{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T21:17:55Z","timestamp":1783027075146,"version":"3.54.6"},"reference-count":46,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"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":["61802131"],"award-info":[{"award-number":["61802131"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005015","name":"South China University of Technology","doi-asserted-by":"publisher","award":["2024B105611002"],"award-info":[{"award-number":["2024B105611002"]}],"id":[{"id":"10.13039\/501100005015","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2026A1515011892"],"award-info":[{"award-number":["2026A1515011892"]}],"id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114158","type":"journal-article","created":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T23:54:05Z","timestamp":1780530845000},"page":"114158","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"PB","title":["Soft local reactivation for communication efficient federated learning"],"prefix":"10.1016","volume":"180","author":[{"given":"Ziyang","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chang","family":"Mu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4753-9022","authenticated-orcid":false,"given":"Kailing","family":"Guo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Tian","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiangmin","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"1","key":"10.1016\/j.patcog.2026.114158_b1","doi-asserted-by":"crossref","first-page":"100005","DOI":"10.1016\/j.dtrs.2025.100005","article-title":"The role of artificial intelligence in shaping dentistry through advancement in data acquisition, clinical practice, education, and research","volume":"1","author":"Tay","year":"2026","journal-title":"Dent. Res."},{"issue":"8058","key":"10.1016\/j.patcog.2026.114158_b2","doi-asserted-by":"crossref","first-page":"368","DOI":"10.1038\/s41586-025-08854-x","article-title":"Universal photonic artificial intelligence acceleration","volume":"640","author":"Ahmed","year":"2025","journal-title":"Nature"},{"key":"10.1016\/j.patcog.2026.114158_b3","unstructured":"B. McMahan, E. Moore, D. Ramage, S. Hampson, B.A. y Arcas, Communication-efficient learning of deep networks from decentralized data, in: Proceedings of the International Conference on Artificial Intelligence and Statistics, vol. 54, 2017, pp. 1273\u20131282."},{"key":"10.1016\/j.patcog.2026.114158_b4","doi-asserted-by":"crossref","first-page":"111048","DOI":"10.1016\/j.patcog.2024.111048","article-title":"Federated incremental learning algorithm based on topological data analysis","volume":"158","author":"Hu","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114158_b5","doi-asserted-by":"crossref","first-page":"111665","DOI":"10.1016\/j.patcog.2025.111665","article-title":"A novel federated learning framework for semantic segmentation of terminal block in smart substation","author":"Xie","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114158_b6","doi-asserted-by":"crossref","unstructured":"S. Hu, Y. Zhu, P. Cheng, C. Guo, K. Tan, J. Padhye, K. Chen, Tagger: Practical PFC deadlock prevention in data center networks, in: Proceedings of the International Conference on Emerging Networking Experiments and Technologies, 2017, pp. 451\u2013463.","DOI":"10.1145\/3143361.3143382"},{"key":"10.1016\/j.patcog.2026.114158_b7","doi-asserted-by":"crossref","unstructured":"S. Hu, et al., Deadlocks in datacenter networks: Why do they form, and how to avoid them, in: Proceedings of the ACM Workshop on Hot Topics in Networks, 2016, pp. 92\u201398.","DOI":"10.1145\/3005745.3005760"},{"key":"10.1016\/j.patcog.2026.114158_b8","doi-asserted-by":"crossref","unstructured":"S. Bibikar, H. Vikalo, Z. Wang, X. Chen, Federated dynamic sparse training: Computing less, communicating less, yet learning better, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, 2022, pp. 6080\u20136088, 6.","DOI":"10.1609\/aaai.v36i6.20555"},{"key":"10.1016\/j.patcog.2026.114158_b9","first-page":"1","article-title":"Model pruning enables efficient federated learning on edge devices","author":"Jiang","year":"2022","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.114158_b10","unstructured":"D. Alistarh, D. Grubic, J. Li, R. Tomioka, M. Vojnovic, QSGD: Communication-efficient SGD via gradient quantization and encoding, in: Proceedings of the Advances in Neural Information Processing Systems, vol. 30, 2017, pp. 1707\u20131718."},{"issue":"12","key":"10.1016\/j.patcog.2026.114158_b11","doi-asserted-by":"crossref","first-page":"10502","DOI":"10.1109\/TNNLS.2022.3167482","article-title":"IFL-GAN: Improved federated learning generative adversarial network with maximum mean discrepancy model aggregation","volume":"34","author":"Li","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.114158_b12","doi-asserted-by":"crossref","first-page":"110122","DOI":"10.1016\/j.patcog.2023.110122","article-title":"Reducing communication in federated learning via efficient client sampling","volume":"148","author":"Ribero","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114158_b13","doi-asserted-by":"crossref","unstructured":"X. Jiang, C. Borcea, Complement Sparsification: Low-Overhead Model Pruning for Federated Learning, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37, 2023, pp. 8087\u20138095, 7.","DOI":"10.1609\/aaai.v37i7.25977"},{"key":"10.1016\/j.patcog.2026.114158_b14","series-title":"LotteryFL: Personalized and communication-efficient federated learning with lottery ticket hypothesis on non-iid datasets","author":"Li","year":"2020"},{"key":"10.1016\/j.patcog.2026.114158_b15","first-page":"1","article-title":"FedPAGE: Pruning adaptively toward global efficiency of heterogeneous federated learning","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Netw."},{"issue":"4","key":"10.1016\/j.patcog.2026.114158_b16","first-page":"3","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume":"56","author":"Han","year":"2015","journal-title":"Fiber"},{"key":"10.1016\/j.patcog.2026.114158_b17","unstructured":"X. Dong, S. Chen, S. Pan, Learning to prune deep neural networks via layer-wise optimal brain surgeon, in: Proceedings of the Advances in Neural Information Processing Systems, vol. 30, 2017, pp. 1\u201311."},{"key":"10.1016\/j.patcog.2026.114158_b18","unstructured":"N. Lee, T. Ajanthan, P.H. Torr, SNIP: Single-shot network pruning based on connection sensitivity, in: Proceedings of the International Conference on Learning Representations, 2019, pp. 1\u201315."},{"key":"10.1016\/j.patcog.2026.114158_b19","unstructured":"C. Wang, G. Zhang, R. Grosse, Picking winning tickets before training by preserving gradient flow, in: Proceedings of the International Conference on Learning Representations, 2020, pp. 1\u201311."},{"key":"10.1016\/j.patcog.2026.114158_b20","doi-asserted-by":"crossref","unstructured":"A. Good, J. Lin, X. Yu, H. Sieg, M. Fergurson, S. Zhe, J. Wieczorek, T. Serra, Recall distortion in neural network pruning and the undecayed pruning algorithm, in: Proceedings of the Advances in Neural Information Processing Systems, vol. 35, 2022, pp. 32762\u201332776.","DOI":"10.52202\/068431-2374"},{"key":"10.1016\/j.patcog.2026.114158_b21","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.neunet.2022.10.011","article-title":"EvoPruneDeepTL: An evolutionary pruning model for transfer learning based deep neural networks","volume":"158","author":"Poyatos","year":"2023","journal-title":"Neural Netw."},{"issue":"10","key":"10.1016\/j.patcog.2026.114158_b22","doi-asserted-by":"crossref","first-page":"7946","DOI":"10.1109\/TNNLS.2022.3147269","article-title":"Carrying out CNN channel pruning in a white box","volume":"34","author":"Zhang","year":"2023","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.patcog.2026.114158_b23","unstructured":"X. Li, K. Huang, W. Yang, S. Wang, Z. Zhang, On the convergence of FedAvg on non-iid data, in: Proceedings of the International Conference on Learning Representations, 2020, pp. 1\u201326."},{"key":"10.1016\/j.patcog.2026.114158_b24","series-title":"Measuring the effects of non-identical data distribution for federated visual classification","author":"Hsu","year":"2019"},{"key":"10.1016\/j.patcog.2026.114158_b25","doi-asserted-by":"crossref","first-page":"127973","DOI":"10.1016\/j.eswa.2025.127973","article-title":"FedAgent: Federated learning on non-IID data via reinforcement learning and knowledge distillation","volume":"285","author":"Sun","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.114158_b26","doi-asserted-by":"crossref","first-page":"111455","DOI":"10.1016\/j.patcog.2025.111455","article-title":"FedPnP: Personalized graph-structured federated learning","author":"Rasti-Meymandi","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114158_b27","doi-asserted-by":"crossref","unstructured":"H. Zheng, S. Song, Z. Hu, M. Zheng, L. Yang, A. Xu, R. Zhao, R. Pu, R. Fang, B. Wang, Intra-class unbiased prototype aggregation and classifier collaboration for personalized federated learning, in: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 40, 2026, pp. 28795\u201328803, 34.","DOI":"10.1609\/aaai.v40i34.40113"},{"key":"10.1016\/j.patcog.2026.114158_b28","unstructured":"M. Luo, F. Chen, D. Hu, Y. Zhang, J. Liang, J. Feng, No fear of heterogeneity: Classifier calibration for federated learning with non-iid data, in: Proceedings of the Advances in Neural Information Processing Systems, vol. 34, 2021, pp. 5972\u20135984."},{"key":"10.1016\/j.patcog.2026.114158_b29","unstructured":"Y. Lin, S. Han, H. Mao, Y. Wang, W.J. Dally, Deep gradient compression: Reducing the communication bandwidth for distributed training, in: Proceedings of the International Conference on Learning Representations, 2018, pp. 1\u201314."},{"key":"10.1016\/j.patcog.2026.114158_b30","unstructured":"R. H\u00f6nig, Y. Zhao, R. Mullins, DAdaQuant: Doubly-adaptive quantization for communication-efficient federated learning, in: Proceedings of the International Conference on Machine Learning, 2022, pp. 8852\u20138866."},{"key":"10.1016\/j.patcog.2026.114158_b31","doi-asserted-by":"crossref","unstructured":"S.-W. Kim, S. Kim, J. Kim, S. Ji, S.-H. Lee, FedWSQ: Efficient federated learning with weight standardization and distribution-aware non-uniform quantization, in: Proceedings of the International Conference on Computer Vision, 2025, pp. 4616\u20134625.","DOI":"10.1109\/ICCV51701.2025.00439"},{"key":"10.1016\/j.patcog.2026.114158_b32","unstructured":"N. Hyeon-Woo, M. Ye-Bin, T.-H. Oh, FedPara: Low-rank hadamard product for communication-efficient federated learning, in: Proceedings of the International Conference on Learning Representations, 2022, pp. 1\u201323."},{"key":"10.1016\/j.patcog.2026.114158_b33","unstructured":"S. Reddi, Z. Charles, M. Zaheer, Z. Garrett, K. Rush, J. Kone\u010dn\u1ef3, S. Kumar, H.B. McMahan, Adaptive federated optimization, in: Proceedings of the International Conference on Learning Representations, 2021, pp. 1\u201338."},{"key":"10.1016\/j.patcog.2026.114158_b34","unstructured":"M. Sun, Z. Liu, A. Bair, J.Z. Kolter, A simple and effective pruning approach for large language models, in: Proceedings of the International Conference on Learning Representations, 2024, pp. 1\u201323."},{"key":"10.1016\/j.patcog.2026.114158_b35","doi-asserted-by":"crossref","unstructured":"A. Prakash, J. Storer, D. Florencio, C. Zhang, RePr: Improved training of convolutional filters, in: Proceedings of the International Conference on Computer Vision and Pattern Recognition, 2019, pp. 10666\u201310675.","DOI":"10.1109\/CVPR.2019.01092"},{"key":"10.1016\/j.patcog.2026.114158_b36","unstructured":"T. Lin, S.U. Stich, L. Barba, D. Dmitriev, M. Jaggi, Dynamic model pruning with feedback, in: Proceedings of the International Conference on Learning Representations, 2020, pp. 1\u201322."},{"key":"10.1016\/j.patcog.2026.114158_b37","doi-asserted-by":"crossref","unstructured":"S. Alam, L. Liu, M. Yan, M. Zhang, FedRolex: Model-heterogeneous federated learning with rolling sub-model extraction, in: Proceedings of the Avances in Neural Information Processing Systems, vol. 35, 2022, pp. 29677\u201329690.","DOI":"10.52202\/068431-2152"},{"key":"10.1016\/j.patcog.2026.114158_b38","unstructured":"H. Huang, J. Yang, Y. Chen, J. Ye, D. Wu, FedRTS: Federated robust pruning via combinatorial thompson sampling, in: Proceedings of the Advances in Neural Information Processing Systems, vol. 38, 2026, pp. 162368\u2013162402."},{"key":"10.1016\/j.patcog.2026.114158_b39","doi-asserted-by":"crossref","unstructured":"J. Xue, M. Liu, S. Sun, Y. Wang, H. Jiang, X. Jiang, FedBIAD: Communication-efficient and accuracy-guaranteed federated learning with bayesian inference-based adaptive dropout, in: Proceedings of the International Parallel and Distributed Processing Symposium, 2023, pp. 489\u2013500.","DOI":"10.1109\/IPDPS54959.2023.00056"},{"key":"10.1016\/j.patcog.2026.114158_b40","unstructured":"U. Evci, T. Gale, J. Menick, P.S. Castro, E. Elsen, Rigging the lottery: Making all tickets winners, in: Proceedings of the International Conference on Machine Learning, 2020, pp. 2943\u20132952."},{"key":"10.1016\/j.patcog.2026.114158_b41","doi-asserted-by":"crossref","unstructured":"Y. Lecun, L. Bottou, Gradient-based learning applied to document recognition, in: Proceedings of the IEEE, vol. 86, 1998, pp. 2278\u20132324, 11.","DOI":"10.1109\/5.726791"},{"key":"10.1016\/j.patcog.2026.114158_b42","series-title":"Learning Multiple Layers of Features from Tiny Images","first-page":"1","author":"Krizhevsky","year":"2009"},{"issue":"7","key":"10.1016\/j.patcog.2026.114158_b43","first-page":"3","article-title":"Tiny imagenet visual recognition challenge","volume":"7","author":"Le","year":"2015","journal-title":"CS 231N"},{"key":"10.1016\/j.patcog.2026.114158_b44","unstructured":"M. Yurochkin, M. Agarwal, S. Ghosh, K. Greenewald, N. Hoang, Y. Khazaeni, Bayesian nonparametric federated learning of Neural networks, in: Proceedings of the International Conference on Machine Learning, 2019, pp. 7252\u20137261."},{"key":"10.1016\/j.patcog.2026.114158_b45","unstructured":"A. Dosovitskiy, L. Beyer, A. Kolesnikov, D. Weissenborn, X. Zhai, T. Unterthiner, M. Dehghani, M. Minderer, G. Heigold, S. Gelly, et al., An image is worth 16x16 words: Transformers for image recognition at scale, in: Proceedings of the International Conference on Learning Representations, 2021, pp. 1\u201321."},{"key":"10.1016\/j.patcog.2026.114158_b46","unstructured":"D.A.E. Acar, Y. Zhao, R.M. Navarro, M. Mattina, P.N. Whatmough, V. Saligrama, Federated learning based on dynamic regularization, in: Proceedings of the International Conference on Learning Representations, 2023, pp. 1\u201336."}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326011234?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326011234?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T20:24:45Z","timestamp":1783023885000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326011234"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":46,"alternative-id":["S0031320326011234"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114158","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Soft local reactivation for communication efficient federated learning","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114158","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114158"}}