{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,8]],"date-time":"2025-06-08T04:01:04Z","timestamp":1749355264227,"version":"3.41.0"},"reference-count":43,"publisher":"Springer Science and Business Media LLC","issue":"5-6","license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,6]]},"DOI":"10.1007\/s13042-024-02436-5","type":"journal-article","created":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T16:03:10Z","timestamp":1730217790000},"page":"3067-3083","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Two-stage model fusion scheme based on knowledge distillation for stragglers in federated learning"],"prefix":"10.1007","volume":"16","author":[{"given":"Jiuyun","family":"Xu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowen","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kongshang","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingzhi","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"2436_CR1","unstructured":"McMahan HB, Moore E, Ramage D et\u00a0al (2016) Federated learning of deep networks using model averaging. arXiv:1602.05629"},{"key":"2436_CR2","unstructured":"McMahan B, Moore E, Ramage D et\u00a0al (2017) Communication-efficient learning of deep networks from decentralized data. In: Artificial intelligence and statistics, PMLR, pp 1273\u20131282"},{"key":"2436_CR3","unstructured":"Li T, Sahu AK, Zaheer M et\u00a0al (2020) Federated optimization in heterogeneous networks. In: Proceedings of machine learning and systems, vol 2, pp 429\u2013450. https:\/\/proceedings.mlsys.org\/paper_files\/paper\/2020\/hash\/1f5fe83998a09396ebe6477d9475ba0c-Abstract.html"},{"issue":"5","key":"2436_CR4","doi-asserted-by":"publisher","first-page":"655","DOI":"10.1109\/TC.2020.2994391","volume":"70","author":"W Wu","year":"2020","unstructured":"Wu W, He L, Lin W et al (2020) Safa: a semi-asynchronous protocol for fast federated learning with low overhead. IEEE Trans Comput 70(5):655\u2013668. https:\/\/doi.org\/10.1109\/TC.2020.2994391","journal-title":"IEEE Trans Comput"},{"key":"2436_CR5","doi-asserted-by":"crossref","unstructured":"Zhang T, Gao L, Lee S et\u00a0al (2023) Timelyfl: heterogeneity-aware asynchronous federated learning with adaptive partial training. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 5064\u20135073","DOI":"10.1109\/CVPRW59228.2023.00535"},{"issue":"2","key":"2436_CR6","doi-asserted-by":"publisher","first-page":"1342","DOI":"10.1109\/COMST.2021.3058573","volume":"23","author":"OA Wahab","year":"2021","unstructured":"Wahab OA, Mourad A, Otrok H et al (2021) Federated machine learning: survey, multi-level classification, desirable criteria and future directions in communication and networking systems. IEEE Commun Surv Tutor 23(2):1342\u20131397. https:\/\/doi.org\/10.1109\/COMST.2021.3058573","journal-title":"IEEE Commun Surv Tutor"},{"key":"2436_CR7","doi-asserted-by":"publisher","unstructured":"Wang Z, Hu Q, Xu M et\u00a0al (2023) Straggler mitigation and latency optimization in blockchain-based hierarchical federated learning. https:\/\/doi.org\/10.48550\/arXiv.2308.01296","DOI":"10.48550\/arXiv.2308.01296"},{"issue":"4","key":"2436_CR8","doi-asserted-by":"publisher","first-page":"2261","DOI":"10.1109\/TSC.2020.3044043","volume":"15","author":"Z Li","year":"2020","unstructured":"Li Z, Zhou H, Zhou T et al (2020) Esync: accelerating intra-domain federated learning in heterogeneous data centers. IEEE Trans Serv Comput 15(4):2261\u20132274. https:\/\/doi.org\/10.1109\/TSC.2020.3044043","journal-title":"IEEE Trans Serv Comput"},{"key":"2436_CR9","doi-asserted-by":"publisher","unstructured":"Xie C, Koyejo S, Gupta I (2019) Asynchronous federated optimization. https:\/\/doi.org\/10.48550\/arXiv.1903.03934","DOI":"10.48550\/arXiv.1903.03934"},{"key":"2436_CR10","unstructured":"Nguyen J, Malik K, Zhan H et\u00a0al (2022) Federated learning with buffered asynchronous aggregation. In: International conference on artificial intelligence and statistics, PMLR, pp 3581\u20133607. https:\/\/proceedings.mlr.press\/v151\/nguyen22b.html"},{"key":"2436_CR11","doi-asserted-by":"publisher","first-page":"48970","DOI":"10.1109\/ACCESS.2020.2978082","volume":"8","author":"X Lu","year":"2020","unstructured":"Lu X, Liao Y, Lio P et al (2020) Privacy-preserving asynchronous federated learning mechanism for edge network computing. IEEE Access 8:48970\u201348981. https:\/\/doi.org\/10.1109\/ACCESS.2020.2978082","journal-title":"IEEE Access"},{"key":"2436_CR12","doi-asserted-by":"publisher","unstructured":"Li X, Qu Z, Tang B et\u00a0al (2021) Stragglers are not disaster: a hybrid federated learning algorithm with delayed gradients. https:\/\/doi.org\/10.48550\/arXiv.2102.06329","DOI":"10.48550\/arXiv.2102.06329"},{"issue":"3","key":"2436_CR13","doi-asserted-by":"publisher","first-page":"1007","DOI":"10.1109\/TPDS.2023.3237752","volume":"34","author":"Y Zhang","year":"2023","unstructured":"Zhang Y, Liu D, Duan M et al (2023) Fedmds: an efficient model discrepancy-aware semi-asynchronous clustered federated learning framework. IEEE Trans Parallel Distrib Syst 34(3):1007\u20131019. https:\/\/doi.org\/10.1109\/TPDS.2023.3237752","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"2436_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/s13042-024-02119-1","author":"S Ji","year":"2024","unstructured":"Ji S, Tan Y, Saravirta T et al (2024) Emerging trends in federated learning: from model fusion to federated x learning. Int J Mach Learn Cybern. https:\/\/doi.org\/10.1007\/s13042-024-02119-1","journal-title":"Int J Mach Learn Cybern"},{"key":"2436_CR15","unstructured":"Zhu Z, Hong J, Zhou J (2021) Data-free knowledge distillation for heterogeneous federated learning. In: International conference on machine learning, PMLR, pp 12878\u201312889. https:\/\/proceedings.mlr.press\/v139\/zhu21b.html"},{"key":"2436_CR16","doi-asserted-by":"publisher","unstructured":"Kim YG, Wu CJ (2021) Autofl: enabling heterogeneity-aware energy efficient federated learning. In: MICRO-54: 54th annual IEEE\/ACM international symposium on microarchitecture, pp 183\u2013198. https:\/\/doi.org\/10.1145\/3466752.3480129","DOI":"10.1145\/3466752.3480129"},{"key":"2436_CR17","doi-asserted-by":"publisher","unstructured":"Chai Z, Ali A, Zawad S et\u00a0al (2020) Tifl: a tier-based federated learning system. In: Proceedings of the 29th international symposium on high-performance parallel and distributed computing, pp 125\u2013136. https:\/\/doi.org\/10.1145\/3369583.3392686","DOI":"10.1145\/3369583.3392686"},{"key":"2436_CR18","doi-asserted-by":"publisher","unstructured":"Nishio T, Yonetani R (2019) Client selection for federated learning with heterogeneous resources in mobile edge. In: ICC 2019-2019 IEEE international conference on communications (ICC). IEEE, pp 1\u20137. https:\/\/doi.org\/10.1109\/ICC.2019.8761315","DOI":"10.1109\/ICC.2019.8761315"},{"key":"2436_CR19","doi-asserted-by":"publisher","unstructured":"Dhakal S, Prakash S, Yona Y et\u00a0al (2019) Coded federated learning. In: 2019 IEEE Globecom workshops (GC Wkshps). IEEE, pp 1\u20136. https:\/\/doi.org\/10.1109\/GCWkshps45667.2019.9024521","DOI":"10.1109\/GCWkshps45667.2019.9024521"},{"key":"2436_CR20","doi-asserted-by":"publisher","unstructured":"Hao J, Zhao Y, Zhang J (2020) Time efficient federated learning with semi-asynchronous communication. In: 2020 IEEE 26th international conference on parallel and distributed systems (ICPADS). IEEE, pp 156\u2013163. https:\/\/doi.org\/10.1109\/ICPADS51040.2020.00030","DOI":"10.1109\/ICPADS51040.2020.00030"},{"key":"2436_CR21","doi-asserted-by":"publisher","unstructured":"Chen Y, Ning Y, Slawski M et\u00a0al (2020) Asynchronous online federated learning for edge devices with non-iid data. In: 2020 IEEE international conference on big data (Big Data). IEEE, pp 15\u201324. https:\/\/doi.org\/10.1109\/BigData50022.2020.9378161","DOI":"10.1109\/BigData50022.2020.9378161"},{"issue":"12","key":"2436_CR22","doi-asserted-by":"publisher","first-page":"3291","DOI":"10.1109\/TPDS.2022.3150579","volume":"33","author":"Z Zhou","year":"2022","unstructured":"Zhou Z, Li Y, Ren X et al (2022) Towards efficient and stable k-asynchronous federated learning with unbounded stale gradients on non-iid data. IEEE Trans Parallel Distrib Syst 33(12):3291\u20133305. https:\/\/doi.org\/10.1109\/TPDS.2022.3150579","journal-title":"IEEE Trans Parallel Distrib Syst"},{"key":"2436_CR23","doi-asserted-by":"publisher","unstructured":"Hinton G, Vinyals O, Dean J (2015) Distilling the knowledge in a neural network. https:\/\/doi.org\/10.48550\/arXiv.1503.02531","DOI":"10.48550\/arXiv.1503.02531"},{"key":"2436_CR24","doi-asserted-by":"crossref","unstructured":"Yun S, Park J, Lee K et\u00a0al (2020) Regularizing class-wise predictions via self-knowledge distillation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 13876\u201313885","DOI":"10.1109\/CVPR42600.2020.01389"},{"key":"2436_CR25","doi-asserted-by":"publisher","unstructured":"Hahn S, Choi H (2019) Self-knowledge distillation in natural language processing. https:\/\/doi.org\/10.48550\/arXiv.1908.01851","DOI":"10.48550\/arXiv.1908.01851"},{"key":"2436_CR26","doi-asserted-by":"crossref","unstructured":"Ji M, Shin S, Hwang S et\u00a0al (2021) Refine myself by teaching myself: Feature refinement via self-knowledge distillation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 10664\u201310673","DOI":"10.1109\/CVPR46437.2021.01052"},{"key":"2436_CR27","doi-asserted-by":"crossref","unstructured":"Kim K, Ji B, Yoon D et\u00a0al (2021) Self-knowledge distillation with progressive refinement of targets. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 6567\u20136576","DOI":"10.1109\/ICCV48922.2021.00650"},{"key":"2436_CR28","doi-asserted-by":"publisher","unstructured":"Tang J, Shivanna R, Zhao Z et\u00a0al (2020) Understanding and improving knowledge distillation. https:\/\/doi.org\/10.48550\/arXiv.2002.03532","DOI":"10.48550\/arXiv.2002.03532"},{"key":"2436_CR29","doi-asserted-by":"publisher","unstructured":"Sau BB, Balasubramanian VN (2016) Deep model compression: distilling knowledge from noisy teachers. https:\/\/doi.org\/10.48550\/arXiv.1610.09650","DOI":"10.48550\/arXiv.1610.09650"},{"key":"2436_CR30","doi-asserted-by":"publisher","unstructured":"Yuan F, Shou L, Pei J et\u00a0al (2021) Reinforced multi-teacher selection for knowledge distillation. In: Proceedings of the AAAI conference on artificial intelligence, pp 14284\u201314291. https:\/\/doi.org\/10.1609\/aaai.v35i16.17680","DOI":"10.1609\/aaai.v35i16.17680"},{"key":"2436_CR31","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.neucom.2020.07.048","volume":"415","author":"Y Liu","year":"2020","unstructured":"Liu Y, Zhang W, Wang J (2020) Adaptive multi-teacher multi-level knowledge distillation. Neurocomputing 415:106\u2013113. https:\/\/doi.org\/10.1016\/j.neucom.2020.07.048","journal-title":"Neurocomputing"},{"key":"2436_CR32","first-page":"2351","volume":"33","author":"T Lin","year":"2020","unstructured":"Lin T, Kong L, Stich SU et al (2020) Ensemble distillation for robust model fusion in federated learning. Adv Neural Inf Process Syst 33:2351\u20132363","journal-title":"Adv Neural Inf Process Syst"},{"key":"2436_CR33","doi-asserted-by":"publisher","unstructured":"Daliang L, Junpu W (2019) Fedmd: heterogenous federated learning via model distillation. https:\/\/doi.org\/10.48550\/arXiv.1910.03581","DOI":"10.48550\/arXiv.1910.03581"},{"key":"2436_CR34","unstructured":"Yang Z, Zhang Y, Zheng Y et\u00a0al (2024) Fedfed: feature distillation against data heterogeneity in federated learning. Advances in neural information processing systems, vol 36"},{"key":"2436_CR35","doi-asserted-by":"crossref","unstructured":"Ma Y, Xie Z, Wang J et\u00a0al (2022) Continual federated learning based on knowledge distillation. In: IJCAI, pp 2182\u20132188","DOI":"10.24963\/ijcai.2022\/303"},{"key":"2436_CR36","doi-asserted-by":"publisher","unstructured":"Chan YH, Ngai EC (2021) Fedhe: heterogeneous models and communication-efficient federated learning. In: 2021 17th international conference on mobility, sensing and networking (MSN). IEEE, pp 207\u2013214. https:\/\/doi.org\/10.1109\/MSN53354.2021.00043","DOI":"10.1109\/MSN53354.2021.00043"},{"issue":"6","key":"2436_CR37","doi-asserted-by":"publisher","first-page":"1107","DOI":"10.1109\/TPDS.2023.3289444","volume":"35","author":"Z Wu","year":"2023","unstructured":"Wu Z, Sun S, Wang Y et al (2023) Fedict: federated multi-task distillation for multi-access edge computing. IEEE Trans Parallel Distrib Syst 35(6):1107\u20131121. https:\/\/doi.org\/10.1109\/TPDS.2023.3289444","journal-title":"IEEE Trans Parallel Distrib Syst"},{"issue":"11","key":"2436_CR38","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun Y, Bottou L, Bengio Y et al (1998) Gradient-based learning applied to document recognition. Proc IEEE 86(11):2278\u20132324. https:\/\/doi.org\/10.1109\/5.726791","journal-title":"Proc IEEE"},{"key":"2436_CR39","unstructured":"Krizhevsky A, Hinton G et\u00a0al (2009) Learning multiple layers of features from tiny images"},{"key":"2436_CR40","doi-asserted-by":"publisher","unstructured":"Xiao H, Rasul K, Vollgraf R (2017) Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. https:\/\/doi.org\/10.48550\/arXiv.1708.07747","DOI":"10.48550\/arXiv.1708.07747"},{"key":"2436_CR41","unstructured":"Yurochkin M, Agarwal M, Ghosh S et\u00a0al (2019) Bayesian nonparametric federated learning of neural networks. In: International conference on machine learning, PMLR, pp 7252\u20137261. https:\/\/proceedings.mlr.press\/v97\/yurochkin19a.html"},{"key":"2436_CR42","doi-asserted-by":"publisher","unstructured":"Hsu TMH, Qi H, Brown M (2019) Measuring the effects of non-identical data distribution for federated visual classification. https:\/\/doi.org\/10.48550\/arXiv.1909.06335","DOI":"10.48550\/arXiv.1909.06335"},{"key":"2436_CR43","doi-asserted-by":"publisher","unstructured":"Naeini MP, Cooper G, Hauskrecht M (2015) Obtaining well calibrated probabilities using Bayesian binning. In: Proceedings of the AAAI conference on artificial intelligence. https:\/\/doi.org\/10.1609\/aaai.v29i1.9602","DOI":"10.1609\/aaai.v29i1.9602"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02436-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-024-02436-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-024-02436-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,7]],"date-time":"2025-06-07T04:28:52Z","timestamp":1749270532000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-024-02436-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"references-count":43,"journal-issue":{"issue":"5-6","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["2436"],"URL":"https:\/\/doi.org\/10.1007\/s13042-024-02436-5","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"type":"print","value":"1868-8071"},{"type":"electronic","value":"1868-808X"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 October 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 October 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}