{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T18:33:17Z","timestamp":1780338797939,"version":"3.54.1"},"reference-count":71,"publisher":"Elsevier BV","issue":"7","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100010418","name":"Institute of Information & Communications Technology Planning & Evaluation","doi-asserted-by":"publisher","award":["R S-2025-02263031"],"award-info":[{"award-number":["R S-2025-02263031"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["RS-2024-00423362"],"award-info":[{"award-number":["RS-2024-00423362"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Information Processing & Management"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.ipm.2026.104798","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T21:44:59Z","timestamp":1775598299000},"page":"104798","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PA","title":["A distributed quantization mechanism for lightweight federated learning model in heterogeneous on-device AI networks"],"prefix":"10.1016","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-0959-3852","authenticated-orcid":false,"given":"Misbah","family":"Bibi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qazi Waqas","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Syed Ali","family":"Yazdan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rashid","family":"Ahmad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Do-Hyeun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.ipm.2026.104798_b1","series-title":"Sparse communication for distributed gradient descent","author":"Aji","year":"2017"},{"key":"10.1016\/j.ipm.2026.104798_b2","series-title":"Advances in neural information processing systems","article-title":"QSGD: Communication-efficient SGD via gradient quantization and encoding","volume":"vol. 30","author":"Alistarh","year":"2017"},{"key":"10.1016\/j.ipm.2026.104798_b3","series-title":"Update aware device scheduling for federated learning at the wireless edge","author":"Amiri","year":"2020"},{"key":"10.1016\/j.ipm.2026.104798_b4","series-title":"Adaptive quantization for federated learning","author":"Amiri","year":"2021"},{"key":"10.1016\/j.ipm.2026.104798_b5","series-title":"Towards federated learning at scale: System design","author":"Bonawitz","year":"2019"},{"key":"10.1016\/j.ipm.2026.104798_b6","series-title":"2025 59th annual conference on information sciences and systems","first-page":"1","article-title":"Communication-efficient federated learning via clipped uniform quantization","author":"Bozorgasl","year":"2025"},{"issue":"1","key":"10.1016\/j.ipm.2026.104798_b7","doi-asserted-by":"crossref","first-page":"6085","DOI":"10.1038\/s41598-018-24271-9","article-title":"Recurrent neural networks for multivariate time series with missing values","volume":"8","author":"Che","year":"2018","journal-title":"Scientific Reports"},{"issue":"8","key":"10.1016\/j.ipm.2026.104798_b8","doi-asserted-by":"crossref","first-page":"1655","DOI":"10.1109\/JPROC.2019.2921977","article-title":"Deep learning with edge computing: A review","volume":"107","author":"Chen","year":"2019","journal-title":"Proceedings of the IEEE"},{"key":"10.1016\/j.ipm.2026.104798_b9","doi-asserted-by":"crossref","unstructured":"Chen, H., & Vikalo, H. (2024). Mixed-precision quantization for federated learning on resource-constrained heterogeneous devices. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 6138\u20136148).","DOI":"10.1109\/CVPR52733.2024.00587"},{"key":"10.1016\/j.ipm.2026.104798_b10","series-title":"A joint learning and communications framework for federated learning over wireless networks","author":"Chen","year":"2019"},{"key":"10.1016\/j.ipm.2026.104798_b11","series-title":"Energy efficient federated learning over heterogeneous mobile devices via joint design of weight quantization and wireless transmission","author":"Chen","year":"2020"},{"key":"10.1016\/j.ipm.2026.104798_b12","article-title":"Energy-efficient federated learning via quantization for smart grids","author":"Cho","year":"2021","journal-title":"IEEE Transactions on Smart Grid"},{"issue":"4","key":"10.1016\/j.ipm.2026.104798_b13","first-page":"1340","article-title":"Toward energy-efficient federated learning via adaptive quantization","volume":"6","author":"Dang","year":"2022","journal-title":"IEEE Transactions on Green Communications and Networking"},{"key":"10.1016\/j.ipm.2026.104798_b14","doi-asserted-by":"crossref","unstructured":"Ding, X., Zhang, X., Ma, N., Han, J., Ding, G., & Sun, J. (2021). RepVGG: Making VGG-style ConvNets Great Again. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 13733\u201313742).","DOI":"10.1109\/CVPR46437.2021.01352"},{"issue":"6","key":"10.1016\/j.ipm.2026.104798_b15","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104253","article-title":"FedMWAD: Module-wise weighted aggregation federated learning combined with Ditto for patient-independent seizure prediction","volume":"62","author":"Ding","year":"2025","journal-title":"Information Processing & Management"},{"key":"10.1016\/j.ipm.2026.104798_b16","doi-asserted-by":"crossref","DOI":"10.1109\/TMLCN.2025.3550119","article-title":"Randomized quantization for privacy in resource constrained machine learning at-the-edge and federated learning","author":"Feng","year":"2025","journal-title":"IEEE Transactions on Machine Learning in Communications and Networking"},{"key":"10.1016\/j.ipm.2026.104798_b17","series-title":"A survey of quantization methods for efficient neural network inference","author":"Gholami","year":"2021"},{"key":"10.1016\/j.ipm.2026.104798_b18","article-title":"Quantization-based federated learning in user-centric cell-free massive MIMO","author":"Guo","year":"2025","journal-title":"IEEE Transactions on Vehicular Technology"},{"key":"10.1016\/j.ipm.2026.104798_b19","doi-asserted-by":"crossref","first-page":"1004","DOI":"10.1109\/LSP.2024.3383948","article-title":"Training neural networks on remote edge devices for unseen class classification","volume":"31","author":"Hamidi","year":"2024","journal-title":"IEEE Signal Processing Letters"},{"issue":"2","key":"10.1016\/j.ipm.2026.104798_b20","first-page":"550","article-title":"Energy-efficient wireless federated learning with joint quantization and client scheduling","volume":"23","author":"Han","year":"2024","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"10.1016\/j.ipm.2026.104798_b21","doi-asserted-by":"crossref","unstructured":"Hardy, C., Merrer, E. L., & Sericola, B. (2017). Distributed Deep Learning on Edge-Devices: Feasibility via Adaptive Compression. In Proc. IEEE int. symp. netw. comput. appl..","DOI":"10.1109\/NCA.2017.8171350"},{"key":"10.1016\/j.ipm.2026.104798_b22","first-page":"1","article-title":"DAdaQuant: Doubly-adaptive quantization for communication-efficient federated learning","volume":"162","author":"Honig","year":"2022","journal-title":"Proceedings of Machine Learning Research"},{"key":"10.1016\/j.ipm.2026.104798_b23","series-title":"Natural compression for distributed deep learning","author":"Horvath","year":"2019"},{"issue":"6","key":"10.1016\/j.ipm.2026.104798_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.ipm.2025.104230","article-title":"PerFedGT: A personalized federated graph transformer for scale-heterogeneous graph data","volume":"62","author":"Jia","year":"2025","journal-title":"Information Processing & Management"},{"issue":"5","key":"10.1016\/j.ipm.2026.104798_b25","first-page":"2107","article-title":"FedDropQ: Federated learning with gradient dropout and quantization","volume":"34","author":"Jiang","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.ipm.2026.104798_b26","series-title":"Advances and open problems in federated learning","author":"Kairouz","year":"2019"},{"key":"10.1016\/j.ipm.2026.104798_b27","doi-asserted-by":"crossref","DOI":"10.1561\/2200000083","article-title":"Advances and open problems in federated learning","author":"Kairouz","year":"2021","journal-title":"Foundations and Trends in Machine Learning"},{"key":"10.1016\/j.ipm.2026.104798_b28","doi-asserted-by":"crossref","first-page":"68031","DOI":"10.1109\/ACCESS.2023.3284976","article-title":"Decentralized machine learning training: a survey on synchronization, consolidation, and topologies","volume":"11","author":"Khan","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.ipm.2026.104798_b29","doi-asserted-by":"crossref","DOI":"10.1016\/j.iot.2024.101476","article-title":"Consensus-driven hyperparameter optimization for accelerated model convergence in decentralized federated learning","volume":"30","author":"Khan","year":"2025","journal-title":"Internet of Things"},{"issue":"4","key":"10.1016\/j.ipm.2026.104798_b30","doi-asserted-by":"crossref","first-page":"5920","DOI":"10.1109\/JIOT.2023.3308579","article-title":"Hetero-FedIoT: A rule-based interworking architecture for heterogeneous federated IoT networks","volume":"11","author":"Khan","year":"2023","journal-title":"IEEE Internet of Things Journal"},{"key":"10.1016\/j.ipm.2026.104798_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.iot.2023.100890","article-title":"A precision-centric approach to overcoming data imbalance and non-iidness in federated learning","volume":"23","author":"Khan","year":"2023","journal-title":"Internet of Things"},{"issue":"3","key":"10.1016\/j.ipm.2026.104798_b32","first-page":"1080","article-title":"Energy-efficient federated learning on mobile devices with dynamic resource allocation","volume":"20","author":"Kim","year":"2021","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"10.1016\/j.ipm.2026.104798_b33","series-title":"Federated optimization: Distributed machine learning for on-device intelligence","author":"Konecn\u00fd","year":"2016"},{"key":"10.1016\/j.ipm.2026.104798_b34","series-title":"The MNIST database of handwritten digits","author":"LeCun","year":"1998"},{"issue":"2","key":"10.1016\/j.ipm.2026.104798_b35","first-page":"678","article-title":"Adaptive quantization strategies for federated learning on edge devices","volume":"22","author":"Li","year":"2023","journal-title":"IEEE Transactions on Mobile Computing"},{"issue":"9","key":"10.1016\/j.ipm.2026.104798_b36","first-page":"2948","article-title":"Edge-aware quantization in federated learning systems","volume":"25","author":"Li","year":"2021","journal-title":"IEEE Communications Letters"},{"key":"10.1016\/j.ipm.2026.104798_b37","article-title":"Federated learning with quantized communication for health data analytics","author":"Li","year":"2022","journal-title":"IEEE Transactions on Mobile Computing"},{"issue":"3","key":"10.1016\/j.ipm.2026.104798_b38","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 Processing Magazine"},{"key":"10.1016\/j.ipm.2026.104798_b39","first-page":"13169","article-title":"ZeroQ: A novel zero-shot quantization framework","author":"Li","year":"2021","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"10.1016\/j.ipm.2026.104798_b40","unstructured":"Lin, Y., Han, S., Mao, H., Wang, Y., & Dally, W. J. (2018). Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training. In Proc. int. conf. learn. representations."},{"issue":"4","key":"10.1016\/j.ipm.2026.104798_b41","first-page":"2501","article-title":"AdaGQ: Adaptive gradient quantization for communication-efficient federated learning","volume":"21","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Wireless Communications"},{"key":"10.1016\/j.ipm.2026.104798_b42","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., & Zhang, C. (2017). Learning efficient convolutional networks through network slimming. In Proceedings of the IEEE international conference on computer vision (pp. 2736\u20132744).","DOI":"10.1109\/ICCV.2017.298"},{"key":"10.1016\/j.ipm.2026.104798_b43","series-title":"FedZip: Efficient federated learning via compression and sparse updates","author":"Liu","year":"2021"},{"key":"10.1016\/j.ipm.2026.104798_b44","series-title":"Communication-efficient federated learning for heterogeneous edge devices based on adaptive gradient quantization","author":"Liu","year":"2022"},{"key":"10.1016\/j.ipm.2026.104798_b45","article-title":"A unified approach to interpreting model predictions","volume":"30","author":"Lundberg","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"1","key":"10.1016\/j.ipm.2026.104798_b46","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1186\/s13638-025-02471-y","article-title":"Data-oriented optimized nonuniform quantization for CR-enhanced communication efficiency in federated learning","volume":"2025","author":"Luo","year":"2025","journal-title":"EURASIP Journal on Wireless Communications and Networking"},{"key":"10.1016\/j.ipm.2026.104798_b47","first-page":"1187","article-title":"Adaptive quantized gradient communication in federated learning with client dropouts","volume":"71","author":"Mao","year":"2023","journal-title":"IEEE Transactions on Signal Processing"},{"key":"10.1016\/j.ipm.2026.104798_b48","series-title":"ACM\/IEEE ioTDI","article-title":"Edge AI for smart farming: Low-bit quantized inference for crop monitoring","author":"Mohan","year":"2020"},{"key":"10.1016\/j.ipm.2026.104798_b49","doi-asserted-by":"crossref","DOI":"10.1109\/TWC.2024.3432758","article-title":"Communication-efficient federated learning over-the-air with sparse one-bit quantization","author":"Oh","year":"2024","journal-title":"IEEE Transactions on Wireless Communications"},{"issue":"12","key":"10.1016\/j.ipm.2026.104798_b50","first-page":"5531","article-title":"Quantization-aware federated learning on edge devices with limited precision","volume":"32","author":"Park","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"7","key":"10.1016\/j.ipm.2026.104798_b51","first-page":"3212","article-title":"FedAQ: Joint uplink and downlink adaptive quantization for communication-efficient federated learning","volume":"34","author":"Qu","year":"2023","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.1016\/j.ipm.2026.104798_b52","unstructured":"Rao, A., & AuthorT, A. (2020). On-Device Quantization for Communication-Efficient Federated Learning. In Proceedings of the 37th international conference on machine learning ICML, (pp. 1231\u20131240)."},{"key":"10.1016\/j.ipm.2026.104798_b53","series-title":"Proc. int. conf. artif. intell. statist.","first-page":"2021","article-title":"FedPAQ: A communication-efficient federated learning method with periodic averaging and quantization","author":"Reisizadeh","year":"2020"},{"key":"10.1016\/j.ipm.2026.104798_b54","first-page":"1229","article-title":"QFedAvg: Communication-efficient federated learning with quantized averaging","volume":"70","author":"Reisizadeh","year":"2022","journal-title":"IEEE Transactions on Signal Processing"},{"key":"10.1016\/j.ipm.2026.104798_b55","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2024.109464","article-title":"Personalized hierarchical heterogeneous federated learning for thermal comfort prediction in smart buildings","volume":"139","author":"Rizwan","year":"2025","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"10.1016\/j.ipm.2026.104798_b56","series-title":"Predict mortality of ICU patients (PhysioNet)","author":"Safi","year":"2023"},{"issue":"1","key":"10.1016\/j.ipm.2026.104798_b57","first-page":"210","article-title":"Efficient quantization techniques for energy-constrained federated learning","volume":"7","author":"Sun","year":"2022","journal-title":"IEEE Transactions on Sustainable Computing"},{"key":"10.1016\/j.ipm.2026.104798_b58","doi-asserted-by":"crossref","unstructured":"Sun, X., Panda, R., Chen, C.-F. R., Wang, N., Pan, B., Oliva, A., Feris, R., & Saenko, K. (2024). Improved techniques for quantizing deep networks with adaptive bit-widths. In Proceedings of the IEEE\/CVF winter conference on applications of computer vision (pp. 957\u2013967).","DOI":"10.1109\/WACV57701.2024.00100"},{"key":"10.1016\/j.ipm.2026.104798_b59","series-title":"Diabetes prediction dataset","author":"Tariq","year":"2025"},{"issue":"5","key":"10.1016\/j.ipm.2026.104798_b60","first-page":"3456","article-title":"Quantized resource-aware federated learning for edge devices","volume":"9","author":"Wang","year":"2022","journal-title":"IEEE Internet of Things Journal"},{"issue":"3","key":"10.1016\/j.ipm.2026.104798_b61","doi-asserted-by":"crossref","DOI":"10.1049\/cim2.12107","article-title":"Adaptive DFL-based straggler mitigation mechanism for synchronous ring topology in digital twin networks","volume":"6","author":"Waqas Khan","year":"2024","journal-title":"IET Collaborative Intelligent Manufacturing"},{"key":"10.1016\/j.ipm.2026.104798_b62","series-title":"Advances in neural information processing systems","article-title":"Terngrad: Ternary gradients to reduce communication in distributed deep learning","volume":"vol. 30","author":"Wen","year":"2017"},{"key":"10.1016\/j.ipm.2026.104798_b63","series-title":"Fashion-MNIST: a novel image dataset for benchmarking machine learning algorithms","author":"Xiao","year":"2017"},{"issue":"3","key":"10.1016\/j.ipm.2026.104798_b64","first-page":"1234","article-title":"FedLite: Device-aware federated learning with adaptive quantization","volume":"20","author":"Xu","year":"2021","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"10.1016\/j.ipm.2026.104798_b65","article-title":"Lightweight on-device inference for health monitoring using quantized models","author":"Xu","year":"2021","journal-title":"IEEE Journal of Biomedical and Health Informatics"},{"issue":"1","key":"10.1016\/j.ipm.2026.104798_b66","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1109\/TCOMM.2019.2944169","article-title":"Scheduling policies for federated learning in wireless networks","volume":"68","author":"Yang","year":"2019","journal-title":"IEEE Transactions on Communications"},{"key":"10.1016\/j.ipm.2026.104798_b67","unstructured":"Yao, Z., Li, Y., Ding, J., Chen, W., Xie, Y., Tan, M., & Wang, C. (2021). HAWQ-V3: Dyadic Neural Network Quantization. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (pp. 8592\u20138601)."},{"issue":"4","key":"10.1016\/j.ipm.2026.104798_b68","first-page":"1450","article-title":"Dynamic bit-width quantization for efficient federated learning on edge devices","volume":"22","author":"Zhang","year":"2023","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"10.1016\/j.ipm.2026.104798_b69","series-title":"AQUILA: Communication efficient federated learning with adaptive quantization in device selection strategy","author":"Zhao","year":"2023"},{"key":"10.1016\/j.ipm.2026.104798_b70","article-title":"Quantization-aware learning for edge-based smart energy management","author":"Zhou","year":"2023","journal-title":"Energy and AI"},{"issue":"7","key":"10.1016\/j.ipm.2026.104798_b71","first-page":"2764","article-title":"Distributed edge computing with adaptive quantization in federated learning","volume":"32","author":"Zhu","year":"2021","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"}],"container-title":["Information Processing & Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326001895?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0306457326001895?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T01:15:04Z","timestamp":1778548504000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0306457326001895"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":71,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2026,11]]}},"alternative-id":["S0306457326001895"],"URL":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104798","relation":{},"ISSN":["0306-4573"],"issn-type":[{"value":"0306-4573","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A distributed quantization mechanism for lightweight federated learning model in heterogeneous on-device AI networks","name":"articletitle","label":"Article Title"},{"value":"Information Processing & Management","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.ipm.2026.104798","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":"104798"}}