.2026.108497_b2","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1109\/JIOT.2016.2579198","article-title":"Edge computing: Vision and challenges","volume":"3","author":"Shi","year":"2016","journal-title":"IEEE Internet Things J."},{"issue":"4","key":"10.1016\/j.comcom.2026.108497_b3","doi-asserted-by":"crossref","first-page":"2964","DOI":"10.1109\/TII.2020.3007817","article-title":"A blockchained federated learning framework for cognitive computing in industry 4.0 networks","volume":"17","author":"Qu","year":"2020","journal-title":"IEEE Trans. Ind. Inform."},{"issue":"2","key":"10.1016\/j.comcom.2026.108497_b4","doi-asserted-by":"crossref","first-page":"2549","DOI":"10.1109\/TR.2024.3427813","article-title":"Federated learning with potential partnership identification for accurate prediction in flexible manufacturing system","volume":"74","author":"Ren","year":"2025","journal-title":"IEEE Trans. Reliab."},{"issue":"2","key":"10.1016\/j.comcom.2026.108497_b5","doi-asserted-by":"crossref","first-page":"60","DOI":"10.1109\/MWC.001.2400303","article-title":"Trustworthy 6G-powered industrial IoT for resilient intelligent manufacturing","volume":"32","author":"Tian","year":"2025","journal-title":"IEEE Wirel. Commun."},{"issue":"4","key":"10.1016\/j.comcom.2026.108497_b6","doi-asserted-by":"crossref","first-page":"4631","DOI":"10.1109\/TITS.2022.3209903","article-title":"AI-empowered trajectory anomaly detection for intelligent transportation systems: A hierarchical federated learning approach","volume":"24","author":"Wang","year":"2022","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"5","key":"10.1016\/j.comcom.2026.108497_b7","doi-asserted-by":"crossref","first-page":"6584","DOI":"10.1109\/TVT.2022.3232603","article-title":"An efficient and reliable asynchronous federated learning scheme for smart public transportation","volume":"72","author":"Xu","year":"2022","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"5","key":"10.1016\/j.comcom.2026.108497_b8","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1109\/IOTM.001.2300286","article-title":"Responsible federated learning in smart transportation: Outlooks and challenges","volume":"7","author":"Huang","year":"2024","journal-title":"IEEE Internet Things Mag."},{"issue":"4","key":"10.1016\/j.comcom.2026.108497_b9","doi-asserted-by":"crossref","first-page":"3018","DOI":"10.1109\/JIOT.2022.3140430","article-title":"A federated learning and blockchain-enabled sustainable energy trade at the edge: A framework for industry 4.0","volume":"10","author":"Otoum","year":"2022","journal-title":"IEEE Internet Things J."},{"issue":"1","key":"10.1016\/j.comcom.2026.108497_b10","doi-asserted-by":"crossref","first-page":"424","DOI":"10.1109\/TGCN.2022.3140978","article-title":"Federatedgrids: Federated learning and blockchain-assisted p2p energy sharing","volume":"6","author":"Bouachir","year":"2022","journal-title":"IEEE Trans. Green Commun. Netw."},{"issue":"1","key":"10.1016\/j.comcom.2026.108497_b11","doi-asserted-by":"crossref","first-page":"2200","DOI":"10.1109\/TCE.2023.3343821","article-title":"Privacy-preserving smart energy management by consumer-electronic chips and federated learning","volume":"70","author":"Huang","year":"2023","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.comcom.2026.108497_b12","first-page":"10","volume":"vol. 10","author":"Voigt","year":"2017"},{"issue":"1","key":"10.1016\/j.comcom.2026.108497_b13","first-page":"1637","article-title":"California consumer privacy act","volume":"75","author":"Illman","year":"2019","journal-title":"Bus. Lawyer"},{"key":"10.1016\/j.comcom.2026.108497_b14","series-title":"Federated unlearning with knowledge distillation","author":"Wu","year":"2022"},{"issue":"5","key":"10.1016\/j.comcom.2026.108497_b15","doi-asserted-by":"crossref","first-page":"2924","DOI":"10.1109\/TNSE.2022.3187992","article-title":"Federated analytics informed distributed industrial IoT learning with non-IID data","volume":"10","author":"Wang","year":"2022","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"issue":"1","key":"10.1016\/j.comcom.2026.108497_b16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3679014","article-title":"A survey on federated unlearning: Challenges, methods, and future directions","volume":"57","author":"Liu","year":"2024","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.comcom.2026.108497_b17","series-title":"Federated unlearning: How to efficiently erase a client in fl?","author":"Halimi","year":"2022"},{"key":"10.1016\/j.comcom.2026.108497_b18","first-page":"19804","article-title":"Federated unlearning with gradient descent and conflict mitigation","volume":"vol. 39","author":"Pan","year":"2025"},{"issue":"2","key":"10.1016\/j.comcom.2026.108497_b19","doi-asserted-by":"crossref","first-page":"1110","DOI":"10.1109\/TSC.2025.3536312","article-title":"Vertical federated unlearning via backdoor certification","volume":"18","author":"Han","year":"2025","journal-title":"IEEE Trans. Serv. Comput."},{"key":"10.1016\/j.comcom.2026.108497_b20","series-title":"International Conference on Machine Learning","first-page":"15809","article-title":"Understanding gradient regularization in deep learning: Efficient finite-difference computation and implicit bias","author":"Karakida","year":"2023"},{"issue":"18","key":"10.1016\/j.comcom.2026.108497_b21","doi-asserted-by":"crossref","first-page":"17844","DOI":"10.1109\/JIOT.2022.3161943","article-title":"Data heterogeneity-robust federated learning via group client selection in industrial IoT","volume":"9","author":"Li","year":"2022","journal-title":"IEEE Internet Things J."},{"issue":"2","key":"10.1016\/j.comcom.2026.108497_b22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3612918","article-title":"A comprehensive survey on collaborative data-access enablers in the IIoT","volume":"56","author":"Sun","year":"2023","journal-title":"ACM Comput. Surv."},{"issue":"2","key":"10.1016\/j.comcom.2026.108497_b23","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3706419","article-title":"Certified unlearning for federated recommendation","volume":"43","author":"Huynh","year":"2025","journal-title":"ACM Trans. Inf. Syst."},{"issue":"7","key":"10.1016\/j.comcom.2026.108497_b24","doi-asserted-by":"crossref","first-page":"8653","DOI":"10.1109\/JIOT.2024.3502666","article-title":"Hier-FUN: Hierarchical federated learning and unlearning in heterogeneous edge computing","volume":"12","author":"Ma","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.comcom.2026.108497_b25","doi-asserted-by":"crossref","unstructured":"Y. Hua, H. Xia, S. Xu, Federated Unlearning for Samples Based on Adaptive Gradient Ascent of Angles, in: 2024 IEEE 23rd International Conference on Trust, Security and Privacy in Computing and Communications, TrustCom, 2024, pp. 834\u2013841.","DOI":"10.1109\/TrustCom63139.2024.00125"},{"issue":"12","key":"10.1016\/j.comcom.2026.108497_b26","doi-asserted-by":"crossref","first-page":"6683","DOI":"10.1109\/TAI.2024.3465441","article-title":"Get rid of your trail: Remotely erasing backdoors in federated learning","volume":"5","author":"Alam","year":"2024","journal-title":"IEEE Trans. Artif. Intell."},{"issue":"3","key":"10.1016\/j.comcom.2026.108497_b27","doi-asserted-by":"crossref","first-page":"1196","DOI":"10.1109\/TSC.2024.3355188","article-title":"Server-initiated federated unlearning to eliminate impacts of low-quality data","volume":"17","author":"Wang","year":"2024","journal-title":"IEEE Trans. Serv. Comput."},{"key":"10.1016\/j.comcom.2026.108497_b28","article-title":"Measuring catastrophic forgetting in neural networks","volume":"vol. 32","author":"Kemker","year":"2018"},{"key":"10.1016\/j.comcom.2026.108497_b29","first-page":"1","article-title":"Model recovery in federated unlearning with restricted server data resources","author":"Zhang","year":"2025","journal-title":"IEEE Internet Things J."},{"key":"10.1016\/j.comcom.2026.108497_b30","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113353","article-title":"Class-wise federated unlearning: Harnessing active forgetting with teacher\u2013student memory generation","volume":"316","author":"Li","year":"2025","journal-title":"Knowl.-Based Syst."},{"issue":"1","key":"10.1016\/j.comcom.2026.108497_b31","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1109\/TMC.2021.3075291","article-title":"Adaptive batch size for federated learning in resource-constrained edge computing","volume":"22","author":"Ma","year":"2021","journal-title":"IEEE Trans. Mob. Comput."},{"key":"10.1016\/j.comcom.2026.108497_b32","series-title":"International Conference on Machine Learning","first-page":"2260","article-title":"Momentum improves normalized sgd","author":"Cutkosky","year":"2020"},{"key":"10.1016\/j.comcom.2026.108497_b33","series-title":"Advances in Neural Information Processing Systems","article-title":"Limitations of the empirical Fisher approximation for natural gradient descent","volume":"32","author":"Kunstner","year":"2019"},{"key":"10.1016\/j.comcom.2026.108497_b34","series-title":"2020 IEEE International Conference on Big Data","first-page":"171","article-title":"Optimization of graph neural networks with natural gradient descent","author":"Izadi","year":"2020"},{"issue":"1","key":"10.1016\/j.comcom.2026.108497_b35","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1007\/s00591-010-0080-8","article-title":"Exponential moving average versus moving exponential average","volume":"58","author":"Klinker","year":"2011","journal-title":"Math. Semesterber."},{"key":"10.1016\/j.comcom.2026.108497_b36","unstructured":"D.P. Kingma, J. Ba, Adam: A Method for Stochastic Optimization, in: International Conference on Learning Representations, ICLR, 2015."},{"key":"10.1016\/j.comcom.2026.108497_b37","first-page":"10665","article-title":"AdaHessian: An adaptive second order optimizer for machine learning","volume":"vol. 35","author":"Yao","year":"2021"},{"key":"10.1016\/j.comcom.2026.108497_b38","unstructured":"S. Reddi, Z. Charles, M. Zaheer, Z. Garrett, K. Rush, J. Kone\u010dn\u00fd, S. Kumar, H.B. McMahan, Adaptive Federated Optimization, in: International Conference on Learning Representations, ICLR, 2021."},{"issue":"1","key":"10.1016\/j.comcom.2026.108497_b39","first-page":"3797","article-title":"New insights and perspectives on the natural gradient method","volume":"15","author":"Martens","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.comcom.2026.108497_b40","article-title":"Limitations of the empirical Fisher approximation for natural gradient descent","volume":"vol. 32","author":"Kunstner","year":"2019"},{"key":"10.1016\/j.comcom.2026.108497_b41","first-page":"26","article-title":"Lecture 6.5-rmsprop: Divide the gradient by a running average of its recent magnitude","volume":"vol. 4","author":"Tieleman","year":"2012"},{"key":"10.1016\/j.comcom.2026.108497_b42","series-title":"2024 IEEE Information Theory Workshop","first-page":"235","article-title":"Feduhb: Accelerating federated unlearning via polyak heavy ball method","author":"Jiang","year":"2024"},{"key":"10.1016\/j.comcom.2026.108497_b43","series-title":"2024 IEEE International Conference on Big Data (BigData)","first-page":"7822","article-title":"Efficient federated unlearning with adaptive differential privacy preservation","author":"Jiang","year":"2024"},{"key":"10.1016\/j.comcom.2026.108497_b44","doi-asserted-by":"crossref","unstructured":"M. Abadi, A. Chu, I. Goodfellow, H.B. McMahan, I. Mironov, K. Talwar, L. Zhang, 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":"10.1016\/j.comcom.2026.108497_b45","article-title":"Towards efficient and certified recovery from poisoning attacks in federated learning","author":"Jiang","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"issue":"6","key":"10.1016\/j.comcom.2026.108497_b46","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1109\/JSAC.2019.2904348","article-title":"Adaptive federated learning in resource constrained edge computing systems","volume":"37","author":"Wang","year":"2019","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"10.1016\/j.comcom.2026.108497_b47","series-title":"Adaptive federated optimization","author":"Reddi","year":"2020"},{"key":"10.1016\/j.comcom.2026.108497_b48","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"Paszke","year":"2019","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.comcom.2026.108497_b49","first-page":"800","article-title":"Tensorflow lite micro: Embedded machine learning for tinyml systems","volume":"3","author":"David","year":"2021","journal-title":"Proc. Mach. Learn. Syst."},{"key":"10.1016\/j.comcom.2026.108497_b50","series-title":"Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"key":"10.1016\/j.comcom.2026.108497_b51","doi-asserted-by":"crossref","first-page":"143","DOI":"10.1017\/S0962492900002919","article-title":"Approximation theory of the MLP model in neural networks","volume":"8","author":"Pinkus","year":"1999","journal-title":"Acta Numer."},{"key":"10.1016\/j.comcom.2026.108497_b52","article-title":"Image classification algorithm based on improved AlexNet","volume":"vol. 1813","author":"Li","year":"2021"},{"key":"10.1016\/j.comcom.2026.108497_b53","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11\u201314, 2016, Proceedings, Part IV 14","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"He","year":"2016"},{"key":"10.1016\/j.comcom.2026.108497_b54","doi-asserted-by":"crossref","unstructured":"C.-H. He, C. Zhang, S.-Z. Hu, Z. Tan, H.-M. Zhu, B. Ge, Chinese News Text Classification Algorithm Based on Online Knowledge Extension and Convolutional Neural Network, in: 2019 16th International Computer Conference on Wavelet Active Media Technology and Information Processing, 2019, pp. 204\u2013211.","DOI":"10.1109\/ICCWAMTIP47768.2019.9067631"},{"key":"10.1016\/j.comcom.2026.108497_b55","series-title":"ICASSP 2025-2025 IEEE International Conference on Acoustics, Speech and Signal Processing","first-page":"1","article-title":"Collaborative personalized federated learning via exponential moving average optimization","author":"Li","year":"2025"}],"container-title":["Computer Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0140366426000873?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0140366426000873?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,4,17]],"date-time":"2026-04-17T17:21:28Z","timestamp":1776446488000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0140366426000873"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":55,"alternative-id":["S0140366426000873"],"URL":"https:\/\/doi.org\/10.1016\/j.comcom.2026.108497","relation":{},"ISSN":["0140-3664"],"issn-type":[{"value":"0140-3664","type":"print"}],"subject":[],"published":{"date-parts":[[2026,4]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Enhancing federated unlearning using catastrophic forgetting in heterogeneous Industrial Internet of Things","name":"articletitle","label":"Article Title"},{"value":"Computer Communications","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.comcom.2026.108497","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"108497"}}