{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:47:29Z","timestamp":1776750449421,"version":"3.51.2"},"reference-count":236,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada (NSERC) Alliance-Alberta Innovates Program","doi-asserted-by":"publisher","award":["RGPIN-2021-04050"],"award-info":[{"award-number":["RGPIN-2021-04050"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada (NSERC) Alliance-Alberta Innovates Program","doi-asserted-by":"publisher","award":["RGPIN-2021-03565"],"award-info":[{"award-number":["RGPIN-2021-03565"]}],"id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Commun. Surv. Tutorials"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/comst.2026.3682638","type":"journal-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T19:49:45Z","timestamp":1775764185000},"page":"5747-5791","source":"Crossref","is-referenced-by-count":0,"title":["Model Compression for Sustainable AI in xG Wireless Networks: Recent Advances, Challenges, and Future Directions"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2786-1164","authenticated-orcid":false,"given":"Fazal Muhammad Ali","family":"Khan","sequence":"first","affiliation":[{"name":"School of Computing, University of the Fraser Valley, Abbotsford, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8623-346X","authenticated-orcid":false,"given":"Mohammad","family":"Hallaq","sequence":"additional","affiliation":[{"name":"Department of Electrical and Software Engineering, University of Calgary, Calgary, AB, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hatem","family":"Abou-Zeid","sequence":"additional","affiliation":[{"name":"Department of Electrical and Software Engineering, University of Calgary, Calgary, AB, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2450-6510","authenticated-orcid":false,"given":"Omar","family":"Erak","sequence":"additional","affiliation":[{"name":"KU 6G Research Center, Khalifa University, Abu Dhabi, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1787-7100","authenticated-orcid":false,"given":"Omer","family":"Waqar","sequence":"additional","affiliation":[{"name":"School of Computing, University of the Fraser Valley, Abbotsford, BC, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8572-7377","authenticated-orcid":false,"given":"Syed Ali","family":"Hassan","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science (SEECS), National University of Sciences and Technology (NUST), Islamabad, Pakistan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1531-5916","authenticated-orcid":false,"given":"Omar","family":"Alhussein","sequence":"additional","affiliation":[{"name":"KU 6G Research Center, Khalifa University, Abu Dhabi, United Arab Emirates"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5932-6887","authenticated-orcid":false,"given":"Ekram","family":"Hossain","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Manitoba, Winnipeg, MB, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"A Vision of 6G URLLC","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.1900411"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/IOTM.001.2300181"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2019.1900271"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2018.2818160"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2017.2758370"},{"key":"ref7","first-page":"743","article-title":"Uniform sparsity in deep neural networks","volume-title":"Proc. Mach. Learn. Syst.","volume":"5","author":"Muralidharan"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1561\/2200000083"},{"key":"ref9","article-title":"DeepMIMO: A generic deep learning dataset for millimeter wave and massive MIMO applications","author":"Alkhateeb","year":"2019","journal-title":"arXiv:1902.06435"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-0676-1"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.2976475"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/computers12030060"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2022.3226481"},{"key":"ref14","article-title":"A survey of model compression and acceleration for deep neural networks","author":"Cheng","year":"2017","journal-title":"arXiv:1710.09282"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1201\/9781003162810-13"},{"key":"ref16","article-title":"What is the state of neural network pruning?","author":"Blalock","year":"2020","journal-title":"arXiv:2003.03033"},{"issue":"241","key":"ref17","first-page":"1","article-title":"Sparsity in deep learning: Pruning and growth for efficient inference and training in neural networks","volume":"22","author":"Hoefler","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2761740"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.07.045"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3365349"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3583683"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2022.3217777"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNSE.2025.3639401"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3724420"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2025.1518965"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3560359"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2024.3437730"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2020.3024783"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2025.3552370"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3300664"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2025.3535554"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3345796"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2024.3382973"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3088875"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3199689"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2023.3315374"},{"key":"ref38","first-page":"598","article-title":"Optimal brain damage","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"2","author":"LeCun"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2478\/s13537-013-0109-x"},{"key":"ref40","first-page":"1","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and Huffman coding","volume-title":"Proc. 4th Int. Conf. Learn. Represent. (ICLR)","author":"Han"},{"key":"ref41","first-page":"8635","article-title":"Sparse double descent: Where network pruning aggravates overfitting","volume-title":"Proc. 39th Int. Conf. Mach. Learn. (ICML)","volume":"162","author":"He"},{"key":"ref42","first-page":"1","article-title":"Pruning filters for efficient convnets","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Li"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3334614"},{"key":"ref44","first-page":"1","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Han"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/DAC18072.2020.9218701"},{"key":"ref46","article-title":"UCP: Uniform channel pruning for deep convolutional neural networks compression and acceleration","author":"Chang","year":"2020","journal-title":"arXiv:2010.01251"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/s21030880"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3447085"},{"key":"ref49","first-page":"1","article-title":"Dynamic network surgery for efficient DNNs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Guo"},{"key":"ref50","article-title":"To prune, or not to prune: Exploring the efficacy of pruning for model compression","author":"Zhu","year":"2017","journal-title":"arXiv:1710.01878"},{"key":"ref51","first-page":"1","article-title":"Layer-adaptive sparsity for the magnitude-based pruning","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lee"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC51575.2020.9345039"},{"key":"ref53","first-page":"1","article-title":"Pruning convolutional neural networks for resource efficient inference","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Molchanov"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-04353-y"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/IOTM.001.2400032"},{"key":"ref56","first-page":"20378","article-title":"Movement pruning: Adaptive sparsity by fine-tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sanh"},{"key":"ref57","article-title":"SparseGPT: Massive language models can be accurately pruned in one-shot","author":"Frantar","year":"2023","journal-title":"arXiv:2301.00774"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.574"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0323"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-41964-6_40"},{"key":"ref62","article-title":"Quantization-guided training for compact TinyML models","author":"Ghamari","year":"2021","journal-title":"arXiv:2103.06231"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3373460"},{"key":"ref64","article-title":"BinaryConnect: Training deep neural networks with binary weights during propagations","author":"Courbariaux","year":"2015","journal-title":"arXiv:1511.00363"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3623402"},{"key":"ref66","article-title":"A white paper on neural network quantization","author":"Nagel","year":"2021","journal-title":"arXiv:2106.08295"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00452"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650109"},{"key":"ref69","first-page":"2849","article-title":"Fixed-point quantization of deep convolutional networks","volume-title":"Proc. 33rd Int. Conf. Mach. Learn. (ICML)","author":"Lin"},{"key":"ref70","article-title":"Mixed precision quantization of ConvNets via differentiable neural architecture search","author":"Wu","year":"2018","journal-title":"arXiv:1812.00090"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00038"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.12.035"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00773"},{"key":"ref74","article-title":"Ternary and binary quantization for improved classification","author":"Lu","year":"2022","journal-title":"arXiv:2203.16798"},{"key":"ref75","article-title":"Ternary quantization: A survey","author":"Liu","year":"2023","journal-title":"arXiv:2303.01505"},{"key":"ref76","article-title":"Low-bit model quantization for deep neural networks: A survey","author":"Liu","year":"2025","journal-title":"arXiv:2505.05530"},{"key":"ref77","article-title":"A survey of low-bit large language models: Basics, systems, and algorithms","author":"Gong","year":"2024","journal-title":"arXiv:2409.16694"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1503.02531"},{"key":"ref79","first-page":"14110","article-title":"Slow learning and fast inference: Efficient graph similarity computation via knowledge distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Qin"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2264"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00145"},{"key":"ref83","first-page":"1","article-title":"FitNets: Hints for thin deep nets","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Romero"},{"key":"ref84","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zagoruyko"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-056-4_050"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098135"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM51629.2021.00069"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.309"},{"key":"ref89","article-title":"A comprehensive survey on knowledge distillation","author":"Mansourian","year":"2025","journal-title":"arXiv:2503.12067"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3476068"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3699518"},{"key":"ref92","article-title":"Federated distillation: A survey","author":"Li","year":"2024","journal-title":"arXiv:2404.08564"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-05318-5_3"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1611.01578"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"ref96","article-title":"Progressive neural networks","author":"Rusu","year":"2016","journal-title":"arXiv:1606.04671"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3469116.3470012"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.3390\/info12100431"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.3233\/JIFS-171947"},{"key":"ref100","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013","journal-title":"arXiv:1308.3432"},{"key":"ref101","article-title":"Soft weight-sharing for neural network compression","author":"Ullrich","year":"2017","journal-title":"arXiv:1702.04008"},{"key":"ref102","first-page":"2285","article-title":"Compressing neural networks with the hashing trick","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2690524"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1137\/07070111X"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.88"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2913945"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2020.2971001"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1007\/s11276-024-03659-8"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3431236"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2025-Fall65116.2025.11310312"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1016\/j.phycom.2022.101793"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.3390\/electronics11193018"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2020.2968030"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM46510.2021.9685815"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2021.3089178"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2023.3306391"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM54140.2023.10436917"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/ICC45041.2023.10279462"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2025.3591169"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2021.3119945"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2023.3282227"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM53939.2023.10229094"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3339824"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/TCOMM.2024.3377724"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2023.3258749"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2021-Fall52928.2021.9625047"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/LCOMM.2021.3076504"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3103120"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/WOCC53213.2021.9602863"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2021.3100493"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3418907"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC59590.2023.10507483"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2021.3064963"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3183596"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/GLOBECOM42002.2020.9322109"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3190435"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2887308"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3351053"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.001.1900239"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2023.3285790"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1109\/SOCC56010.2022.9908091"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2019.2956146"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2020.3004386"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2024.3369748"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3325735"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/LWC.2025.3543965"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2021.3051490"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2021.3129466"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2023.3347665"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2021.3064466"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.3390\/electronics12071694"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1109\/TCCN.2022.3149092"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2024.3396798"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3078782"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS57453.2023.10226112"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/s12083-023-01564-z"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1049\/cmu2.12129"},{"key":"ref158","first-page":"1","article-title":"Low complexity channel estimation with neural network solutions","volume-title":"Proc. 25th Int. ITG Workshop Smart Antennas","author":"Luan"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.23919\/JCIN.2022.9906943"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2022.3180794"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2022.3163786"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2022.3207269"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2022.3220784"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/LES.2021.3094965"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/ICC52391.2025.11161984"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/ISITIA59021.2023.10220996"},{"key":"ref167","first-page":"1","article-title":"NAS-FL: Fingerprint localization method based on automatically designed neural network architecture","volume-title":"Proc. Work-in-Progress Papers, 14th Int. Conf. Indoor Positioning Indoor Navig. (IPIN-WiP)","author":"Liu"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1155\/2015\/403242"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1109\/ISTEL.2008.4651329"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-29429-w"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26505"},{"key":"ref172","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638949"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1038\/44565"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_14"},{"key":"ref176","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/OJCOMS.2025.3600616"},{"key":"ref179","article-title":"IQFM\u2014A wireless foundational model for I\/Q streams in AI-native 6G","author":"Mashaal","year":"2025","journal-title":"arXiv:2506.06718"},{"key":"ref180","article-title":"WirelessJEPA: A multi-antenna foundation model using spatio-temporal wireless latent predictions","author":"Chu","year":"2026","journal-title":"arXiv:2601.20190"},{"key":"ref181","article-title":"Lightweight foundation model for wireless time series downstream tasks on edge devices","author":"Cheraghinia","year":"2025","journal-title":"arXiv:2511.14895"},{"key":"ref182","article-title":"A survey on large language model acceleration based on KV cache management","author":"Li","year":"2024","journal-title":"arXiv:2412.19442"},{"key":"ref183","first-page":"1","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Shazeer"},{"issue":"120","key":"ref184","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref185","first-page":"1","article-title":"GShard: Scaling giant models with conditional computation and automatic sharding","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lepikhin"},{"key":"ref186","article-title":"ZSMerge: Zero-shot KV cache compression for memory-efficient long-context LLMs","author":"Liu","year":"2025","journal-title":"arXiv:2503.10714"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1506"},{"key":"ref188","first-page":"32332","article-title":"KIVI: A tuning-free asymmetric 2-bit quantization for KV cache","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","volume":"235","author":"Liu"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0040"},{"key":"ref190","first-page":"19274","article-title":"Fast inference from transformers via speculative decoding","volume-title":"Proc. 40th Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Leviathan"},{"key":"ref191","article-title":"Accelerating large language model decoding with speculative sampling","author":"Chen","year":"2023","journal-title":"arXiv:2302.01318"},{"key":"ref192","first-page":"28935","article-title":"EAGLE: Speculative sampling requires rethinking feature uncertainty","volume-title":"Proc. 41st Int. Conf. Mach. Learn. (ICML)","volume":"235","author":"Li"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2025.111387"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/IPIN.2014.7275492"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/TVT.2018.2868698"},{"key":"ref196","article-title":"CRAWDAD OWL-InIT","author":"Schmidt","year":"2022"},{"key":"ref197","volume-title":"DeepSig Dataset: RadioML 2016.10A","year":"2016"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1145\/3191755"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/MWC.2012.6393523"},{"key":"ref200","volume-title":"BLE RSSI Dataset for Indoor Localization and Navigation","author":"Mohammadi","year":"2018"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2023.3342735"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1109\/MLSP.2019.8918866"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3401046"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1155\/2019\/5629572"},{"key":"ref205","first-page":"5533","article-title":"Inducing and exploiting activation sparsity for fast inference on deep neural networks","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"119","author":"Kurtz"},{"key":"ref206","volume-title":"OpenVINO Toolkit Documentation","year":"2025"},{"key":"ref207","article-title":"Neural network compression framework for fast model inference","author":"Kozlov","year":"2020","journal-title":"arXiv:2002.08679"},{"key":"ref208","volume-title":"Intel\u00ae Neural Compressor","author":"Tian","year":"2022"},{"key":"ref209","volume-title":"NVIDIA TensorRT Documentation","year":"2025"},{"key":"ref210","volume-title":"AIMET: AI Model Efficiency Toolkit","year":"2025"},{"key":"ref211","volume-title":"TensorFlow Model Optimization Toolkit","year":"2025"},{"key":"ref212","volume-title":"LiteRT: Lightweight Runtime for Edge AI","year":"2025"},{"key":"ref213","volume-title":"Torchao: PyTorch Native Quantization and Sparsity for Training and Inference","year":"2024"},{"key":"ref214","volume-title":"PyTorch Executorch: Lightweight Runtime for Edge AI","year":"2025"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01544"},{"key":"ref216","article-title":"Xilinx\/brevitas","author":"Pappalardo","year":"2023"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-76423-4_3"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.3390\/a15120441"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.1145\/3242897"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2303\/1\/012047"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.3390\/fi15060219"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1007\/s00500-021-05891-2"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/IWCMC65282.2025.11059726"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122666"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1145\/3690624.3709241"},{"key":"ref226","article-title":"Characteristic performance study on solving oscillator ODEs via soft-constrained physics-informed neural network with small data","author":"Lu","year":"2024","journal-title":"arXiv:2408. 11077"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-025-88378-6"},{"key":"ref228","doi-asserted-by":"publisher","DOI":"10.3390\/electronics13152963"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/ojcoms.2026.3676928"},{"key":"ref230","article-title":"GAWM: Global-aware world model for multi-agent reinforcement learning","author":"Shi","year":"2025","journal-title":"arXiv:2501.10116"},{"key":"ref231","doi-asserted-by":"publisher","DOI":"10.1515\/nanoph-2017-0118"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.3390\/jmse13061103"},{"key":"ref233","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2021.3124855"},{"key":"ref234","doi-asserted-by":"publisher","DOI":"10.1109\/JCN.2020.000016"},{"key":"ref235","first-page":"19655","article-title":"Hydra: Pruning adversarially robust neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sehwag"},{"key":"ref236","doi-asserted-by":"publisher","DOI":"10.1145\/3453688.3461755"}],"container-title":["IEEE Communications Surveys & Tutorials"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9739\/11321210\/11478444.pdf?arnumber=11478444","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,21]],"date-time":"2026-04-21T05:20:04Z","timestamp":1776748804000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11478444\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":236,"URL":"https:\/\/doi.org\/10.1109\/comst.2026.3682638","relation":{},"ISSN":["1553-877X","2373-745X"],"issn-type":[{"value":"1553-877X","type":"electronic"},{"value":"2373-745X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}