{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:37:45Z","timestamp":1784399865117,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":86,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,9,18]],"date-time":"2020-09-18T00:00:00Z","timestamp":1600387200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,9,21]]},"DOI":"10.1145\/3372224.3419194","type":"proceedings-article","created":{"date-parts":[[2020,9,19]],"date-time":"2020-09-19T02:16:16Z","timestamp":1600481776000},"page":"1-15","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":281,"title":["SPINN"],"prefix":"10.1145","author":[{"given":"Stefanos","family":"Laskaridis","sequence":"first","affiliation":[{"name":"University of Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stylianos I.","family":"Venieris","sequence":"additional","affiliation":[{"name":"University of Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mario","family":"Almeida","sequence":"additional","affiliation":[{"name":"University of Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ilias","family":"Leontiadis","sequence":"additional","affiliation":[{"name":"University of Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicholas D.","family":"Lane","sequence":"additional","affiliation":[{"name":"University of Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2020,9,18]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (OSDI). 265--283","author":"Abadi Mart\u00edn","year":"2016"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","volume-title":"EmBench: Quantifying Performance Variations of Deep Neural Networks Across Modern Commodity Devices. In The 3rd International Workshop on Deep Learning for Mobile Systems and Applications (EMDL)","author":"Almeida Mario","DOI":"10.1145\/3325413.3329793"},{"key":"e_1_3_2_1_3_1","volume-title":"Amazon Inferentia ML Chip. https:\/\/aws.amazon.com\/machine-learning\/inferentia\/. [Retrieved","year":"2020"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3301418.3313946"},{"key":"e_1_3_2_1_5_1","volume-title":"AWS Flap Detector: An Efficient Way to Detect Flapping Auto Scaling Groups on AWS Cloud","author":"Chandrasekar D."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071131"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/MM.2018.022071131"},{"key":"e_1_3_2_1_8_1","unstructured":"A. E. Eshratifar M. S. Abrishami and M. Pedram. 2019. JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services. IEEE Transactions on Mobile Computing (TMC) (2019).  A. E. Eshratifar M. S. Abrishami and M. Pedram. 2019. JointDNN: An Efficient Training and Inference Engine for Intelligent Mobile Cloud Computing Services. IEEE Transactions on Mobile Computing (TMC) (2019)."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3241539.3241559"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1167\/9.8.1037"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2926040"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/SC.2018.00069"},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML). 1321--1330","author":"Guo Chuan"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2017.2705069"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/990064.990068"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2808319"},{"key":"e_1_3_2_1_17_1","volume-title":"Trained Quantization and Huffman Coding. International Conference on Learning Representations (ICLR)","author":"Han Song","year":"2016"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/2906388.2906396"},{"key":"e_1_3_2_1_19_1","volume-title":"2018 IEEE International Symposium on High Performance Computer Architecture (HPCA). 620--629","author":"Hazelwood K."},{"key":"e_1_3_2_1_20_1","volume-title":"Deep Residual Learning for Image Recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770--778","author":"He K","year":"2016"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the 12th USENIX Conference on Operating Systems Design and Implementation (OSDI). USENIX Association, 269--286","author":"Hsieh Kevin","year":"2018"},{"key":"e_1_3_2_1_22_1","volume-title":"Dynamic Adaptive DNN Surgery for Inference Acceleration on the Edge. In IEEE INFOCOM 2019 - IEEE Conference on Computer Communications. 1423--1431","author":"Hu C."},{"key":"e_1_3_2_1_23_1","volume-title":"Multi-Scale Dense Networks for Resource Efficient Image Classification. In International Conference on Learning Representations (ICLR).","author":"Huang Gao"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.5555\/3122009.3242044"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00447"},{"key":"e_1_3_2_1_26_1","unstructured":"UK ISPs. 2020. 4G Mobile Network Experience Report. https:\/\/www.opensignal.com\/reports\/2019\/04\/uk\/mobile-network-experience.  UK ISPs. 2020. 4G Mobile Network Experience Report. https:\/\/www.opensignal.com\/reports\/2019\/04\/uk\/mobile-network-experience."},{"key":"e_1_3_2_1_27_1","unstructured":"UK ISPs. 2020. 5G Mobile Network Report. https:\/\/www.opensignal.com\/2020\/02\/20\/how-att-sprint-t-mobile-and-verizon-differ-in-their-early-5g-approach.  UK ISPs. 2020. 5G Mobile Network Report. https:\/\/www.opensignal.com\/2020\/02\/20\/how-att-sprint-t-mobile-and-verizon-differ-in-their-early-5g-approach."},{"key":"e_1_3_2_1_28_1","volume-title":"Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2704--2713","author":"Jacob B."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3267809.3267828"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3173162.3173205"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/HOTCHIPS.2014.7478821"},{"key":"e_1_3_2_1_32_1","volume-title":"Proceedings of the 44th Annual International Symposium on Computer Architecture (ISCA). ACM, 1--12","author":"Norman"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.14778\/3137628.3137664"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037698"},{"key":"e_1_3_2_1_35_1","volume-title":"Shallow-Deep Networks: Understanding and Mitigating Network Overthinking. In International Conference on Machine Learning (ICML). 3301--3310","author":"Kaya Yigitcan","year":"2019"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1145\/3302424.3303950"},{"key":"e_1_3_2_1_37_1","volume-title":"IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 1--9.","author":"Kouris A."},{"key":"e_1_3_2_1_38_1","volume-title":"CascadeCNN: Pushing the Performance Limits of Quantisation in Convolutional Neural Networks. In 2018 28th International Conference on Field Programmable Logic and Applications (FPL). 155--1557","author":"Kouris A."},{"key":"e_1_3_2_1_39_1","volume-title":"Automation Test in Europe Conference Exhibition (DATE). 1656--1661","author":"Kouris A."},{"key":"e_1_3_2_1_40_1","volume-title":"Automation Test in Europe Conference Exhibition (DATE). 1351--1356","author":"Kozyrakis C.","year":"2013"},{"key":"e_1_3_2_1_41_1","unstructured":"Alex Krizhevsky Geoffrey Hinton etal 2009. Learning multiple layers of features from tiny images. Technical Report.  Alex Krizhevsky Geoffrey Hinton et al. 2009. Learning multiple layers of features from tiny images. Technical Report."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/MCE.2018.2828440"},{"key":"e_1_3_2_1_43_1","volume-title":"DeepX: A Software Accelerator for Low-Power Deep Learning Inference on Mobile Devices. In 2016 15th ACM\/IEEE International Conference on Information Processing in Sensor Networks (IPSN). 1--12","author":"Lane N. D."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","volume-title":"HAPI: Hardware-Aware Progressive Inference. In IEEE\/ACM International Conference on Computer-Aided Design (ICCAD).","author":"Laskaridis Stefanos","DOI":"10.1145\/3400302.3415698"},{"key":"e_1_3_2_1_45_1","volume-title":"MobiSR: Efficient On-Device Super-Resolution Through Heterogeneous Mobile Processors. In The 25th Annual International Conference on Mobile Computing and Networking (MobiCom).","author":"Lee Royson"},{"key":"e_1_3_2_1_46_1","volume-title":"Edge AI: On-Demand Accelerating Deep Neural Network Inference via Edge Computing","author":"Li E.","year":"2020"},{"key":"e_1_3_2_1_47_1","volume-title":"Proceedings of the International Conference on Parallel and Distributed Systems (ICPADS). 671--678","author":"Li Hongshan","year":"2019"},{"key":"e_1_3_2_1_48_1","volume-title":"Improved Techniques for Training Adaptive Deep Networks. In International Conference on Computer Vision (ICCV).","author":"Li Hao","year":"2019"},{"key":"e_1_3_2_1_49_1","volume-title":"Optimizing CNN Model Inference on CPUs. In 2019 USENIX Annual Technical Conference (USENIX ATC 19)","author":"Liu Yizhi","year":"2019"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.23919\/DATE.2017.7927211"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCAD.2017.8203852"},{"key":"e_1_3_2_1_52_1","volume-title":"Survey of multi-objective optimization methods for engineering. Structural and multidisciplinary optimization 26, 6","author":"Timothy Marler R","year":"2004"},{"key":"e_1_3_2_1_53_1","volume-title":"GPU Technology Conference.","author":"Migacz Szymon","year":"2017"},{"key":"e_1_3_2_1_54_1","volume-title":"International Conference on Machine Learning (ICML). 807--814","author":"Nair Vinod","year":"2010"},{"key":"e_1_3_2_1_55_1","volume-title":"Nervana's Early Exit Inference. https:\/\/nervanasystems.github.io\/distiller\/algo_earlyexit.html. [Retrieved","author":"Nervana Intel","year":"2020"},{"key":"e_1_3_2_1_56_1","volume-title":"Characterizing Sources of Ineffectual Computations in Deep Learning Networks. In IEEE International Symposium on Performance Analysis of Systems and Software (ISPASS). 165--176","author":"Nikoli\u0107 Milo\u0161","year":"2019"},{"key":"e_1_3_2_1_57_1","volume-title":"SOCK: Rapid Task Provisioning with Serverless-Optimized Containers. In 2018 USENIX Annual Technical Conference (USENIX ATC 18)","author":"Oakes Edward","year":"2018"},{"key":"e_1_3_2_1_58_1","volume-title":"PyTorch: An Imperative Style","author":"Paszke Adam"},{"key":"e_1_3_2_1_59_1","volume-title":"Proceedings of the 34th International Conference on Machine Learning (ICML)","volume":"70","author":"Raghu Maithra","year":"2017"},{"key":"e_1_3_2_1_60_1","volume-title":"Compressing DMA Engine: Leveraging Activation Sparsity for Training Deep Neural Networks. In 2018 IEEE International Symposium on High Performance Computer Architecture (HPCA). 78--91","author":"Rhu M."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/MICRO.2016.7783720"},{"key":"e_1_3_2_1_63_1","volume-title":"Very Deep Convolutional Networks for Large-Scale Image Recognition. In International Conference on Learning Representations (ICLR).","author":"Simonyan K."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2016.11.027"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.1145\/3297858.3304072"},{"key":"e_1_3_2_1_66_1","volume-title":"2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS). 4241--4247","author":"Smolyanskiy N."},{"key":"e_1_3_2_1_67_1","volume-title":"And the Bit Goes Down: Revisiting the Quantization of Neural Networks. In International Conference on Learning Representations (ICLR).","author":"Stock Pierre","year":"2020"},{"key":"e_1_3_2_1_68_1","volume-title":"Inception-ResNet and the Impact of Residual Connections on Learning. In AAAI Conference on Artificial Intelligence.","author":"Szegedy Christian","year":"2017"},{"key":"e_1_3_2_1_69_1","volume-title":"Rethinking the Inception Architecture for Computer Vision. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2818--2826","author":"Szegedy C."},{"key":"e_1_3_2_1_70_1","unstructured":"Willy Tarreau et al. 2012. HAProxy-the reliable high-performance TCP\/HTTP load balancer.  Willy Tarreau et al. 2012. HAProxy-the reliable high-performance TCP\/HTTP load balancer."},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"publisher","DOI":"10.1145\/3211332.3211336"},{"key":"e_1_3_2_1_72_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"e_1_3_2_1_73_1","volume-title":"2017 IEEE 37th International Conference on Distributed Computing Systems (ICDCS). 328--339","author":"Teerapittayanon S."},{"key":"e_1_3_2_1_74_1","volume-title":"Tenstorrent's Grayskull AI Chip. https:\/\/www.tenstorrent.com\/technology\/. [Retrieved","year":"2020"},{"key":"e_1_3_2_1_75_1","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2844093"},{"key":"e_1_3_2_1_76_1","doi-asserted-by":"publisher","DOI":"10.1145\/2984356.2988518"},{"key":"e_1_3_2_1_77_1","volume-title":"Peeking Behind the Curtains of Serverless Platforms. In 2018 USENIX Annual Technical Conference (USENIX ATC 18)","author":"Wang Liang","year":"2018"},{"key":"e_1_3_2_1_78_1","doi-asserted-by":"crossref","unstructured":"S. Wang A. Pathania and T. Mitra. 2020. Neural Network Inference on Mobile SoCs. IEEE Design Test (2020).  S. Wang A. Pathania and T. Mitra. 2020. Neural Network Inference on Mobile SoCs. IEEE Design Test (2020).","DOI":"10.1109\/MDAT.2020.2968258"},{"key":"e_1_3_2_1_79_1","doi-asserted-by":"publisher","DOI":"10.1145\/3061639.3062207"},{"key":"e_1_3_2_1_80_1","volume-title":"2019 IEEE International Symposium on High Performance Computer Architecture (HPCA). 331--344","author":"Wu C."},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"e_1_3_2_1_82_1","unstructured":"Bing Xu Naiyan Wang Tianqi Chen and Mu Li. 2015. Empirical Evaluation of Rectified Activations in Convolutional Network. In CoRR.  Bing Xu Naiyan Wang Tianqi Chen and Mu Li. 2015. Empirical Evaluation of Rectified Activations in Convolutional Network. In CoRR."},{"key":"e_1_3_2_1_83_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00381"},{"key":"e_1_3_2_1_84_1","volume-title":"SCAN: A Scalable Neural Networks Framework Towards Compact and Efficient Models. In Advances in Neural Information Processing Systems (NeurIPS).","author":"Zhang Linfeng","year":"2019"},{"key":"e_1_3_2_1_85_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCAD.2018.2858384"},{"key":"e_1_3_2_1_86_1","volume-title":"Incremental Network Quantization: Towards Lossless CNNs with Low-Precision Weights. In International Conference on Learning Representations (ICLR).","author":"Zhou Aojun","year":"2017"}],"event":{"name":"MobiCom '20: The 26th Annual International Conference on Mobile Computing and Networking","location":"London United Kingdom","acronym":"MobiCom '20","sponsor":["SIGMOBILE ACM Special Interest Group on Mobility of Systems, Users, Data and Computing"]},"container-title":["Proceedings of the 26th Annual International Conference on Mobile Computing and Networking"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3372224.3419194","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3372224.3419194","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T21:32:10Z","timestamp":1750195930000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3372224.3419194"}},"subtitle":["synergistic progressive inference of neural networks over device and cloud"],"short-title":[],"issued":{"date-parts":[[2020,9,18]]},"references-count":86,"alternative-id":["10.1145\/3372224.3419194","10.1145\/3372224"],"URL":"https:\/\/doi.org\/10.1145\/3372224.3419194","relation":{},"subject":[],"published":{"date-parts":[[2020,9,18]]},"assertion":[{"value":"2020-09-18","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}