{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T17:55:32Z","timestamp":1781805332119,"version":"3.54.5"},"reference-count":50,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134296","type":"journal-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T16:24:51Z","timestamp":1781627091000},"page":"134296","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["SynFed-DP: A synergistic adaptive framework for differentially private heterogeneous federated learning"],"prefix":"10.1016","volume":"698","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3581-5515","authenticated-orcid":false,"given":"Wei","family":"Xue","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6003-1998","authenticated-orcid":false,"given":"Qi","family":"Min","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weichao","family":"Ding","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jin","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"4","key":"10.1016\/j.neucom.2026.134296_bib0005","first-page":"3326","article-title":"A survey on federated learning: the journey from centralized to distributed on-site learning and beyond","volume":"35","author":"Mothukuri","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"3","key":"10.1016\/j.neucom.2026.134296_bib0010","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."},{"issue":"4","key":"10.1016\/j.neucom.2026.134296_bib0015","doi-asserted-by":"crossref","first-page":"3347","DOI":"10.1109\/TKDE.2021.3124599","article-title":"A survey on federated learning systems: vision, hype and reality for data privacy and protection","volume":"35","author":"Li","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"issue":"2","key":"10.1016\/j.neucom.2026.134296_bib0020","doi-asserted-by":"crossref","first-page":"194","DOI":"10.1109\/TBDATA.2024.3362191","article-title":"Decentralized federated learning: a survey on security and privacy","volume":"10","author":"Hallaji","year":"2024","journal-title":"IEEE Trans. Big Data"},{"issue":"2","key":"10.1016\/j.neucom.2026.134296_bib0025","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1109\/TAI.2024.3363670","article-title":"Privacy inference attack and defense in centralized and federated learning: a comprehensive survey","volume":"6","author":"Rao","year":"2025","journal-title":"IEEE Trans. Artif. Intell."},{"issue":"2","key":"10.1016\/j.neucom.2026.134296_bib0030","doi-asserted-by":"crossref","first-page":"1407","DOI":"10.1109\/TNET.2023.3317870","article-title":"Shield against gradient leakage attacks: adaptive privacy-preserving federated learning","volume":"32","author":"Hu","year":"2024","journal-title":"IEEE\/ACM Trans. Netw."},{"issue":"1","key":"10.1016\/j.neucom.2026.134296_bib0035","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3547331","article-title":"A comprehensive survey on privacy attacks in federated learning","volume":"55","author":"Lyu","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"10.1016\/j.neucom.2026.134296_bib0040","series-title":"Theory of Cryptography Conference","first-page":"265","article-title":"Calibrating noise to sensitivity in private data analysis","author":"Dwork","year":"2006"},{"issue":"1","key":"10.1016\/j.neucom.2026.134296_bib0045","first-page":"108","article-title":"Applications of differential privacy in social network analysis: a survey","volume":"35","author":"Jiang","year":"2023","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"10.1016\/j.neucom.2026.134296_bib0050","series-title":"Proceedings of the ACM SIGSAC Conference on Computer and Communications Security","first-page":"308","article-title":"Deep learning with differential privacy","author":"Abadi","year":"2016"},{"key":"10.1016\/j.neucom.2026.134296_bib0055","doi-asserted-by":"crossref","first-page":"7211","DOI":"10.1109\/TIFS.2025.3581103","article-title":"Hardening LLM fine-tuning: from differentially private data selection to trustworthy model quantization","volume":"20","author":"Deng","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.neucom.2026.134296_bib0060","author":"Fu"},{"issue":"1","key":"10.1016\/j.neucom.2026.134296_bib0065","doi-asserted-by":"crossref","first-page":"3635","DOI":"10.1109\/TCE.2023.3338464","article-title":"Differentially private federated learning with importance client sampling","volume":"70","author":"Chen","year":"2024","journal-title":"IEEE Trans. Consum. Electron."},{"key":"10.1016\/j.neucom.2026.134296_bib0070","series-title":"International Conference on Very Large Databases","first-page":"2826","article-title":"Uldp-FL: federated learning with across-silo user-level differential privacy","volume":"vol. 17","author":"Kato","year":"2024"},{"issue":"5","key":"10.1016\/j.neucom.2026.134296_bib0075","doi-asserted-by":"crossref","first-page":"4094","DOI":"10.1109\/TII.2025.3538096","article-title":"Energy-efficient wireless resource allocation for heterogeneous federated multitask networks based on evolutionary learning","volume":"21","author":"Jiang","year":"2025","journal-title":"IEEE Trans. Ind. Inform."},{"issue":"12","key":"10.1016\/j.neucom.2026.134296_bib0080","doi-asserted-by":"crossref","first-page":"2693","DOI":"10.1109\/TPDS.2025.3611304","article-title":"FedSR: a semi-decentralized federated learning framework for Non-IID data based on incremental subgradient optimization","volume":"36","author":"Huang","year":"2025","journal-title":"IEEE Trans. Parallel Distrib. Syst."},{"key":"10.1016\/j.neucom.2026.134296_bib0085","doi-asserted-by":"crossref","first-page":"5690","DOI":"10.1109\/TIFS.2025.3577498","article-title":"PriRoAgg: achieving robust model aggregation with minimum privacy leakage for federated learning","volume":"20","author":"Hou","year":"2025","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.neucom.2026.134296_bib0090","series-title":"Proceedings of the ACM SIGSAC Conference on Computer and Communications Security","first-page":"303","article-title":"Cross-silo federated learning with record-level personalized differential privacy","author":"Liu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134296_bib0095","series-title":"Advances in Neural Information Processing Systems","first-page":"5925","article-title":"On privacy and personalization in cross-silo federated learning","volume":"vol. 35","author":"Liu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134296_bib0100","series-title":"IEEE International Conference on Trust, Security and Privacy in Computing and Communications","first-page":"656","article-title":"Adap DP-FL: differentially private federated learning with adaptive noise","author":"Fu","year":"2022"},{"key":"10.1016\/j.neucom.2026.134296_bib0105","series-title":"Proceedings of the International Workshop on Security and Privacy of Sensing Systems","first-page":"22","article-title":"ACLI-DPFL: differentially private federated learning with adaptive clipping and local iteration","author":"Nakajima","year":"2025"},{"key":"10.1016\/j.neucom.2026.134296_bib0110","series-title":"European Conference on Computer Vision","article-title":"AdaCLIP: adapting CLIP with hybrid learnable prompts for zero-shot anomaly detection","author":"Cao","year":"2024"},{"key":"10.1016\/j.neucom.2026.134296_bib0115","series-title":"International Conference on Learning Representations","article-title":"Learning differentially private recurrent language models","author":"McMahan","year":"2018"},{"issue":"11","key":"10.1016\/j.neucom.2026.134296_bib0120","doi-asserted-by":"crossref","first-page":"17586","DOI":"10.1109\/TVT.2024.3423718","article-title":"Communication-efficient and privacy-preserving federated learning via joint knowledge distillation and differential privacy in bandwidth-constrained networks","volume":"73","author":"Gad","year":"2024","journal-title":"IEEE Trans. Veh. Technol."},{"issue":"2","key":"10.1016\/j.neucom.2026.134296_bib0125","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1016\/j.ejor.2023.08.040","article-title":"An explainable federated learning and blockchain-based secure credit modeling method","volume":"317","author":"Yang","year":"2024","journal-title":"Eur. J. Oper. Res."},{"issue":"2","key":"10.1016\/j.neucom.2026.134296_bib0130","first-page":"1679","article-title":"A differential privacy federated learning scheme based on adaptive Gaussian noise","volume":"138","author":"Jiao","year":"2023","journal-title":"CMES - Comput. Model. Eng. Sci."},{"issue":"4","key":"10.1016\/j.neucom.2026.134296_bib0135","doi-asserted-by":"crossref","first-page":"2708","DOI":"10.1109\/TNSE.2022.3168969","article-title":"AdaFed: optimizing participation-aware federated learning with adaptive aggregation weights","volume":"9","author":"Tan","year":"2022","journal-title":"IEEE Trans. Netw. Sci. Eng."},{"key":"10.1016\/j.neucom.2026.134296_bib0140","series-title":"IEEE INFOCOM - IEEE Conference on Computer Communications","first-page":"1","article-title":"AdaPDP: adaptive personalized differential privacy","author":"Niu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134296_bib0145","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2023.120266","article-title":"A novel local differential privacy federated learning under multi-privacy regimes","volume":"227","author":"Liu","year":"2023","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.neucom.2026.134296_bib0150","series-title":"Proceedings of the ACM International Workshop on Edge Systems, Analytics and Networking","first-page":"61","article-title":"LDP-fed: federated learning with local differential privacy","author":"Truex","year":"2020"},{"key":"10.1016\/j.neucom.2026.134296_bib0155","series-title":"Artificial Intelligence and Statistics, 54","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","author":"McMahan","year":"2017"},{"key":"10.1016\/j.neucom.2026.134296_bib0160","series-title":"Proceedings of the International Conference on Machine Learning, 80","first-page":"394","article-title":"Improving the Gaussian mechanism for differential privacy: analytical calibration and optimal denoising","author":"Balle","year":"2018"},{"key":"10.1016\/j.neucom.2026.134296_bib0165","author":"Reddi"},{"key":"10.1016\/j.neucom.2026.134296_bib0170","doi-asserted-by":"crossref","first-page":"3454","DOI":"10.1109\/TIFS.2020.2988575","article-title":"Federated learning with differential privacy: algorithms and performance analysis","volume":"15","author":"Wei","year":"2020","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"10.1016\/j.neucom.2026.134296_bib0175","author":"Geyer"},{"key":"10.1016\/j.neucom.2026.134296_bib0180","series-title":"Proceedings of the International Conference on Machine Learning","first-page":"5827","article-title":"A tail-index analysis of stochastic gradient noise in deep neural networks","volume":"vol. 97","author":"Simsekli","year":"2019"},{"key":"10.1016\/j.neucom.2026.134296_bib0185","series-title":"Advances in Neural Information Processing Systems, 35","first-page":"17017","article-title":"Taming fat-tailed (\u201c heavier-tailed\u201d with potentially infinite variance) noise in federated learning","author":"Yang","year":"2022"},{"key":"10.1016\/j.neucom.2026.134296_bib0190","author":"Pichapati"},{"key":"10.1016\/j.neucom.2026.134296_bib0195","series-title":"IEEE Computer Security Foundations Symposium","first-page":"263","article-title":"R\u00e9nyi differential privacy","author":"Mironov","year":"2017"},{"key":"10.1016\/j.neucom.2026.134296_bib0200","series-title":"International Conference on Learning Representations","article-title":"Local SGD converges fast and communicates little","author":"Stich","year":"2019"},{"key":"10.1016\/j.neucom.2026.134296_bib0205","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12109","article-title":"An upload-efficient scheme for transferring knowledge from a server-side pre-trained generator to clients in heterogeneous federated learning","author":"Zhang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134296_bib0210","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2025.113008","article-title":"Bidirectional domain transfer knowledge distillation for catastrophic forgetting in federated learning with heterogeneous data","volume":"311","author":"Min","year":"2025","journal-title":"Knowl.-based Syst."},{"key":"10.1016\/j.neucom.2026.134296_bib0215","series-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"10.1016\/j.neucom.2026.134296_bib0220","doi-asserted-by":"crossref","first-page":"2032","DOI":"10.1038\/s41467-022-29763-x","article-title":"Communication-efficient federated learning via knowledge distillation","volume":"13","author":"Wu","year":"2022","journal-title":"Nat. Commun."},{"key":"10.1016\/j.neucom.2026.134296_bib0225","series-title":"IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks","first-page":"349","article-title":"ALI-DPFL: differentially private federated learning with adaptive local iterations","author":"Ling","year":"2024"},{"key":"10.1016\/j.neucom.2026.134296_bib0230","series-title":"IEEE\/ACM International Symposium on Quality of Service","first-page":"1","article-title":"AdaDP-CFL: cluster federated learning with adaptive clipping threshold differential privacy","author":"Yang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134296_bib0235","doi-asserted-by":"crossref","DOI":"10.1016\/j.comnet.2025.111139","article-title":"Differential private federated learning with per-sample adaptive clipping and layer-wise gradient perturbation","volume":"261","author":"Yuan","year":"2025","journal-title":"Comput. Netw."},{"key":"10.1016\/j.neucom.2026.134296_bib0240","doi-asserted-by":"crossref","DOI":"10.1016\/j.sysarc.2024.103067","article-title":"CLFLDP: communication-efficient layer clipping federated learning with local differential privacy","volume":"148","author":"Chen","year":"2024","journal-title":"J. Syst. Archit."},{"key":"10.1016\/j.neucom.2026.134296_bib0245","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.134296_bib0250","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"2261","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226016942?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226016942?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T17:35:04Z","timestamp":1781804104000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226016942"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":50,"alternative-id":["S0925231226016942"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134296","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SynFed-DP: A synergistic adaptive framework for differentially private heterogeneous federated learning","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134296","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":"134296"}}