{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:48:28Z","timestamp":1775746108712,"version":"3.50.1"},"reference-count":76,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"name":"Framework of the Horizon Europe Project CENTRIC","award":["101096379"],"award-info":[{"award-number":["101096379"]}]},{"name":"European Union\u2019s NextGenerationEU Instrument","award":["0000DONOTUSETHIS0000.3"],"award-info":[{"award-number":["0000DONOTUSETHIS0000.3"]}]},{"name":"enlarged partnership \u201cTelecommunications of the Future\u201d","award":["PE00000001"],"award-info":[{"award-number":["PE00000001"]}]},{"name":"Program \u201cRESTART\u201d"},{"name":"NSF","award":["CNS 2134567"],"award-info":[{"award-number":["CNS 2134567"]}]},{"name":"NSF","award":["CNS 2003237"],"award-info":[{"award-number":["CNS 2003237"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Networking"],"published-print":{"date-parts":[[2024,4]]},"DOI":"10.1109\/tnet.2023.3323023","type":"journal-article","created":{"date-parts":[[2023,10,16]],"date-time":"2023-10-16T18:37:30Z","timestamp":1697481450000},"page":"1600-1615","source":"Crossref","is-referenced-by-count":5,"title":["Tuning DNN Model Compression to Resource and Data Availability in Cooperative Training"],"prefix":"10.1109","volume":"32","author":[{"given":"Francesco","family":"Malandrino","sequence":"first","affiliation":[{"name":"CNR-IEIIT and CNIT, Turin, Italy"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9990-512X","authenticated-orcid":false,"given":"Giuseppe di","family":"Giacomo","sequence":"additional","affiliation":[{"name":"Politecnico di Torino, Turin, Italy"}]},{"given":"Armin","family":"Karamzade","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of California at Irvine, Irvine, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6920-4189","authenticated-orcid":false,"given":"Marco","family":"Levorato","sequence":"additional","affiliation":[{"name":"Computer Science Department, University of California at Irvine, Irvine, CA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1410-660X","authenticated-orcid":false,"given":"Carla Fabiana","family":"Chiasserini","sequence":"additional","affiliation":[{"name":"CNR-IEIIT and CNIT, Turin, Italy"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229076"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2021.3051378"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/DySPAN53946.2021.9677132"},{"key":"ref4","article-title":"Federated optimization: Distributed optimization beyond the datacenter","author":"Kone\u010dn\u00fd","year":"2015","journal-title":"arXiv:1511.03575"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229027"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3111723"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.011.2100075"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WoWMoM54355.2022.00034"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488723"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412599"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2019.2953106"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636206"},{"key":"ref13","first-page":"1","article-title":"Learning structured sparsity in deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wen"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref15","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref16","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref17","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.softx.2021.100907"},{"key":"ref19","article-title":"RED++: Data-free pruning of deep neural networks via input splitting and output merging","author":"Yvinec","year":"2021","journal-title":"arXiv:2110.01397"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3386263.3407650"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICECS46596.2019.8965157"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3055523"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/gamm.202100008"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2017.8050588"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/JSAIT.2020.2991332"},{"key":"ref26","article-title":"Exact solutions to the nonlinear dynamics of learning in deep linear neural networks","author":"Saxe","year":"2013","journal-title":"arXiv:1312.6120"},{"key":"ref27","first-page":"1","article-title":"Learning and generalization in overparameterized neural networks, going beyond two layers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Allen-Zhu"},{"key":"ref28","article-title":"Deep learning scaling is predictable, empirically","author":"Hestness","year":"2017","journal-title":"arXiv:1712.00409"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2017.8317913"},{"key":"ref30","first-page":"1","article-title":"On the convergence of FedAvg on non-IID data","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/0377-2217(92)90077-M"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1137\/0205006"},{"key":"ref33","first-page":"1","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Krizhevsky"},{"key":"ref34","volume-title":"NVIDIA A100 Datasheet","year":"2021"},{"key":"ref35","volume-title":"NVIDIA RTX A4000 Datasheet","year":"2021"},{"key":"ref36","volume-title":"Broadcom VideoCore VI Technical Details","year":"2021"},{"key":"ref37","first-page":"1273","article-title":"Communication-efficient learning of deep networks from decentralized data","volume-title":"Proc. 20th Int. Conf. Artif. Intell. Statist.","author":"McMahan"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2966745"},{"key":"ref39","article-title":"KnowRU: Knowledge reusing via knowledge distillation in multi-agent reinforcement learning","author":"Gao","year":"2021","journal-title":"arXiv:2103.14891"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2022.3162241"},{"key":"ref41","article-title":"Solvable model for inheriting the regularization through knowledge distillation","author":"Saglietti","year":"2020","journal-title":"arXiv:2012.00194"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICInfA.2018.8812321"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10733"},{"key":"ref44","first-page":"1","article-title":"Collaborative inter-agent knowledge distillation for reinforcement learning","volume-title":"Proc. ICLR","author":"Hong"},{"key":"ref45","first-page":"1","article-title":"The lottery ticket hypothesis: Finding sparse, trainable neural networks","volume-title":"Proc. ICLR","author":"Frankle"},{"key":"ref46","first-page":"9356","article-title":"DropNet: Reducing neural network complexity via iterative pruning","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_12"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3373376.3378534"},{"key":"ref49","article-title":"Prune your model before distill it","author":"Park","year":"2021","journal-title":"arXiv:2109.14960"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00356"},{"key":"ref51","article-title":"Generalization of teacher\u2013student network and CNN pruning","author":"Menzies","year":"2018"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.12720\/jait.13.3.295-300"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3039714"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2021.3090331"},{"key":"ref56","article-title":"AdaSplit: Adaptive trade-offs for resource-constrained distributed deep learning","author":"Chopra","year":"2021","journal-title":"arXiv:2112.01637"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/icccn58024.2023.10230190"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3527155"},{"key":"ref59","first-page":"15070","article-title":"Personalized federated learning through local memorization","volume-title":"Proc. ICML","author":"Marfoq"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2019.2904348"},{"key":"ref61","article-title":"Resource-efficient federated learning","author":"Abdelmoniem","year":"2021","journal-title":"arXiv:2111.01108"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2001016"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2021.3084406"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA51294.2020.00185"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3477114.3488760"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2022.3144994"},{"key":"ref67","first-page":"1","article-title":"Reading digits in natural images with unsupervised feature learning","volume-title":"Proc. NIPS","author":"Netzer"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2022.3222640"},{"key":"ref69","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746093"},{"key":"ref71","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Coates"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737602"},{"key":"ref73","article-title":"Dynamic network-assisted D2D-aided coded distributed learning","author":"Zeulin","year":"2021","journal-title":"arXiv:2111.14789"},{"key":"ref74","first-page":"1","article-title":"How much over-parameterization is sufficient to learn deep ReLU networks?","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref75","first-page":"5142","article-title":"Towards understanding knowledge distillation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Phuong"},{"key":"ref76","article-title":"Analysis of knowledge transfer in kernel regime","author":"Rahbar","year":"2020","journal-title":"arXiv:2003.13438"}],"container-title":["IEEE\/ACM Transactions on Networking"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/90\/10505042\/10286454-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/90\/10505042\/10286454.pdf?arnumber=10286454","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,19]],"date-time":"2024-04-19T17:40:15Z","timestamp":1713548415000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10286454\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4]]},"references-count":76,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tnet.2023.3323023","relation":{},"ISSN":["1063-6692","1558-2566"],"issn-type":[{"value":"1063-6692","type":"print"},{"value":"1558-2566","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4]]}}}