{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:11:04Z","timestamp":1771953064078,"version":"3.50.1"},"reference-count":199,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T00:00:00Z","timestamp":1748995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFA1011704"],"award-info":[{"award-number":["2023YFA1011704"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFA1011704"],"award-info":[{"award-number":["2023YFA1011704"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFA1011704"],"award-info":[{"award-number":["2023YFA1011704"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Supercomput"],"DOI":"10.1007\/s11227-025-07451-z","type":"journal-article","created":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T15:07:46Z","timestamp":1749049666000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Balancing communication overhead and accuracy in compression integration: a survey"],"prefix":"10.1007","volume":"81","author":[{"given":"Aiqiang","family":"Yang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jie","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyao","family":"Mo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Keqin","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,4]]},"reference":[{"key":"7451_CR1","doi-asserted-by":"crossref","unstructured":"Li M, Andersen DG, Smola A, Yu K (2014) Communication efficient distributed machine learning with the parameter server. Advances in Neural Information Processing Systems 27","DOI":"10.1145\/2640087.2644155"},{"key":"7451_CR2","unstructured":"Zinkevich M, Weimer M, Li L, Smola A (2010) Parallelized stochastic gradient descent. Advances in Neural Information Processing Systems 23"},{"key":"7451_CR3","unstructured":"Lian X, Zhang C, Zhang H, Hsieh C-J, Zhang W, Liu, J (2017) Can decentralized algorithms outperform centralized algorithms? a case study for decentralized parallel stochastic gradient descent. Advances in Neural Information Processing Systems 30"},{"key":"7451_CR4","doi-asserted-by":"crossref","unstructured":"Seide F, Fu H, Droppo J, Li G, Yu D (2014) 1-bit stochastic gradient descent and its application to data-parallel distributed training of speech dnns. In: Fifteenth Annual Conference of the International Speech Communication Association","DOI":"10.21437\/Interspeech.2014-274"},{"key":"7451_CR5","unstructured":"Achiam J, Adler S, Agarwal S, Ahmad L, Akkaya I, Aleman FL, Almeida D, Altenschmidt J, Altman S, Anadkat S et al (2023) Gpt-4 technical report. arXiv preprint arXiv:2303.08774"},{"issue":"4","key":"7451_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3320060","volume":"52","author":"T Ben-Nun","year":"2019","unstructured":"Ben-Nun T, Hoefler T (2019) Demystifying parallel and distributed deep learning: an in-depth concurrency analysis. ACM Comput Surv (CSUR) 52(4):1\u201343","journal-title":"ACM Comput Surv (CSUR)"},{"key":"7451_CR7","unstructured":"Bertsekas DP, Tsitsiklis JN (2003) Parallel and distributed computation: numerical methods (2nd ed.). Athena Scientific"},{"issue":"6","key":"7451_CR8","doi-asserted-by":"publisher","first-page":"1031","DOI":"10.1109\/JPROC.2010.2044470","volume":"98","author":"J Wright","year":"2010","unstructured":"Wright J, Ma Y, Mairal J, Sapiro G, Huang TS, Yan S (2010) Sparse representation for computer vision and pattern recognition. Proc IEEE 98(6):1031\u20131044","journal-title":"Proc IEEE"},{"key":"7451_CR9","unstructured":"Yaguchi A, Suzuki T, Nitta S, Sakata Y, Tanizawa A (2019) Scalable deep neural networks via low-rank matrix factorization. arXiv preprint arXiv:1910.13141"},{"key":"7451_CR10","unstructured":"Li H, Kadav A, Durdanovic I, Samet H, Graf HP (2016) Pruning filters for efficient convnets. arXiv preprint arXiv:1608.08710"},{"key":"7451_CR11","unstructured":"Wangni J, Wang J, Liu J, Zhang T (2018) Gradient sparsification for communication-efficient distributed optimization. Advances in Neural Information Processing Systems 31"},{"key":"7451_CR12","doi-asserted-by":"crossref","unstructured":"Li S, Hoefler T (2022) Near-optimal sparse allreduce for distributed deep learning. In: Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming, pp 135\u2013149","DOI":"10.1145\/3503221.3508399"},{"issue":"12","key":"7451_CR13","doi-asserted-by":"publisher","first-page":"7330","DOI":"10.1109\/TNNLS.2021.3084806","volume":"33","author":"L Abrahamyan","year":"2021","unstructured":"Abrahamyan L, Chen Y, Bekoulis G, Deligiannis N (2021) Learned gradient compression for distributed deep learning. IEEE Trans Neural Netw Learn Syst 33(12):7330\u20137344","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"7451_CR14","first-page":"18955","volume":"35","author":"X Huang","year":"2022","unstructured":"Huang X, Chen Y, Yin W, Yuan K (2022) Lower bounds and nearly optimal algorithms in distributed learning with communication compression. Adv Neural Inf Process Syst 35:18955\u201318969","journal-title":"Adv Neural Inf Process Syst"},{"key":"7451_CR15","doi-asserted-by":"crossref","unstructured":"Luzuriaga JE, Perez M, Boronat P, Cano JC, Calafate C, Manzoni P (2015) A comparative evaluation of amqp and mqtt protocols over unstable and mobile networks. In: 2015 12th Annual IEEE Consumer Communications and Networking Conference (CCNC). IEEE, pp 931\u2013936","DOI":"10.1109\/CCNC.2015.7158101"},{"issue":"5","key":"7451_CR16","doi-asserted-by":"publisher","first-page":"871","DOI":"10.1109\/JSAC.1987.1146600","volume":"5","author":"J Winters","year":"1987","unstructured":"Winters J (1987) On the capacity of radio communication systems with diversity in a Rayleigh fading environment. IEEE J Sel Areas Commun 5(5):871\u2013878","journal-title":"IEEE J Sel Areas Commun"},{"issue":"3","key":"7451_CR17","doi-asserted-by":"publisher","first-page":"230","DOI":"10.1049\/trit.2020.0082","volume":"5","author":"J Jiang","year":"2020","unstructured":"Jiang J, Hu L (2020) Decentralised federated learning with adaptive partial gradient aggregation. CAAI Trans Intell Technol 5(3):230\u2013236","journal-title":"CAAI Trans Intell Technol"},{"key":"7451_CR18","unstructured":"Deng Y, Kamani MM, Mahdavi M (2020) Adaptive personalized federated learning. arXiv preprint arXiv:2003.13461"},{"key":"7451_CR19","unstructured":"Jiang Y, Zhu Y, Lan C, Yi B, Cui Y, Guo C (2020) A unified architecture for accelerating distributed $$\\{$$DNN$$\\}$$ training in heterogeneous $$\\{$$GPU\/CPU$$\\}$$ clusters. In: 14th USENIX Symposium on Operating Systems Design and Implementation (OSDI 20), pp 463\u2013479"},{"key":"7451_CR20","doi-asserted-by":"publisher","first-page":"102927","DOI":"10.1016\/j.sysarc.2023.102927","volume":"142","author":"Z Wang","year":"2023","unstructured":"Wang Z, Wen M, Xu Y, Zhou Y, Wang JH, Zhang L (2023) Communication compression techniques in distributed deep learning: a survey. J Syst Architect 142:102927","journal-title":"J Syst Architect"},{"key":"7451_CR21","unstructured":"Hanna OA, Ezzeldin YH, Fragouli C, Diggavi S (2020) Quantizing data for distributed learning. arXiv preprint arXiv:2012.07913"},{"issue":"3","key":"7451_CR22","first-page":"345","volume":"14","author":"H-S Liu","year":"2011","unstructured":"Liu H-S, Chuang C-C, Lin C-C, Chang R-I, Wang C-H, Hsieh C-C (2011) Data compression for energy efficient communication on ubiquitous sensor network. Tamkang J Sci Eng 14(3):345\u2013354","journal-title":"Tamkang J Sci Eng"},{"key":"7451_CR23","unstructured":"Li H, Xu Y, Chen J, Dwivedula R, Wu W, He K, Akella A, Kim D (2024) Accelerating distributed deep learning using lossless homomorphic compression. arXiv preprint arXiv:2402.07529"},{"key":"7451_CR24","unstructured":"Makarenko M, Gasanov E, Islamov R, Sadiev A, Richt\u00e1rik P (2022) Adaptive compression for communication-efficient distributed training. arXiv preprint arXiv:2211.00188"},{"key":"7451_CR25","unstructured":"Wang Z, Wu XC, Xu Z, Ng TE (2023) Cupcake: a compression optimizer for scalable communication-efficient distributed training. In: Proceedings of the Sixth Conference on Machine Learning and Systems (MLSys\u2019 23). Proceedings of the Sixth Conference on Machine Learning and Systems (MLSys\u2019 23)"},{"key":"7451_CR26","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2023.104719","volume":"180","author":"C-C Chen","year":"2023","unstructured":"Chen C-C, Chou Y-M, Chou J (2023) Phy: A performance-driven hybrid communication compression method for distributed training. J Parallel Distrib Comput 180:104719","journal-title":"J Parallel Distrib Comput"},{"issue":"9","key":"7451_CR27","doi-asserted-by":"publisher","first-page":"2678","DOI":"10.1109\/JSAC.2022.3192050","volume":"40","author":"G Yan","year":"2022","unstructured":"Yan G, Li T, Huang S-L, Lan T, Song L (2022) Ac-sgd: Adaptively compressed sgd for communication-efficient distributed learning. IEEE J Sel Areas Commun 40(9):2678\u20132693","journal-title":"IEEE J Sel Areas Commun"},{"key":"7451_CR28","unstructured":"Stich SU (2018) Local sgd converges fast and communicates little. arXiv preprint arXiv:1805.09767"},{"key":"7451_CR29","unstructured":"Tsuzuku Y, Imachi H, Akiba T (2018) Variance-based gradient compression for efficient distributed deep learning. arXiv preprint arXiv:1802.06058"},{"key":"7451_CR30","first-page":"652","volume":"4","author":"S Agarwal","year":"2022","unstructured":"Agarwal S, Wang H, Venkataraman S, Papailiopoulos D (2022) On the utility of gradient compression in distributed training systems. Proc Mach Learn Syst 4:652\u2013672","journal-title":"Proc Mach Learn Syst"},{"key":"7451_CR31","unstructured":"Khirirat S, Feyzmahdavian HR, Johansson M (2018) Distributed learning with compressed gradients. arXiv preprint arXiv:1806.06573"},{"key":"7451_CR32","unstructured":"Karimireddy SP, Rebjock Q, Stich S, Jaggi M (2019) Error feedback fixes signsgd and other gradient compression schemes. In: International Conference on Machine Learning. PMLR, pp 3252\u20133261"},{"key":"7451_CR33","unstructured":"Xu H, Ho C-Y, Abdelmoniem AM, Dutta A, Bergou EH, Karatsenidis K, Canini M, Kalnis P (2020) Compressed communication for distributed deep learning: survey and quantitative evaluation. Technical report"},{"key":"7451_CR34","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"7451_CR35","unstructured":"Konecn\u1ef3 J, McMahan HB, Yu FX, Richt\u00e1rik P, Suresh AT, Bacon D (2016) Federated learning: strategies for improving communication efficiency. arXiv preprint arXiv:1610.05492"},{"key":"7451_CR36","first-page":"53","volume":"1","author":"H Lim","year":"2019","unstructured":"Lim H, Andersen DG, Kaminsky M (2019) 3lc: Lightweight and effective traffic compression for distributed machine learning. Proc Mach Learn Syst 1:53\u201364","journal-title":"Proc Mach Learn Syst"},{"key":"7451_CR37","unstructured":"Lin Y, Han S, Mao H, Wang Y, Dally W (2017) Deep gradient compression: reducing the communication bandwidth for distributed training. arXiv preprint arXiv:1712.01887"},{"issue":"1","key":"7451_CR38","doi-asserted-by":"publisher","first-page":"11658","DOI":"10.1038\/s41598-023-38916-x","volume":"13","author":"Y Ren","year":"2023","unstructured":"Ren Y, Cao Y, Ye C, Cheng X (2023) Two-layer accumulated quantized compression for communication-efficient federated learning: Tlaqc. Sci Rep 13(1):11658","journal-title":"Sci Rep"},{"key":"7451_CR39","unstructured":"Tang H, Yu C, Lian X, Zhang T, Liu J (2019) Doublesqueeze: parallel stochastic gradient descent with double-pass error-compensated compression. In: International Conference on Machine Learning. PMLR, pp 6155\u20136165"},{"key":"7451_CR40","first-page":"13551","volume":"33","author":"C-Y Chen","year":"2020","unstructured":"Chen C-Y, Ni J, Lu S, Cui X, Chen P-Y, Sun X, Wang N, Venkataramani S, Srinivasan VV, Zhang W et al (2020) Scalecom: Scalable sparsified gradient compression for communication-efficient distributed training. Adv Neural Inf Process Syst 33:13551\u201313563","journal-title":"Adv Neural Inf Process Syst"},{"key":"7451_CR41","doi-asserted-by":"crossref","unstructured":"Str\u00f6m N (2015) Scalable distributed dnn training using commodity gpu cloud computing. In Proceedings of the 16th Annual Conference of the International Speech Communication Association (INTERSPEECH 2015) (pp. 1488\u20131492). ISCA","DOI":"10.21437\/Interspeech.2015-354"},{"key":"7451_CR42","unstructured":"Wen W, Xu C, Yan F, Wu C, Wang Y, Chen Y, Li HT (2017) Ternary gradients to reduce communication in distributed deep learning. arXiv preprint arXiv:1705.07878"},{"key":"7451_CR43","doi-asserted-by":"crossref","unstructured":"Yu R, Li A, Chen C-F, Lai J-H, Morariu VI, Han X, Gao M, Lin C-Y, Davis LS (2018) Nisp: pruning networks using neuron importance score propagation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9194\u20139203","DOI":"10.1109\/CVPR.2018.00958"},{"issue":"7553","key":"7451_CR44","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun Y, Bengio Y, Hinton G (2015) Deep learning. Nature 521(7553):436\u2013444","journal-title":"Nature"},{"issue":"241","key":"7451_CR45","first-page":"1","volume":"22","author":"T Hoefler","year":"2021","unstructured":"Hoefler T, Alistarh D, Ben-Nun T, Dryden N, Peste A (2021) Sparsity in deep learning: pruning and growth for efficient inference and training in neural networks. J Mach Learn Res 22(241):1\u2013124","journal-title":"J Mach Learn Res"},{"key":"7451_CR46","doi-asserted-by":"crossref","unstructured":"Luo J-H, Wu J (2020) Neural network pruning with residual-connections and limited-data. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 1458\u20131467","DOI":"10.1109\/CVPR42600.2020.00153"},{"issue":"6","key":"7451_CR47","first-page":"10003","volume":"45","author":"Z Weng","year":"2023","unstructured":"Weng Z, Liu K, Zheng Z (2023) Cattle face detection method based on channel pruning yolov5 network and mobile deployment. J Intell Fuzzy Syst 45(6):10003\u201310020","journal-title":"J Intell Fuzzy Syst"},{"key":"7451_CR48","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2022.101429","volume":"77","author":"H Sajjad","year":"2023","unstructured":"Sajjad H, Dalvi F, Durrani N, Nakov P (2023) On the effect of dropping layers of pre-trained transformer models. Comput Speech Lang 77:101429","journal-title":"Comput Speech Lang"},{"key":"7451_CR49","unstructured":"Wang G, Qin H, Jacobs SA, Holmes C, Rajbhandari S, Ruwase O, Yan F, Yang L, He Y (2023) Zero++: extremely efficient collective communication for giant model training. arXiv preprint arXiv:2306.10209"},{"key":"7451_CR50","unstructured":"Dean J, Corrado G, Monga R, Chen K, Devin M, Mao M, Ranzato M, Senior A, Tucker P, Yang K et al (2012) Large scale distributed deep networks. Advances in Neural Information Processing Systems 25"},{"key":"7451_CR51","unstructured":"Recht B, Re C, Wright S, Niu F (2011) Hogwild!: A lock-free approach to parallelizing stochastic gradient descent. Advances in Neural Information Processing Systems 24"},{"key":"7451_CR52","unstructured":"Lian X, Zhang W, Zhang C, Liu J (2018) Asynchronous decentralized parallel stochastic gradient descent. In: International Conference on Machine Learning. PMLR, pp 3043\u20133052"},{"key":"7451_CR53","unstructured":"Stich SU, Cordonnier J-B, Jaggi M (2018) Sparsified sgd with memory. Advances in Neural Information Processing Systems 31"},{"key":"7451_CR54","unstructured":"Wu J, Huang W, Huang J, Zhang T (2018) Error compensated quantized sgd and its applications to large-scale distributed optimization. In: International Conference on Machine Learning. PMLR, pp 5325\u20135333"},{"key":"7451_CR55","unstructured":"Alistarh D, Grubic D, Li J, Tomioka R, Vojnovic M (2017) QSGD: communication-efficient sgd via gradient quantization and encoding. Advances in Neural Information Processing Systems 30"},{"issue":"114","key":"7451_CR56","first-page":"1","volume":"22","author":"A Ramezani-Kebrya","year":"2021","unstructured":"Ramezani-Kebrya A, Faghri F, Markov I, Aksenov V, Alistarh D, Roy DM (2021) Nuqsgd: Provably communication-efficient data-parallel sgd via nonuniform quantization. J Mach Learn Res 22(114):1\u201343","journal-title":"J Mach Learn Res"},{"key":"7451_CR57","unstructured":"Moritz P, Nishihara R, Stoica I, Jordan MI (2015) Sparknet: training deep networks in spark. arXiv preprint arXiv:1511.06051"},{"key":"7451_CR58","doi-asserted-by":"publisher","first-page":"2128","DOI":"10.1109\/TSP.2020.2983166","volume":"68","author":"Y Du","year":"2020","unstructured":"Du Y, Yang S, Huang K (2020) High-dimensional stochastic gradient quantization for communication-efficient edge learning. IEEE Trans Signal Process 68:2128\u20132142","journal-title":"IEEE Trans Signal Process"},{"key":"7451_CR59","doi-asserted-by":"crossref","unstructured":"Abdi A, Fekri F (2020) Quantized compressive sampling of stochastic gradients for efficient communication in distributed deep learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 34, pp 3105\u20133112","DOI":"10.1609\/aaai.v34i04.5706"},{"key":"7451_CR60","doi-asserted-by":"crossref","unstructured":"Dryden N, Moon T, Jacobs SA, Van\u00a0Essen B (2016) Communication quantization for data-parallel training of deep neural networks. In: 2016 2nd Workshop on Machine Learning in HPC Environments (MLHPC). IEEE, pp 1\u20138","DOI":"10.1109\/MLHPC.2016.004"},{"key":"7451_CR61","unstructured":"Malekijoo A, Fadaeieslam MJ, Malekijou H, Homayounfar M, Alizadeh-Shabdiz F, Rawassizadeh R (2021) Fedzip: a compression framework for communication-efficient federated learning. arXiv preprint arXiv:2102.01593"},{"key":"7451_CR62","unstructured":"Haddadpour F, Kamani MM, Mokhtari A, Mahdavi M (2021) Federated learning with compression: unified analysis and sharp guarantees. In: International Conference on Artificial Intelligence and Statistics. PMLR, pp 2350\u20132358"},{"key":"7451_CR63","doi-asserted-by":"crossref","unstructured":"Qu L, Song S, Tsui C-Y (2022) Feddq: Communication-efficient federated learning with descending quantization. In: GLOBECOM 2022-2022 IEEE Global Communications Conference. IEEE, pp 281\u2013286","DOI":"10.1109\/GLOBECOM48099.2022.10001205"},{"issue":"2","key":"7451_CR64","doi-asserted-by":"publisher","first-page":"1087","DOI":"10.1109\/TWC.2022.3201207","volume":"22","author":"Y Oh","year":"2022","unstructured":"Oh Y, Lee N, Jeon Y-S, Poor HV (2022) Communication-efficient federated learning via quantized compressed sensing. IEEE Trans Wirel Commun 22(2):1087\u20131100","journal-title":"IEEE Trans Wirel Commun"},{"key":"7451_CR65","doi-asserted-by":"crossref","unstructured":"Jonkman JA, Sherson T, Heusdens R (2018) Quantisation effects in distributed optimisation. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 3649\u20133653","DOI":"10.1109\/ICASSP.2018.8461782"},{"key":"7451_CR66","doi-asserted-by":"publisher","first-page":"62","DOI":"10.3389\/fams.2018.00062","volume":"4","author":"J Kone\u010dn\u1ef3","year":"2018","unstructured":"Kone\u010dn\u1ef3 J, Richt\u00e1rik P (2018) Randomized distributed mean estimation: accuracy vs. communication. Front Appl Math Stat 4:62","journal-title":"Front Appl Math Stat"},{"issue":"11","key":"7451_CR67","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1109\/MCOM.2010.5621984","volume":"48","author":"CR Berger","year":"2010","unstructured":"Berger CR, Wang Z, Huang J, Zhou S (2010) Application of compressive sensing to sparse channel estimation. IEEE Commun Mag 48(11):164\u2013174","journal-title":"IEEE Commun Mag"},{"key":"7451_CR68","doi-asserted-by":"publisher","first-page":"3906","DOI":"10.1109\/TSP.2021.3089824","volume":"69","author":"A Mitra","year":"2021","unstructured":"Mitra A, Richards JA, Bagchi S, Sundaram S (2021) Distributed inference with sparse and quantized communication. IEEE Trans Signal Process 69:3906\u20133921","journal-title":"IEEE Trans Signal Process"},{"key":"7451_CR69","unstructured":"Eghlidi NF, Jaggi M (2020) Sparse communication for training deep networks. arXiv preprint arXiv:2009.09271"},{"key":"7451_CR70","first-page":"8133","volume":"34","author":"AN Sahu","year":"2021","unstructured":"Sahu AN, Dutta A, Abdelmoniem AM, Banerjee T, Canini M, Kalnis P (2021) Rethinking gradient sparsification as total error minimization. Adv Neural Inf Process Syst 34:8133\u20138146","journal-title":"Adv Neural Inf Process Syst"},{"key":"7451_CR71","unstructured":"Wang H, Sievert S, Liu S, Charles Z, Papailiopoulos D, Wright S (2018) Atomo: communication-efficient learning via atomic sparsification. Advances in Neural Information Processing Systemss 31"},{"key":"7451_CR72","doi-asserted-by":"crossref","unstructured":"Shi S, Wang Q, Chu X, Li B, Qin Y, Liu R, Zhao X (2020) Communication-efficient distributed deep learning with merged gradient sparsification on gpus. In: IEEE INFOCOM 2020-IEEE Conference on Computer Communications. IEEE, pp 406\u2013415","DOI":"10.1109\/INFOCOM41043.2020.9155269"},{"key":"7451_CR73","unstructured":"Mishchenko K, Gorbunov E, Tak\u00e1\u010d M, Richt\u00e1rik P (2019) Distributed learning with compressed gradient differences. arXiv preprint arXiv:1901.09269"},{"key":"7451_CR74","doi-asserted-by":"crossref","unstructured":"Zhen K, Nguyen HD, Chang F-J, Mouchtaris A, Rastrow A (2021) Sparsification via compressed sensing for automatic speech recognition. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp 6009\u20136013","DOI":"10.1109\/ICASSP39728.2021.9413844"},{"key":"7451_CR75","doi-asserted-by":"crossref","unstructured":"Ozfatura E, Ozfatura K, G\u00fcnd\u00fcz D (2021) Time-correlated sparsification for communication-efficient federated learning. In: 2021 IEEE International Symposium on Information Theory (ISIT). IEEE, pp 461\u2013466","DOI":"10.1109\/ISIT45174.2021.9518221"},{"key":"7451_CR76","doi-asserted-by":"crossref","unstructured":"Shi S, Zhao K, Wang Q, Tang Z, Chu X (2019) A convergence analysis of distributed SGD with communication-efficient gradient sparsification. In: IJCAI, pp 3411\u20133417","DOI":"10.24963\/ijcai.2019\/473"},{"issue":"5","key":"7451_CR77","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1109\/TCSVT.2015.2513698","volume":"27","author":"J Hou","year":"2015","unstructured":"Hou J, Chau L-P, Magnenat-Thalmann N, He Y (2015) Sparse low-rank matrix approximation for data compression. IEEE Trans Circuits Syst Video Technol 27(5):1043\u20131054","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"7451_CR78","unstructured":"Vogels T, Karimireddy SP, Jaggi M (2019) Powersgd: practical low-rank gradient compression for distributed optimization. Advances in Neural Information Processing Systems"},{"key":"7451_CR79","unstructured":"Bernstein J, Wang Y-X, Azizzadenesheli K, Anandkumar A (2018) SIGNSGD: compressed optimisation for non-convex problems. In: International Conference on Machine Learning. PMLR, pp 560\u2013569"},{"key":"7451_CR80","unstructured":"Vogels T, Karimireddy SP, Jaggi M (2020) Powergossip: practical low-rank communication compression in decentralized deep learning. arXiv preprint arXiv:2008.01425"},{"key":"7451_CR81","unstructured":"Qiao Z, Yu X, Zhang J, Letaief KB (2021) Communication-efficient federated learning with dual-side low-rank compression. arXiv preprint arXiv:2104.12416"},{"issue":"8","key":"7451_CR82","doi-asserted-by":"publisher","first-page":"3618","DOI":"10.1109\/TIP.2014.2329449","volume":"23","author":"W Dong","year":"2014","unstructured":"Dong W, Shi G, Li X, Ma Y, Huang F (2014) Compressive sensing via nonlocal low-rank regularization. IEEE Trans Image Process 23(8):3618\u20133632","journal-title":"IEEE Trans Image Process"},{"key":"7451_CR83","first-page":"29321","volume":"34","author":"P Chen","year":"2021","unstructured":"Chen P, Yu H-F, Dhillon I, Hsieh C-J (2021) Drone: data-aware low-rank compression for large NLP models. Adv Neural Inf Process Syst 34:29321\u201329334","journal-title":"Adv Neural Inf Process Syst"},{"key":"7451_CR84","doi-asserted-by":"crossref","unstructured":"Idelbayev Y, Carreira-Perpin\u00e1n MA (2020) Low-rank compression of neural nets: Learning the rank of each layer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 8049\u20138059","DOI":"10.1109\/CVPR42600.2020.00807"},{"key":"7451_CR85","doi-asserted-by":"crossref","unstructured":"Jacob M, Mani M, Ye J (2019) Structured low-rank algorithms: theory, MR applications, and links to machine learning, arXiv preprint","DOI":"10.1109\/MSP.2019.2950432"},{"issue":"3","key":"7451_CR86","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1109\/MCI.2018.2840738","volume":"13","author":"T Young","year":"2018","unstructured":"Young T, Hazarika D, Poria S, Cambria E (2018) Recent trends in deep learning based natural language processing. IEEE Comput Intell Mag 13(3):55\u201375","journal-title":"IEEE Comput Intell Mag"},{"key":"7451_CR87","unstructured":"Devlin J, Chang M-W, Lee K, Toutanova K (2018) Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805"},{"key":"7451_CR88","unstructured":"Xiao X, Shen S, Bao Q, Rong H, Liu K, Wang Z, Liu J (2024) Cora: Optimizing low-rank adaptation with common subspace of large language models. arXiv preprint arXiv:2409.02119"},{"issue":"1","key":"7451_CR89","doi-asserted-by":"publisher","first-page":"2383","DOI":"10.1038\/s41467-018-04316-3","volume":"9","author":"DC Mocanu","year":"2018","unstructured":"Mocanu DC, Mocanu E, Stone P, Nguyen PH, Gibescu M, Liotta A (2018) Scalable training of artificial neural networks with adaptive sparse connectivity inspired by network science. Nat Commun 9(1):2383","journal-title":"Nat Commun"},{"key":"7451_CR90","doi-asserted-by":"crossref","unstructured":"Shen X, Liu W, Tsang I, Shen F, Sun Q-S (2017) Compressed k-means for large-scale clustering. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 31","DOI":"10.1609\/aaai.v31i1.10852"},{"key":"7451_CR91","unstructured":"Mao H, Dally W (2016) Deep compression: compressing deep neural. In: ICLR"},{"issue":"4","key":"7451_CR92","first-page":"1","volume":"52","author":"A Moffat","year":"2019","unstructured":"Moffat A (2019) Huffman coding. ACM Comput Surv CSUR) 52(4):1\u201335","journal-title":"ACM Comput Surv CSUR)"},{"key":"7451_CR93","unstructured":"Han S, Mao H, Dally W (2015) Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. arXiv preprint arXiv:1510.00149"},{"key":"7451_CR94","first-page":"12","volume":"2","author":"M VidyaSagar","year":"2013","unstructured":"VidyaSagar M, Victor JR (2013) Modified run length encoding scheme for high data compression rate. Int J Adv Res Comput Eng Technol (IJARCET) 2:12","journal-title":"Int J Adv Res Comput Eng Technol (IJARCET)"},{"issue":"6","key":"7451_CR95","doi-asserted-by":"publisher","first-page":"857","DOI":"10.1109\/5.286189","volume":"82","author":"PG Howard","year":"1994","unstructured":"Howard PG, Vitter JS (1994) Arithmetic coding for data compression. Proc IEEE 82(6):857\u2013865","journal-title":"Proc IEEE"},{"issue":"14","key":"7451_CR96","doi-asserted-by":"publisher","first-page":"5331","DOI":"10.3390\/s22145331","volume":"22","author":"Z Ma","year":"2022","unstructured":"Ma Z, Zhu H, He Z, Lu Y, Song F (2022) Deep lossless compression algorithm based on arithmetic coding for power data. Sensors 22(14):5331","journal-title":"Sensors"},{"issue":"6","key":"7451_CR97","doi-asserted-by":"publisher","first-page":"3048","DOI":"10.1109\/TPAMI.2021.3055564","volume":"44","author":"L Wang","year":"2021","unstructured":"Wang L, Yoon K-J (2021) Knowledge distillation and student\u2013teacher learning for visual intelligence: a review and new outlooks. IEEE Trans Pattern Anal Machine Intell 44(6):3048\u20133068","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"key":"7451_CR98","doi-asserted-by":"crossref","unstructured":"Zhang Y, Xiang T, Hospedales TM, Lu H (2018) Deep mutual learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4320\u20134328","DOI":"10.1109\/CVPR.2018.00454"},{"key":"7451_CR99","doi-asserted-by":"crossref","unstructured":"Xue H, Ren K (2021) Recent research trends on model compression and knowledge transfer in cnns. In: 2021 IEEE International Conference on Computer Science, Artificial Intelligence and Electronic Engineering (CSAIEE). IEEE, pp 136\u2013142","DOI":"10.1109\/CSAIEE54046.2021.9543192"},{"issue":"9","key":"7451_CR100","doi-asserted-by":"publisher","first-page":"15256","DOI":"10.1109\/TITS.2021.3139001","volume":"23","author":"S An","year":"2022","unstructured":"An S, Liao Q, Lu Z, Xue J-H (2022) Efficient semantic segmentation via self-attention and self-distillation. IEEE Trans Intell Transp Syst 23(9):15256\u201315266","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"7451_CR101","doi-asserted-by":"crossref","unstructured":"Ji M, Shin S, Hwang S, Park G, Moon I-C (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":"7451_CR102","doi-asserted-by":"crossref","unstructured":"Mou T, Jiang X, Li J, Yan B, Chen Q, Zhang T, Huang W, Gao C, Chen Y (2023) FedRAMP: decentralized federated learning with a feature attention based multi-teacher knowledge distillation for healthcare. In: 2023 IEEE 29th International Conference on Parallel and Distributed Systems (ICPADS). IEEE, pp 1246\u20131253","DOI":"10.1109\/ICPADS60453.2023.00180"},{"key":"7451_CR103","doi-asserted-by":"crossref","unstructured":"Lee Y, Wu W (2024) QMKD: atwo-stage approach to enhance multi-teacher knowledge distillation. In: 2024 International Joint Conference on Neural Networks (IJCNN). IEEE, pp 1\u20137","DOI":"10.1109\/IJCNN60899.2024.10650186"},{"key":"7451_CR104","doi-asserted-by":"crossref","unstructured":"Liu H, Wang Y, Liu H, Sun F, Yao A (2024) Small scale data-free knowledge distillation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 6008\u20136016","DOI":"10.1109\/CVPR52733.2024.00574"},{"key":"7451_CR105","doi-asserted-by":"crossref","unstructured":"Zhao K, Zhao M (2024) Self-supervised quantization-aware knowledge distillation. arXiv preprint arXiv:2403.11106","DOI":"10.1145\/3583740.3626620"},{"key":"7451_CR106","first-page":"6906","volume":"34","author":"S Stanton","year":"2021","unstructured":"Stanton S, Izmailov P, Kirichenko P, Alemi AA, Wilson AG (2021) Does knowledge distillation really work? Adv Neural Inf Process Syst 34:6906\u20136919","journal-title":"Adv Neural Inf Process Syst"},{"key":"7451_CR107","unstructured":"Feng Q, Li W, Lin T, Chen X (2024) Align-kd: Distilling cross-modal alignment knowledge for mobile vision-language model. arXiv preprint arXiv:2412.01282"},{"key":"7451_CR108","unstructured":"Ren J, Rajbhandari S, Aminabadi RY, Ruwase O, Yang S, Zhang M, Li D, He Y (2021) $$\\{$$Zero-offload$$\\}$$: Democratizing $$\\{$$billion-scale$$\\}$$ model training. In: 2021 USENIX Annual Technical Conference (USENIX ATC 21), pp 551\u2013564"},{"key":"7451_CR109","unstructured":"Arora R, Marinov TV, Ullah E (2020) Private stochastic convex optimization: efficient algorithms for non-smooth objectives. arXiv preprint arXiv:2002.09609"},{"key":"7451_CR110","doi-asserted-by":"crossref","unstructured":"Pan J, Bulat A, Tan F, Zhu X, Dudziak L, Li H, Tzimiropoulos G, Martinez B (2022) EdgeViTs: competing light-weight cnns on mobile devices with vision transformers. In: European Conference on Computer Vision. Springer, Berlin, pp 294\u2013311","DOI":"10.1007\/978-3-031-20083-0_18"},{"key":"7451_CR111","doi-asserted-by":"crossref","unstructured":"Qu R, Bo P, Zhang Y, Wang T, Zhang W, Zhang L (2022) Security verification of 1553b bus components used in aerospace. In: 2022 IEEE 4th International Conference on Power, Intelligent Computing and Systems (ICPICS). IEEE, pp 486\u2013489","DOI":"10.1109\/ICPICS55264.2022.9873735"},{"key":"7451_CR112","doi-asserted-by":"crossref","unstructured":"Hanif MA, Shafique M (2023) Cross-layer optimizations for efficient deep learning inference at the edge. In: Embedded Machine Learning for Cyber-Physical, IoT, and Edge Computing: Software Optimizations and Hardware\/Software Codesign. Springer, Cham, pp 225\u2013248","DOI":"10.1007\/978-3-031-39932-9_9"},{"key":"7451_CR113","doi-asserted-by":"crossref","unstructured":"Song J, Yim J, Jung J, Jang H, Kim H-J, Kim Y, Lee J (2023) Optimus-cc: efficient large nlp model training with 3d parallelism aware communication compression. In: Proceedings of the 28th ACM International Conference on Architectural Support for Programming Languages and Operating Systems, vol 2 pp 560\u2013573","DOI":"10.1145\/3575693.3575712"},{"key":"7451_CR114","doi-asserted-by":"publisher","unstructured":"Islamov R, Qian X, Hanzely S, Safaryan M, Richt\u00e1rik P (2023) Distributed newton-type methods with communication compression and bernoulli aggregation. Trans Mach Learn Res. https:\/\/doi.org\/10.48550\/arXiv.2206.03588","DOI":"10.48550\/arXiv.2206.03588"},{"key":"7451_CR115","doi-asserted-by":"publisher","DOI":"10.1016\/j.sysarc.2024.103116","volume":"150","author":"Z Wang","year":"2024","unstructured":"Wang Z, Duan Q, Xu Y, Zhang L (2024) An efficient bandwidth-adaptive gradient compression algorithm for distributed training of deep neural networks. J Syst Architect 150:103116","journal-title":"J Syst Architect"},{"key":"7451_CR116","doi-asserted-by":"crossref","unstructured":"Zhang L, Zhang L, Shi S, Chu X, Li B (2023) Evaluation and optimization of gradient compression for distributed deep learning. In: 2023 IEEE 43rd International Conference on Distributed Computing Systems (ICDCS). IEEE, pp 361\u2013371","DOI":"10.1109\/ICDCS57875.2023.00031"},{"key":"7451_CR117","unstructured":"Zhong Y, Xie C, Zheng S, Lin H (2021) Compressed communication for distributed training: adaptive methods and system. arXiv preprint arXiv:2105.07829"},{"key":"7451_CR118","unstructured":"Huang X, Li P, Li X (2023) Stochastic controlled averaging for federated learning with communication compression. arXiv preprint arXiv:2308.08165"},{"key":"7451_CR119","unstructured":"Zheng S, Huang Z, Kwok J (2019) Communication-efficient distributed blockwise momentum sgd with error-feedback. Advances in Neural Information Processing Systems 32"},{"key":"7451_CR120","doi-asserted-by":"crossref","unstructured":"Li L, Shi D, Hou R, Li H, Pan M, Han Z (2021) To talk or to work: flexible communication compression for energy efficient federated learning over heterogeneous mobile edge devices. In: IEEE INFOCOM 2021-IEEE Conference on Computer Communications. IEEE, pp 1\u201310","DOI":"10.1109\/INFOCOM42981.2021.9488839"},{"key":"7451_CR121","unstructured":"Rammal A, Gruntkowska K, Fedin N, Gorbunov E, Richt\u00e1rik P (2024) Communication compression for byzantine robust learning: new efficient algorithms and improved rates. In: International Conference on Artificial Intelligence and Statistics. PMLR, pp 1207\u20131215"},{"key":"7451_CR122","doi-asserted-by":"crossref","unstructured":"Zhang B, Tian J, Di S, Yu X, Feng Y, Liang X, Tao D, Cappello F (2023) FZ-GPU: a fast and high-ratio lossy compressor for scientific computing applications on gpus. In: Proceedings of the 32nd International Symposium on High-Performance Parallel and Distributed Computing, pp 129\u2013142","DOI":"10.1145\/3588195.3592994"},{"key":"7451_CR123","doi-asserted-by":"crossref","unstructured":"Li S, Lindstrom P, Clyne J (2023) Lossy scientific data compression with sperr. In: 2023 IEEE International Parallel and Distributed Processing Symposium (IPDPS). IEEE, pp 1007\u20131017","DOI":"10.1109\/IPDPS54959.2023.00104"},{"key":"7451_CR124","doi-asserted-by":"crossref","unstructured":"Kriemann R, Ltaief H, Luong MB, P\u00e9rez FEH, Im HG, Keyes D (2022) High-performance spatial data compression for scientific applications. In: European Conference on Parallel Processing. Springer, Berlin, pp 403\u2013418","DOI":"10.1007\/978-3-031-12597-3_25"},{"key":"7451_CR125","doi-asserted-by":"crossref","unstructured":"Liu Y, Jia W, Yang T, Yin M, Jin S (2024) Enhancing lossy compression through cross-field information for scientific applications. In: SC24-W: Workshops of the International Conference for High Performance Computing, Networking, Storage and Analysis. IEEE, pp 300\u2013308","DOI":"10.1109\/SCW63240.2024.00046"},{"key":"7451_CR126","unstructured":"Shen L, Sun Y, Yu Z, Ding L, Tian X, Tao D (2023) On efficient training of large-scale deep learning models: a literature review. arXiv preprint arXiv:2304.03589"},{"key":"7451_CR127","doi-asserted-by":"crossref","unstructured":"Dowe DL, Hern\u00e1ndez-Orallo J, Das PK (2011) Compression and intelligence: social environments and communication. In: Artificial General Intelligence: 4th International Conference, AGI 2011, Mountain View, CA, USA, August 3-6, 2011. Proceedings 4. Springer, Berlin, pp 204\u2013211","DOI":"10.1007\/978-3-642-22887-2_21"},{"key":"7451_CR128","unstructured":"Hanzely F, Mishchenko K, Richt\u00e1rik P (2018) Sega: variance reduction via gradient sketching. Advances in Neural Information Processing Systems 31"},{"key":"7451_CR129","doi-asserted-by":"crossref","unstructured":"Sattler F, Wiedemann S, M\u00fcller K-R, Samek W (2019) Sparse binary compression: towards distributed deep learning with minimal communication. In: 2019 International Joint Conference on Neural Networks (IJCNN). IEEE, pp 1\u20138","DOI":"10.1109\/IJCNN.2019.8852172"},{"key":"7451_CR130","unstructured":"Yu Y, Wu J, Huang L (2019) Double quantization for communication-efficient distributed optimization. Advances in Neural Information Processing Systems 32"},{"key":"7451_CR131","doi-asserted-by":"crossref","unstructured":"Li Y, Park J, Alian M, Yuan Y, Qu Z, Pan P, Wang R, Schwing A, Esmaeilzadeh H, Kim NS (2018) A network-centric hardware\/algorithm co-design to accelerate distributed training of deep neural networks. In: 2018 51st Annual IEEE\/ACM International Symposium on Microarchitecture (MICRO). IEEE, pp 175\u2013188","DOI":"10.1109\/MICRO.2018.00023"},{"key":"7451_CR132","unstructured":"Tyurin A, Richt\u00e1rik P (2024) 2direction: theoretically faster distributed training with bidirectional communication compression. Advances in Neural Information Processing Systems 36"},{"issue":"4","key":"7451_CR133","doi-asserted-by":"publisher","first-page":"851","DOI":"10.1109\/JSAC.2023.3242710","volume":"41","author":"X Cao","year":"2023","unstructured":"Cao X, Ba\u015far T, Diggavi S, Eldar YC, Letaief KB, Poor HV, Zhang J (2023) Communication-efficient distributed learning: an overview. IEEE J Sel Areas Commun 41(4):851\u2013873","journal-title":"IEEE J Sel Areas Commun"},{"key":"7451_CR134","unstructured":"Koloskova A, Loizou N, Boreiri S, Jaggi M, Stich S (2020) A unified theory of decentralized sgd with changing topology and local updates. In: International Conference on Machine Learning. PMLR, pp 5381\u20135393"},{"key":"7451_CR135","doi-asserted-by":"crossref","unstructured":"Abdelmoniem AM, Canini M (2021) Dc2: delay-aware compression control for distributed machine learning. In: IEEE INFOCOM 2021-IEEE Conference on Computer Communications. IEEE, pp 1\u201310","DOI":"10.1109\/INFOCOM42981.2021.9488810"},{"issue":"9","key":"7451_CR136","doi-asserted-by":"publisher","first-page":"5477","DOI":"10.1109\/TAC.2022.3225515","volume":"68","author":"X Yi","year":"2022","unstructured":"Yi X, Zhang S, Yang T, Chai T, Johansson KH (2022) Communication compression for distributed nonconvex optimization. IEEE Trans Autom Control 68(9):5477\u20135492","journal-title":"IEEE Trans Autom Control"},{"key":"7451_CR137","unstructured":"He Y, Huang X, Yuan K (2024) Unbiased compression saves communication in distributed optimization: when and how much? Advances in Neural Information Processing Systems 36"},{"key":"7451_CR138","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpdc.2023.104811","volume":"185","author":"L Dai","year":"2024","unstructured":"Dai L, Gong L, An Z, Xu Y, Diao B (2024) Sketch-fusion: a gradient compression method with multi-layer fusion for communication-efficient distributed training. J Parallel Distrib Comput 185:104811","journal-title":"J Parallel Distrib Comput"},{"key":"7451_CR139","doi-asserted-by":"crossref","unstructured":"Minton GT, Price E (2014) Improved concentration bounds for count-sketch. In: Proceedings of the Twenty-fifth Annual ACM-SIAM Symposium on Discrete Algorithms, pp. 669\u2013686","DOI":"10.1137\/1.9781611973402.51"},{"key":"7451_CR140","unstructured":"Tang H, Gan S, Zhang C, Zhang T, Liu J (2018) Communication compression for decentralized training. Advances in Neural Information Processing Systems 31 (NeurIPS 2018)"},{"key":"7451_CR141","unstructured":"Koloskova A, Lin T, Stich SU, Jaggi M (2019) Decentralized deep learning with arbitrary communication compression. arXiv preprint arXiv:1907.09356"},{"issue":"1","key":"7451_CR142","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1080\/10556788.2022.2117355","volume":"38","author":"S Horv\u00e1th","year":"2023","unstructured":"Horv\u00e1th S, Kovalev D, Mishchenko K, Richt\u00e1rik P, Stich S (2023) Stochastic distributed learning with gradient quantization and double-variance reduction. Optim Methods Softw 38(1):91\u2013106","journal-title":"Optim Methods Softw"},{"key":"7451_CR143","doi-asserted-by":"crossref","unstructured":"Rasley J, Rajbhandari S, Ruwase O, He Y (2020) Deepspeed: System optimizations enable training deep learning models with over 100 billion parameters. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 3505\u20133506","DOI":"10.1145\/3394486.3406703"},{"issue":"3","key":"7451_CR144","doi-asserted-by":"publisher","first-page":"963","DOI":"10.1109\/SURV.2012.060912.00149","volume":"15","author":"T Ma","year":"2012","unstructured":"Ma T, Hempel M, Peng D, Sharif H (2012) A survey of energy-efficient compression and communication techniques for multimedia in resource constrained systems. IEEE Commun Surv Tutor 15(3):963\u2013972","journal-title":"IEEE Commun Surv Tutor"},{"key":"7451_CR145","unstructured":"Horv\u00f3th S, Ho C-Y, Horvath L, Sahu AN, Canini M, Richt\u00e1rik P (2022) Natural compression for distributed deep learning. In: Mathematical and Scientific Machine Learning. PMLR, pp. 129\u2013141"},{"key":"7451_CR146","unstructured":"McMahan B, Moore E, Ramage D, Hampson S, Arcas BA (2017) Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics. PMLR, pp 1273\u20131282"},{"key":"7451_CR147","first-page":"4285","volume":"35","author":"Z Li","year":"2022","unstructured":"Li Z, Zhao H, Li B, Chi Y (2022) SoteriaFL: a unified framework for private federated learning with communication compression. Adv Neural Inf Process Syst 35:4285\u20134300","journal-title":"Adv Neural Inf Process Syst"},{"issue":"2","key":"7451_CR148","doi-asserted-by":"publisher","first-page":"845","DOI":"10.1109\/TCOMM.2023.3327778","volume":"72","author":"Y Liu","year":"2023","unstructured":"Liu Y, Rini S, Salehkalaibar S, Chen J (2023) M22: a communication-efficient algorithm for federated learning inspired by rate-distortion. IEEE Trans Commun 72(2):845\u2013860","journal-title":"IEEE Trans Commun"},{"key":"7451_CR149","doi-asserted-by":"publisher","DOI":"10.1016\/j.is.2023.102226","volume":"116","author":"J Wu","year":"2023","unstructured":"Wu J, Wang Y, Shen Z, Liu L (2023) Adaptive client and communication optimizations in federated learning. Inf Syst 116:102226","journal-title":"Inf Syst"},{"key":"7451_CR150","doi-asserted-by":"crossref","unstructured":"Shahid O, Pouriyeh S, Parizi RM, Sheng QZ, Srivastava G, Zhao L (2021) Communication efficiency in federated learning: Achievements and challenges. arXiv preprint arXiv:2107.10996","DOI":"10.3390\/app12188980"},{"key":"7451_CR151","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.comcom.2023.03.002","volume":"203","author":"Z Yang","year":"2023","unstructured":"Yang Z, Sun Q (2023) Joint think locally and globally: communication-efficient federated learning with feature-aligned filter selection. Comput Commun 203:119\u2013128","journal-title":"Comput Commun"},{"key":"7451_CR152","doi-asserted-by":"publisher","first-page":"376","DOI":"10.1016\/j.future.2022.10.026","volume":"140","author":"X Zhu","year":"2023","unstructured":"Zhu X, Wang J, Chen W, Sato K (2023) Model compression and privacy preserving framework for federated learning. Future Gener Comput Syst 140:376\u2013389","journal-title":"Future Gener Comput Syst"},{"issue":"12","key":"7451_CR153","doi-asserted-by":"publisher","first-page":"8669","DOI":"10.1016\/j.jfranklin.2022.12.053","volume":"360","author":"Z Zhao","year":"2023","unstructured":"Zhao Z, Mao Y, Liu Y, Song L, Ouyang Y, Chen X, Ding W (2023) Towards efficient communications in federated learning: a contemporary survey. J Frankl Inst 360(12):8669\u20138703","journal-title":"J Frankl Inst"},{"key":"7451_CR154","doi-asserted-by":"crossref","unstructured":"Zhou Q, Kousha P, Anthony Q, Shafie\u00a0Khorassani K, Shafi A, Subramoni H, Panda DK (2022) Accelerating mpi all-to-all communication with online compression on modern GPU clusters. In: International Conference on High Performance Computing. Springer, Berlin, pp 3\u201325","DOI":"10.1007\/978-3-031-07312-0_1"},{"key":"7451_CR155","doi-asserted-by":"crossref","unstructured":"Huang J, Di S, Yu X, Zhai Y, Liu J, Huang Y, Raffenetti K, Zhou H, Zhao K, Chen Z et al (2024) Poster: optimizing collective communications with error-bounded lossy compression for GPU clusters. In: Proceedings of the 29th ACM SIGPLAN Annual Symposium on Principles and Practice of Parallel Programming, pp 454\u2013456","DOI":"10.1145\/3627535.3638467"},{"key":"7451_CR156","doi-asserted-by":"crossref","unstructured":"Huang J, Di S, Yu X, Zhai Y, Zhang Z, Liu J, Lu X, Raffenetti K, Zhou H, Zhao K, Chen Z, Cappello F, Guo Y, Thakur R (2024) An optimized error-controlled MPI Collective Framework Integrated with Lossy Compression","DOI":"10.1109\/IPDPS57955.2024.00072"},{"key":"7451_CR157","doi-asserted-by":"crossref","unstructured":"Yu X, Di S, Zhao K, Tian J, Tao D, Liang X, Cappello F (2022) Ultrafast error-bounded lossy compression for scientific datasets. In: Proceedings of the 31st International Symposium on High-Performance Parallel and Distributed Computing, pp 159\u2013171","DOI":"10.1145\/3502181.3531473"},{"key":"7451_CR158","doi-asserted-by":"crossref","unstructured":"Fei J, Ho C-Y, Sahu AN, Canini M, Sapio A (2021) Efficient sparse collective communication and its application to accelerate distributed deep learning. In: Proceedings of the 2021 ACM SIGCOMM 2021 Conference, pp 676\u2013691","DOI":"10.1145\/3452296.3472904"},{"key":"7451_CR159","unstructured":"Tang H, Gan S, Awan AA, Rajbhandari S, Li C, Lian X, Liu J, Zhang C, He Y (2021) 1-bit adam: Communication efficient large-scale training with adam\u2019s convergence speed. In: International Conference on Machine Learning. PMLR, pp 10118\u201310129"},{"key":"7451_CR160","doi-asserted-by":"crossref","unstructured":"Huang J, Di S, Yu X, Zhai Y, Liu J, Huang Y, Raffenetti K, Zhou H, Zhao K, Chen Z et al (2023) GZCCL: compression-accelerated collective communication framework for GPU clusters. arXiv preprint arXiv:2308.05199","DOI":"10.1145\/3650200.3656636"},{"key":"7451_CR161","unstructured":"Huang J, Di S, Yu X, Guo Y. Accelerating collective communications with lossy compression on GPU. Dimensions 449, 849\u2013849235"},{"key":"7451_CR162","unstructured":"Suresh AT, Felix XY, Kumar S, McMahan HB (2017) Distributed mean estimation with limited communication. In: International Conference on Machine learning. PMLR, pp 3329\u20133337"},{"key":"7451_CR163","unstructured":"Liu X, Li Y, Wang R, Tang J, Yan M (2020) Linear convergent decentralized optimization with compression. arXiv preprint arXiv:2007.00232"},{"issue":"15","key":"7451_CR164","doi-asserted-by":"publisher","first-page":"2375","DOI":"10.1049\/iet-com.2018.5348","volume":"13","author":"H Haneche","year":"2019","unstructured":"Haneche H, Ouahabi A, Boudraa B (2019) New mobile communication system design for rayleigh environments based on compressed sensing-source coding. IET Commun 13(15):2375\u20132385","journal-title":"IET Commun"},{"issue":"1","key":"7451_CR165","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/JSAC.2020.3036968","volume":"39","author":"H Xie","year":"2020","unstructured":"Xie H, Qin Z (2020) A lite distributed semantic communication system for internet of things. IEEE J Sel Areas Commun 39(1):142\u2013153","journal-title":"IEEE J Sel Areas Commun"},{"issue":"4","key":"7451_CR166","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/IOTM.001.2200177","volume":"5","author":"C Zhang","year":"2022","unstructured":"Zhang C, Zou H, Lasaulce S, Saad W, Kountouris M, Bennis M (2022) Goal-oriented communications for the IoT and application to data compression. IEEE Intern Things Mag 5(4):58\u201363","journal-title":"IEEE Intern Things Mag"},{"issue":"1","key":"7451_CR167","doi-asserted-by":"publisher","first-page":"100","DOI":"10.47839\/ijc.21.1.2523","volume":"21","author":"YS Manzhos","year":"2022","unstructured":"Manzhos YS, Sokolova YV (2022) A method of iot information compression. Int J Comput 21(1):100\u2013110","journal-title":"Int J Comput"},{"key":"7451_CR168","doi-asserted-by":"crossref","unstructured":"Cappello F, Di S, Gok AM (2020) Fulfilling the promises of lossy compression for scientific applications. In: Driving Scientific and Engineering Discoveries Through the Convergence of HPC, Big Data and AI: 17th Smoky Mountains Computational Sciences and Engineering Conference, SMC 2020, Oak Ridge, TN, USA, August 26\u201328, 2020, Revised Selected Papers 17. Springer, Berlin, pp 99\u2013116","DOI":"10.1007\/978-3-030-63393-6_7"},{"issue":"11","key":"7451_CR169","doi-asserted-by":"publisher","first-page":"1219","DOI":"10.1109\/TCSVT.2004.835150","volume":"14","author":"WA Pearlman","year":"2004","unstructured":"Pearlman WA, Islam A, Nagaraj N, Said A (2004) Efficient, low-complexity image coding with a set-partitioning embedded block coder. IEEE Trans Circuits Syst Video Technol 14(11):1219\u20131235","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"7451_CR170","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1016\/j.compfluid.2012.04.020","volume":"80","author":"R Sakai","year":"2013","unstructured":"Sakai R, Sasaki D, Nakahashi K (2013) Parallel implementation of large-scale CFD data compression toward aeroacoustic analysis. Comput Fluids 80:116\u2013127","journal-title":"Comput Fluids"},{"key":"7451_CR171","doi-asserted-by":"publisher","DOI":"10.1016\/j.cageo.2020.104599","volume":"145","author":"A Poppick","year":"2020","unstructured":"Poppick A, Nardi J, Feldman N, Baker AH, Pinard A, Hammerling DM (2020) A statistical analysis of lossily compressed climate model data. Comput Geosci 145:104599","journal-title":"Comput Geosci"},{"key":"7451_CR172","doi-asserted-by":"crossref","unstructured":"Chen Y, Zhang F, Hong Y, Chai Y, Lu W, Chen H, Du X, Wang P, Mi L, Li J et al (2022) Taming the big data monster: managing petabytes of data with multi-model databases. In: 2022 IEEE 34th International Symposium on Computer Architecture and High Performance Computing (SBAC-PAD). IEEE, pp 283\u2013292","DOI":"10.1109\/SBAC-PAD55451.2022.00039"},{"key":"7451_CR173","doi-asserted-by":"crossref","unstructured":"Liu Z, Shi Z (2020) A fusion algorithm of multi-model pruning and collaborative distillation learning. In: Journal of Physics: Conference Series, vol 1607, p 012096","DOI":"10.1088\/1742-6596\/1607\/1\/012096"},{"key":"7451_CR174","doi-asserted-by":"crossref","unstructured":"Shi P, Gao F, Liang S, Yu S (2020) Multi-model inference acceleration on embedded multi-core processors. In: 2020 International Conference on Intelligent Computing and Human\u2013Computer Interaction (ICHCI). IEEE, pp 400\u2013403","DOI":"10.1109\/ICHCI51889.2020.00090"},{"issue":"5s","key":"7451_CR175","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3358205","volume":"18","author":"K Bhardwaj","year":"2019","unstructured":"Bhardwaj K, Lin C-Y, Sartor A, Marculescu R (2019) Memory-and communication-aware model compression for distributed deep learning inference on IoT. ACM Trans Embed Comput Syst TECS) 18(5s):1\u201322","journal-title":"ACM Trans Embed Comput Syst (TECS)"},{"key":"7451_CR176","unstructured":"Liu X, Li Y, Tang J, Yan M (2020) A double residual compression algorithm for efficient distributed learning. In: International Conference on Artificial Intelligence and Statistics. PMLR, pp 133\u2013143"},{"issue":"5","key":"7451_CR177","doi-asserted-by":"publisher","first-page":"1366","DOI":"10.1109\/TIFS.2018.2878172","volume":"14","author":"C Ting","year":"2018","unstructured":"Ting C, Field R, Fisher A, Bauer T (2018) Compression analytics for classification and anomaly detection within network communication. IEEE Trans Inf Forens Secur 14(5):1366\u20131376","journal-title":"IEEE Trans Inf Forens Secur"},{"key":"7451_CR178","doi-asserted-by":"crossref","unstructured":"Chen B, Bakhshi A, Batista G, Ng B, Chin T-J (2022) Update compression for deep neural networks on the edge. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 3076\u20133086","DOI":"10.1109\/CVPRW56347.2022.00347"},{"key":"7451_CR179","doi-asserted-by":"crossref","unstructured":"Peng J, Fang J, Liu J, Xie M, Dai Y, Yang B, Li S, Wang Z (2023) Optimizing mpi collectives on shared memory multi-cores. In: Proceedings of the International Conference for High Performance Computing, Networking, Storage and Analysis, pp 1\u201315","DOI":"10.1145\/3581784.3607074"},{"key":"7451_CR180","doi-asserted-by":"crossref","unstructured":"Jeon W, Ko G, Lee J, Lee H, Ha D, Ro WW (2021) Deep learning with gpus. In: Advances in Computers. Elsevier, Amsterdam, vol 122, pp 167\u2013215","DOI":"10.1016\/bs.adcom.2020.11.003"},{"key":"7451_CR181","unstructured":"Fadhil A, Haarslev V (2006) Gloo: a graphical query language for owl ontologies. In: OWLED, vol 216"},{"issue":"3","key":"7451_CR182","first-page":"421","volume":"1","author":"B P\u00e9rez\u2013Acu\u00f1a","year":"2021","unstructured":"P\u00e9rez\u2013Acu\u00f1a B, Fern\u00e1ndez-Aller C (2021) Facebook and artificial intelligence: a review of good practices. AI and Ethics 1(3):421\u2013435","journal-title":"AI and Ethics"},{"key":"7451_CR183","doi-asserted-by":"crossref","unstructured":"Hazelwood K, Bird S, Brooks D, Chintala S, Diril U, Dzhulgakov D, Fawzy M, Jia B, Jia Y, Kalro A et al (2018) Applied machine learning at facebook: a datacenter infrastructure perspective. In: 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA). IEEE, pp 620\u2013629","DOI":"10.1109\/HPCA.2018.00059"},{"key":"7451_CR184","first-page":"82","volume":"2","author":"L Luo","year":"2020","unstructured":"Luo L, West P, Nelson J, Krishnamurthy A, Ceze L (2020) Plink: discovering and exploiting locality for accelerated distributed training on the public cloud. Proc Mach Learn Syst 2:82\u201397","journal-title":"Proc Mach Learn Syst"},{"key":"7451_CR185","unstructured":"Sergeev A, Del\u00a0Balso M (2018) Horovod: fast and easy distributed deep learning in tensorflow. arXiv preprint arXiv:1802.05799"},{"key":"7451_CR186","unstructured":"Farhat A, Ghobadi M Communication patterns in distributed deep learning. Massachusetts institute of technology. https:\/\/people.csail.mit.edu\/ghobadi\/theses\/amir_farhat_superUROP_report"},{"key":"7451_CR187","volume-title":"Quantum computation and quantum information","author":"MA Nielsen","year":"2010","unstructured":"Nielsen MA, Chuang IL (2010) Quantum computation and quantum information. Cambridge University Press, Cambridge"},{"issue":"4","key":"7451_CR188","doi-asserted-by":"publisher","DOI":"10.1088\/2058-9565\/aa8072","volume":"2","author":"J Romero","year":"2017","unstructured":"Romero J, Olson JP, Aspuru-Guzik A (2017) Quantum autoencoders for efficient compression of quantum data. Quantum Sci Technol 2(4):045001","journal-title":"Quantum Sci Technol"},{"key":"7451_CR189","doi-asserted-by":"crossref","unstructured":"Lee S, Park J, Heo J (2018) Improved reconciliation with polar codes in quantum key distribution. arXiv preprint arXiv:1805.05046","DOI":"10.1109\/ICUFN.2018.8436787"},{"issue":"1","key":"7451_CR190","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1109\/JSTSP.2022.3224591","volume":"17","author":"M Xu","year":"2022","unstructured":"Xu M, Niyato D, Yang Z, Xiong Z, Kang J, Kim DI, Shen X (2022) Privacy-preserving intelligent resource allocation for federated edge learning in quantum internet. IEEE J Sel Top Signal Process 17(1):142\u2013157","journal-title":"IEEE J Sel Top Signal Process"},{"issue":"3","key":"7451_CR191","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41566-019-0358-x","volume":"13","author":"AL Gaeta","year":"2019","unstructured":"Gaeta AL, Lipson M, Kippenberg T (2019) Photonic-chip-based frequency combs. Nat Photon 13(3):158\u2013169","journal-title":"Nat Photon"},{"key":"7451_CR192","unstructured":"Liu C-Y, Kuo E-J, Lin C-HA, Young JG, Chang Y-J, Hsieh M-H, Goan H-S (2024) Quantum-train: rethinking hybrid quantum-classical machine learning in the model compression perspective. arXiv preprint arXiv:2405.11304"},{"issue":"1","key":"7451_CR193","doi-asserted-by":"publisher","first-page":"912","DOI":"10.1038\/s41467-023-36493-1","volume":"14","author":"S Bartolucci","year":"2023","unstructured":"Bartolucci S, Birchall P, Bombin H, Cable H, Dawson C, Gimeno-Segovia M, Johnston E, Kieling K, Nickerson N, Pant M et al (2023) Fusion-based quantum computation. Nat Commun 14(1):912","journal-title":"Nat Commun"},{"issue":"1","key":"7451_CR194","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1038\/s42005-022-01123-7","volume":"6","author":"L Parny","year":"2023","unstructured":"Parny L, Alibart O, Debaud J, Gressani S, Lagarrigue A, Martin A, Metrat A, Schiavon M, Troisi T, Diamanti E et al (2023) Satellite-based quantum information networks: use cases, architecture, and roadmap. Commun Phys 6(1):12","journal-title":"Commun Phys"},{"key":"7451_CR195","doi-asserted-by":"publisher","first-page":"79","DOI":"10.22331\/q-2018-08-06-79","volume":"2","author":"J Preskill","year":"2018","unstructured":"Preskill J (2018) Quantum computing in the nisq era and beyond. Quantum 2:79","journal-title":"Quantum"},{"issue":"7","key":"7451_CR196","doi-asserted-by":"publisher","first-page":"1419","DOI":"10.1007\/s00607-023-01154-0","volume":"105","author":"M Bagherian","year":"2023","unstructured":"Bagherian M, Chehade S, Whitney B, Passian A (2023) Classical and quantum compression for edge computing: the ubiquitous data dimensionality reduction. Computing 105(7):1419\u20131465","journal-title":"Computing"},{"key":"7451_CR197","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.physletb.2017.12.053","volume":"778","author":"D George","year":"2018","unstructured":"George D, Huerta EA (2018) Deep learning for real-time gravitational wave detection and parameter estimation: Results with advanced ligo data. Phys Lett B 778:64\u201370","journal-title":"Phys Lett B"},{"key":"7451_CR198","doi-asserted-by":"crossref","unstructured":"Dunjko V, Briegel H (2017) Machine learning and artificial intelligence in the quantum domain. arXiv preprint arXiv:1709.02779","DOI":"10.1088\/1361-6633\/aab406"},{"issue":"1","key":"7451_CR199","doi-asserted-by":"publisher","first-page":"175","DOI":"10.1038\/s41377-023-01173-8","volume":"12","author":"W Luo","year":"2023","unstructured":"Luo W, Cao L, Shi Y, Wan L, Zhang H, Li S, Chen G, Li Y, Li S, Wang Y et al (2023) Recent progress in quantum photonic chips for quantum communication and internet. Light Sci Appl 12(1), 175","journal-title":"Light Sci Appl"}],"container-title":["The Journal of Supercomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07451-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11227-025-07451-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11227-025-07451-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T16:03:23Z","timestamp":1749053003000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11227-025-07451-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,4]]},"references-count":199,"journal-issue":{"issue":"8","published-online":{"date-parts":[[2025,6]]}},"alternative-id":["7451"],"URL":"https:\/\/doi.org\/10.1007\/s11227-025-07451-z","relation":{},"ISSN":["1573-0484"],"issn-type":[{"value":"1573-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,4]]},"assertion":[{"value":"12 May 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 June 2025","order":2,"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":"Competing interests"}}],"article-number":"964"}}