{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,3]],"date-time":"2026-04-03T15:08:14Z","timestamp":1775228894149,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","funder":[{"DOI":"10.13039\/100000144","name":"Division of Computer and Network Systems","doi-asserted-by":"publisher","award":["1704092"],"award-info":[{"award-number":["1704092"]}],"id":[{"id":"10.13039\/100000144","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000144","name":"Division of Computer and Network Systems","doi-asserted-by":"publisher","award":["1704662"],"award-info":[{"award-number":["1704662"]}],"id":[{"id":"10.13039\/100000144","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Mobile Comput."],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmc.2021.3107424","type":"journal-article","created":{"date-parts":[[2021,8,30]],"date-time":"2021-08-30T21:15:44Z","timestamp":1630358144000},"page":"1-1","source":"Crossref","is-referenced-by-count":17,"title":["A Co-Scheduling Framework for DNN Models on Mobile and Edge Devices with Heterogeneous Hardware"],"prefix":"10.1109","author":[{"given":"Zhiyuan","family":"Xu","sequence":"first","affiliation":[]},{"given":"Dejun","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Chengxiang","family":"Yin","sequence":"additional","affiliation":[]},{"given":"Jian","family":"Tang","sequence":"additional","affiliation":[]},{"given":"Yanzhi","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Guoliang","family":"Xue","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref1","article-title":"Tensorflow: Large-scale machine learning on heterogeneous distributed systems","author":"Abadi","year":"2016"},{"key":"ref4","first-page":"5151","article-title":"Scalable methods for 8-bit training of neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Banner"},{"key":"ref5","first-page":"742","article-title":"Learning efficient object detection models with knowledge distillation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref6","first-page":"395","article-title":"PCC: Re-architecting congestion control for consistent high performance","volume-title":"Proc. USENIX Conf. Netw. Syst. Des. Implementation","author":"Dong"},{"key":"ref7","article-title":"TVM: An automated end-to-end optimizing compiler for deep learning","author":"Chen","year":"2015"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241559"},{"key":"ref10","first-page":"1126","article-title":"Model-Agnostic meta-learning for fast adaptation of deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Finn"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/2973750.2973777"},{"key":"ref12","volume-title":"Deep Learning","author":"Goodfellow","year":"2016"},{"key":"ref13","first-page":"123","article-title":"MCDNN: An execution framework for deep neural networks on resource-constrained devices","volume-title":"Proc. Annu. Int. Conf. Mobile Syst. Appl. Serv.","author":"Han"},{"key":"ref14","first-page":"1135","article-title":"Learning both weights and connections for efficient neural network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref15","article-title":"Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding","author":"Han"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_48"},{"key":"ref19","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref20","first-page":"1","article-title":"Distributed prioritized experience replay","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Horgan"},{"key":"ref21","first-page":"1","article-title":"Loss-aware weight quantization of deep networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hou"},{"key":"ref22","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017"},{"key":"ref23","first-page":"4107","article-title":"Binarized neural networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Hubara"},{"key":"ref24","article-title":"SqueezeNet: Alexnet-level accuracy with 50x fewer parameters and< 0.5 MB model size","author":"Iandola","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037698"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2012.12.006"},{"key":"ref27","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/IPSN.2016.7460664"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref30","article-title":"Ternary weight networks","volume-title":"2016","author":"Li"},{"key":"ref31","first-page":"1","article-title":"Continuous control with deep reinforcement learning,","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lillicrap"},{"key":"ref32","first-page":"345","article-title":"Towards accurate binary convolutional neural network","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst., 2017","author":"Lin"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.l007\/978-3-319-46448-0_2"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/PACT.2017.57"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3210240.3210337"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5924"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2014.2368999"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.541"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1038\/nature14236"},{"key":"ref41","first-page":"1928","article-title":"Asynchronous methods for deep reinforcement learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Mnih"},{"key":"ref42","article-title":"MNN: A universal and efficient inference engine","author":"Jiang","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TWC.2013.103113.130470"},{"key":"ref46","first-page":"1","article-title":"Model compression via distillation and quantization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Polino"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"ref50","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref51","article-title":"Fitnets: Hints for thin deep Nets","author":"Romero"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3987"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CCBD.2016.029"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-8176-8216-3"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.446"},{"key":"ref56","article-title":"Deep learning using linear support vector machines","author":"Tang","year":"2013"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.5555\/3157096.3157329"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2534169.2486020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8485853"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2019.2893250"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS.2019.00033"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3131672.3131675"},{"key":"ref65","first-page":"1","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zagoruyko"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1800506"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_12"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3274783.3275199"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/RTAS.2018.00028"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292075"}],"container-title":["IEEE Transactions on Mobile Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/7755\/4358975\/09525229.pdf?arnumber=9525229","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,11]],"date-time":"2024-01-11T23:10:44Z","timestamp":1705014644000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9525229\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmc.2021.3107424","relation":{},"ISSN":["1536-1233","1558-0660","2161-9875"],"issn-type":[{"value":"1536-1233","type":"print"},{"value":"1558-0660","type":"electronic"},{"value":"2161-9875","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}