{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:30:21Z","timestamp":1792787421932,"version":"4.5.0"},"reference-count":174,"publisher":"Association for Computing Machinery (ACM)","issue":"5","license":[{"start":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T00:00:00Z","timestamp":1670025600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nd\/4.0\/"}],"funder":[{"name":"NSF","award":["IIS-1724331, MLWiNS-2003237, CCF-2140154, and CNS-2134567"],"award-info":[{"award-number":["IIS-1724331, MLWiNS-2003237, CCF-2140154, and CNS-2134567"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Comput. Surv."],"published-print":{"date-parts":[[2023,5,31]]},"abstract":"<jats:p>Mobile devices such as smartphones and autonomous vehicles increasingly rely on deep neural networks (DNNs) to execute complex inference tasks such as image classification and speech recognition, among others. However, continuously executing the entire DNN on mobile devices can quickly deplete their battery. Although task offloading to cloud\/edge servers may decrease the mobile device\u2019s computational burden, erratic patterns in channel quality, network, and edge server load can lead to a significant delay in task execution. Recently, approaches based on split computing (SC) have been proposed, where the DNN is split into a head and a tail model, executed respectively on the mobile device and on the edge server. Ultimately, this may reduce bandwidth usage as well as energy consumption. Another approach, called early exiting (EE), trains models to embed multiple \u201cexits\u201d earlier in the architecture, each providing increasingly higher target accuracy. Therefore, the tradeoff between accuracy and delay can be tuned according to the current conditions or application demands. In this article, we provide a comprehensive survey of the state of the art in SC and EE strategies by presenting a comparison of the most relevant approaches. We conclude the article by providing a set of compelling research challenges.<\/jats:p>","DOI":"10.1145\/3527155","type":"journal-article","created":{"date-parts":[[2022,3,31]],"date-time":"2022-03-31T08:01:16Z","timestamp":1648713676000},"page":"1-30","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":278,"title":["Split Computing and Early Exiting for Deep Learning Applications: Survey and Research Challenges"],"prefix":"10.1145","volume":"55","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5620-0760","authenticated-orcid":false,"given":"Yoshitomo","family":"Matsubara","sequence":"first","affiliation":[{"name":"University of California, Irvine, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Levorato","sequence":"additional","affiliation":[{"name":"University of California, Irvine, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Francesco","family":"Restuccia","sequence":"additional","affiliation":[{"name":"Northeastern University, Boston, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,12,3]]},"reference":[{"key":"e_1_3_2_2_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2017.1600613"},{"key":"e_1_3_2_3_2","unstructured":"arXiv preprint arXiv:2105.00591 2021 Single-training collaborative object detectors adaptive to bandwidth and computation"},{"key":"e_1_3_2_4_2","first-page":"2654","volume-title":"Neural Information Processing Systems 2014","author":"Ba Jimmy","year":"2014","unstructured":"Jimmy Ba and Rich Caruana. 2014. Do deep nets really need to be deep? In Neural Information Processing Systems 2014. 2654\u20132662."},{"key":"e_1_3_2_5_2","volume-title":"International Conference on Learning Representations","author":"Ball\u00e9 Johannes","year":"2017","unstructured":"Johannes Ball\u00e9, Valero Laparra, and Eero P. Simoncelli. 2017. End-to-end optimized image compression. In International Conference on Learning Representations."},{"key":"e_1_3_2_6_2","volume-title":"International Conference on Learning Representations","author":"Ball\u00e9 Johannes","year":"2018","unstructured":"Johannes Ball\u00e9, David Minnen, Saurabh Singh, Sung Jin Hwang, and Nick Johnston. 2018. Variational image compression with a scale hyperprior. In International Conference on Learning Representations."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFCOM.2013.6566921"},{"key":"e_1_3_2_8_2","volume-title":"Proceedings of Text Analysis Conference (TAC\u201909)","author":"Bentivogli Luisa","year":"2009","unstructured":"Luisa Bentivogli, Peter Clark, Ido Dagan, and Danilo Giampiccolo. 2009. The fifth PASCAL recognizing textual entailment challenge. In Proceedings of Text Analysis Conference (TAC\u201909)."},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/1150402.1150464"},{"key":"e_1_3_2_10_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/S17-2001"},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2019.2921977"},{"key":"e_1_3_2_12_2","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen Liang-Chieh","year":"2017","unstructured":"Liang-Chieh Chen, George Papandreou, Florian Schroff, and Hartwig Adam. 2017. Rethinking atrous convolution for semantic image segmentation. arXiv preprint arXiv:1706.05587 (2017).","journal-title":"arXiv preprint arXiv:1706.05587"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9671948"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451100"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053011"},{"key":"e_1_3_2_16_2","volume-title":"International Conference on Learning Representations","author":"Clark Kevin","year":"2019","unstructured":"Kevin Clark, Minh-Thang Luong, Quoc V. Le, and Christopher D. Manning. 2019. ELECTRA: Pre-training text encoders as discriminators rather than generators. In International Conference on Learning Representations."},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102797"},{"key":"e_1_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.5555\/1953048.2078186"},{"key":"e_1_3_2_19_2","doi-asserted-by":"publisher","DOI":"10.1007\/11736790_9"},{"key":"e_1_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/2713168.2713194"},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639344"},{"key":"e_1_3_2_22_2","first-page":"4171","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin Jacob","year":"2019","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). 4171\u20134186."},{"key":"e_1_3_2_23_2","volume-title":"Proceedings of the 3rd International Workshop on Paraphrasing (IWP\u201905)","author":"Dolan William B.","year":"2005","unstructured":"William B. Dolan and Chris Brockett. 2005. Automatically constructing a corpus of sentential paraphrases. In Proceedings of the 3rd International Workshop on Paraphrasing (IWP\u201905)."},{"key":"e_1_3_2_24_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_32"},{"key":"e_1_3_2_25_2","volume-title":"International Conference on Learning Representations","author":"Elbayad Maha","year":"2020","unstructured":"Maha Elbayad, Jiatao Gu, E. Grave, and M. Auli. 2020. Depth-adaptive transformer. In International Conference on Learning Representations."},{"key":"e_1_3_2_26_2","article-title":"JointDNN: An efficient training and inference engine for intelligent mobile cloud computing services","author":"Eshratifar Amir Erfan","year":"2019","unstructured":"Amir Erfan Eshratifar, Mohammad Saeed Abrishami, and Massoud Pedram. 2019. JointDNN: An efficient training and inference engine for intelligent mobile cloud computing services. IEEE Transactions on Mobile Computing (2019).","journal-title":"IEEE Transactions on Mobile Computing"},{"key":"e_1_3_2_27_2","first-page":"1","volume-title":"2019 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED\u201919)","author":"Eshratifar Amir Erfan","year":"2019","unstructured":"Amir Erfan Eshratifar, Amirhossein Esmaili, and Massoud Pedram. 2019. BottleNet: A deep learning architecture for intelligent mobile cloud computing services. In 2019 IEEE\/ACM International Symposium on Low Power Electronics and Design (ISLPED\u201919). 1\u20136. https:\/\/ieeexplore.ieee.org\/document\/8824955."},{"key":"e_1_3_2_28_2","unstructured":"Mark Everingham Luc Van Gool C. K. I. Williams John Winn and Andrew Zisserman. 2012. The PASCAL Visual Object Classes Challenge 2012 (VOC2012)."},{"key":"e_1_3_2_29_2","article-title":"The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results","author":"Everingham M.","unstructured":"M. Everingham, L. Van Gool, C. K. I. Williams, J. Winn, and A. Zisserman. [n.d.]. The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results. http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2007\/workshop\/index.html.","journal-title":"http:\/\/www.pascal-network.org\/challenges\/VOC\/voc2007\/workshop\/index.html"},{"key":"e_1_3_2_30_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.79"},{"issue":"1","key":"e_1_3_2_31_2","first-page":"A16177\u2013A16177","article-title":"Deep learning to detect atrial fibrillation from short noisy ECG segments measured with wireless sensors","volume":"138","author":"Gadaleta Matteo","year":"2018","unstructured":"Matteo Gadaleta, Michele Rossi, Steven R. Steinhubl, and Giorgio Quer. 2018. Deep learning to detect atrial fibrillation from short noisy ECG segments measured with wireless sensors. Circulation 138, Suppl_1 (2018), A16177\u2013A16177.","journal-title":"Circulation"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.583"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6282"},{"key":"e_1_3_2_34_2","doi-asserted-by":"publisher","DOI":"10.5555\/1654536.1654538"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11503"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E.2018.00042"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2015.2495297"},{"key":"e_1_3_2_38_2","volume-title":"Proceedings of the 2nd PASCAL Challenges Workshop on Recognising Textual Entailment","author":"Haim R. Bar","year":"2006","unstructured":"R. Bar Haim, Ido Dagan, Bill Dolan, Lisa Ferro, Danilo Giampiccolo, Bernardo Magnini, and Idan Szpektor. 2006. The second Pascal recognising textual entailment challenge. In Proceedings of the 2nd PASCAL Challenges Workshop on Recognising Textual Entailment."},{"key":"e_1_3_2_39_2","volume-title":"4th International Conference on Learning Representations","author":"Han Song","year":"2016","unstructured":"Song Han, Huizi Mao, and William J. Dally. 2016. Deep compression: Compressing deep neural networks with pruning, trained quantization and huffman coding. In 4th International Conference on Learning Representations."},{"key":"e_1_3_2_40_2","article-title":"Learning both weights and connections for efficient neural network","volume":"28","author":"Han Song","year":"2015","unstructured":"Song Han, Jeff Pool, John Tran, and William Dally. 2015. Learning both weights and connections for efficient neural network. Advances in Neural Information Processing Systems 28 (2015), 1135\u20131143.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_41_2","unstructured":"arXiv preprint arXiv:1412.5567 2014 Deep speech: Scaling up end-to-end speech recognition"},{"key":"e_1_3_2_42_2","doi-asserted-by":"publisher","DOI":"10.1038\/s41591-018-0268-3"},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"e_1_3_2_46_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"e_1_3_2_47_2","volume-title":"Deep Learning and Representation Learning Workshop: NIPS 2014","author":"Hinton Geoffrey","year":"2014","unstructured":"Geoffrey Hinton, Oriol Vinyals, and Jeff Dean. 2014. Distilling the knowledge in a neural network. In Deep Learning and Representation Learning Workshop: NIPS 2014."},{"key":"e_1_3_2_48_2","first-page":"1314","article-title":"Searching for MobileNetV3","year":"2019","unstructured":"Andrew Howard, Mark Sandler, Grace Chu, Liang-Chieh Chen, Bo Chen, Mingxing Tan, Weijun Wang, Yukun Zhu, Ruoming Pang, Vijay Vasudevan, Quoc V. Le, and Hartwig Adam. 2019. Searching for MobileNetV3. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 1314\u20131324.","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"e_1_3_2_49_2","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard Andrew G.","year":"2017","unstructured":"Andrew G. Howard, Menglong Zhu, Bo Chen, Dmitry Kalenichenko, Weijun Wang, Tobias Weyand, Marco Andreetto, and Hartwig Adam. 2017. MobileNets: Efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017).","journal-title":"arXiv preprint arXiv:1704.04861"},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1109\/IoTDI49375.2020.00023"},{"key":"e_1_3_2_51_2","volume-title":"International Conference on Learning Representations","author":"Huang Gao","year":"2018","unstructured":"Gao Huang, Danlu Chen, T. Li, Felix Wu, L. V. D. Maaten, and Kilian Q. Weinberger. 2018. Multi-scale dense networks for resource efficient image classification. In International Conference on Learning Representations."},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_3_2_53_2","first-page":"448","volume-title":"International Conference on Machine Learning","author":"Ioffe Sergey","year":"2015","unstructured":"Sergey Ioffe and Christian Szegedy. 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International Conference on Machine Learning. PMLR, 448\u2013456."},{"key":"e_1_3_2_54_2","article-title":"Packet-loss-tolerant split inference for delay-sensitive deep learning in lossy wireless networks","author":"Itahara Sohei","year":"2021","unstructured":"Sohei Itahara, Takayuki Nishio, and Koji Yamamoto. 2021. Packet-loss-tolerant split inference for delay-sensitive deep learning in lossy wireless networks. arXiv preprint arXiv:2104.13629 (2021).","journal-title":"arXiv preprint arXiv:2104.13629"},{"key":"e_1_3_2_55_2","unstructured":"Shankar Iyer Nikhil Dandekar and Korn\u00e9l Csernai. [n.d.]. First Quora Dataset Release: Question Pairs. Retrieved January 25 2021 from https:\/\/www.quora.com\/q\/quoradata\/First-Quora-Dataset-Release-Question-Pairs."},{"key":"e_1_3_2_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00286"},{"key":"e_1_3_2_57_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.adhoc.2019.101913"},{"key":"e_1_3_2_58_2","first-page":"1","volume-title":"2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC\u201920)","author":"Jankowski Mikolaj","year":"2020","unstructured":"Mikolaj Jankowski, Deniz G\u00fcnd\u00fcz, and Krystian Mikolajczyk. 2020. Joint device-edge inference over wireless links with pruning. In 2020 IEEE 21st International Workshop on Signal Processing Advances in Wireless Communications (SPAWC\u201920). IEEE, 1\u20135."},{"key":"e_1_3_2_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00154"},{"key":"e_1_3_2_60_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6311"},{"key":"e_1_3_2_61_2","doi-asserted-by":"publisher","DOI":"10.1145\/3037697.3037698"},{"key":"e_1_3_2_62_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1139"},{"key":"e_1_3_2_63_2","volume-title":"3rd International Conference on Learning Representations","author":"Kingma Diederik P.","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations."},{"key":"e_1_3_2_64_2","unstructured":"Alex Krizhevsky. 2009. Learning multiple layers of features from tiny images. (2009). http:\/\/www.cs.toronto.edu\/kriz\/cifar.html."},{"key":"e_1_3_2_65_2","first-page":"1097","volume-title":"Advances in Neural Information Processing Systems 25","author":"Krizhevsky Alex","year":"2012","unstructured":"Alex Krizhevsky, Ilya Sutskever, and Geoffrey E. Hinton. 2012. ImageNet classification with deep convolutional neural networks. In Advances in Neural Information Processing Systems 25, F. Pereira, C. J. C. Burges, L. Bottou, and K. Q. Weinberger (Eds.). 1097\u20131105."},{"key":"e_1_3_2_66_2","article-title":"Adversarial examples in the physical world","author":"Kurakin Alexey","year":"2016","unstructured":"Alexey Kurakin, Ian Goodfellow, and Samy Bengio. 2016. Adversarial examples in the physical world. arXiv preprint arXiv:1607.02533 (2016).","journal-title":"arXiv preprint arXiv:1607.02533"},{"key":"e_1_3_2_67_2","volume-title":"International Conference on Learning Representations","author":"Lan Zhenzhong","year":"2019","unstructured":"Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, and Radu Soricut. 2019. ALBERT: A lite BERT for self-supervised learning of language representations. In International Conference on Learning Representations."},{"key":"e_1_3_2_68_2","doi-asserted-by":"publisher","DOI":"10.1145\/3372224.3419194"},{"key":"e_1_3_2_69_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"e_1_3_2_71_2","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS52988.2021.9663806"},{"key":"e_1_3_2_72_2","first-page":"552","volume-title":"Proceedings of the 13th International Conference on Principles of Knowledge Representation and Reasoning","author":"Levesque Hector J.","year":"2012","unstructured":"Hector J. Levesque, Ernest Davis, and Leora Morgenstern. 2012. The Winograd schema challenge. In Proceedings of the 13th International Conference on Principles of Knowledge Representation and Reasoning. 552\u2013561."},{"key":"e_1_3_2_73_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2015.7301352"},{"key":"e_1_3_2_74_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01418-6_40"},{"key":"e_1_3_2_75_2","volume-title":"4th International Conference on Learning Representations","author":"Li Hao","year":"2016","unstructured":"Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf. 2016. Pruning filters for efficient ConvNets. In 4th International Conference on Learning Representations."},{"key":"e_1_3_2_76_2","volume-title":"5th International Conference on Learning Representations","author":"Li Hao","year":"2017","unstructured":"Hao Li, Asim Kadav, Igor Durdanovic, Hanan Samet, and Hans Peter Graf. 2017. Pruning filters for efficient ConvNets. In 5th International Conference on Learning Representations."},{"key":"e_1_3_2_77_2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.2018.1700202"},{"key":"e_1_3_2_78_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00198"},{"key":"e_1_3_2_79_2","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-432"},{"key":"e_1_3_2_80_2","first-page":"5958","volume-title":"International Conference on Machine Learning","author":"Li Zhuohan","year":"2020","unstructured":"Zhuohan Li, Eric Wallace, Sheng Shen, Kevin Lin, Kurt Keutzer, Dan Klein, and Joey Gonzalez. 2020. Train big, then compress: Rethinking model size for efficient training and inference of transformers. In International Conference on Machine Learning. PMLR, 5958\u20135968."},{"key":"e_1_3_2_81_2","unstructured":"Min Lin Qiang Chen and Shuicheng Yan. 2014. Network in network. In Second International Conference on Learning Representations . (2014)."},{"key":"e_1_3_2_82_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_83_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_3_2_84_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_85_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.537"},{"key":"e_1_3_2_86_2","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. RoBERTa: A robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019).","journal-title":"arXiv preprint arXiv:1907.11692"},{"key":"e_1_3_2_87_2","first-page":"4814","volume-title":"Findings of the Association for Computational Linguistics (ACL-IJCNLP\u201921)","author":"Liu Zejian","year":"2021","unstructured":"Zejian Liu, Fanrong Li, Gang Li, and Jian Cheng. 2021. EBERT: Efficient BERT inference with dynamic structured pruning. In Findings of the Association for Computational Linguistics (ACL-IJCNLP\u201921). 4814\u20134823."},{"key":"e_1_3_2_88_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCD.2017.49"},{"key":"e_1_3_2_89_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2017.2745201"},{"key":"e_1_3_2_90_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICC.2019.8761718"},{"key":"e_1_3_2_91_2","doi-asserted-by":"publisher","DOI":"10.1145\/3349614.3356022"},{"key":"e_1_3_2_92_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3039714"},{"key":"e_1_3_2_93_2","article-title":"BottleFit: Learning compressed representations in deep neural networks for effective and efficient split computing","author":"Matsubara Yoshitomo","year":"2022","unstructured":"Yoshitomo Matsubara, Davide Callegaro, Sameer Singh, Marco Levorato, and Francesco Restuccia. 2022. BottleFit: Learning compressed representations in deep neural networks for effective and efficient split computing. arXiv preprint arXiv:2201.02693 (2022).","journal-title":"arXiv preprint arXiv:2201.02693"},{"key":"e_1_3_2_94_2","doi-asserted-by":"publisher","DOI":"10.1145\/3410338.3412338"},{"key":"e_1_3_2_95_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412388"},{"key":"e_1_3_2_96_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401266"},{"key":"e_1_3_2_97_2","article-title":"SC2: Supervised compression for split computing","author":"Matsubara Yoshitomo","year":"2022","unstructured":"Yoshitomo Matsubara, Ruihan Yang, Marco Levorato, and Stephan Mandt. 2022. SC2: Supervised compression for split computing. arXiv preprint arXiv:2203.08875 (2022).","journal-title":"arXiv preprint arXiv:2203.08875"},{"key":"e_1_3_2_98_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00100"},{"key":"e_1_3_2_99_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5963"},{"key":"e_1_3_2_100_2","article-title":"Playing Atari with deep reinforcement learning","author":"Mnih Volodymyr","year":"2013","unstructured":"Volodymyr Mnih, Koray Kavukcuoglu, David Silver, Alex Graves, Ioannis Antonoglou, Daan Wierstra, and Martin Riedmiller. 2013. Playing Atari with deep reinforcement learning. arXiv preprint arXiv:1312.5602 (2013).","journal-title":"arXiv preprint arXiv:1312.5602"},{"key":"e_1_3_2_101_2","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"e_1_3_2_102_2","doi-asserted-by":"publisher","DOI":"10.1109\/VTC2021-Fall52928.2021.9625464"},{"key":"e_1_3_2_103_2","doi-asserted-by":"crossref","first-page":"265","DOI":"10.1109\/ISQED.2019.8697497","volume-title":"20th International Symposium on Quality Electronic Design (ISQED\u201919)","author":"Neshatpour Katayoun","year":"2019","unstructured":"Katayoun Neshatpour, Farnaz Behnia, Houman Homayoun, and Avesta Sasan. 2019. Exploiting energy-accuracy trade-off through contextual awareness in multi-stage convolutional neural networks. In 20th International Symposium on Quality Electronic Design (ISQED\u201919). 265\u2013270."},{"key":"e_1_3_2_104_2","volume-title":"NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011","author":"Netzer Yuval","unstructured":"Yuval Netzer, Tao Wang, Adam Coates, Alessandro Bissacco, Bo Wu, and Andrew Y. Ng. [n.d.]. Reading digits in natural images with unsupervised feature learning. In NIPS Workshop on Deep Learning and Unsupervised Feature Learning 2011."},{"key":"e_1_3_2_105_2","volume-title":"CoCo@ NIPS","author":"Nguyen Tri","year":"2016","unstructured":"Tri Nguyen, Mir Rosenberg, Xia Song, Jianfeng Gao, Saurabh Tiwary, Rangan Majumder, and Li Deng. 2016. MS MARCO: A human generated machine reading comprehension dataset. In CoCo@ NIPS."},{"key":"e_1_3_2_106_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2018.07.099"},{"key":"e_1_3_2_107_2","article-title":"CRIME: Input-dependent collaborative inference for recurrent neural networks","author":"Pagliari Daniele Jahier","year":"2020","unstructured":"Daniele Jahier Pagliari, Roberta Chiaro, Enrico Macii, and Massimo Poncino. 2020. CRIME: Input-dependent collaborative inference for recurrent neural networks. IEEE Transactions on Computers 70, 10 (2020), 1626\u20131639.","journal-title":"IEEE Transactions on Computers"},{"key":"e_1_3_2_108_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_2_109_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00144"},{"key":"e_1_3_2_110_2","doi-asserted-by":"publisher","DOI":"10.3390\/e24010001"},{"key":"e_1_3_2_111_2","doi-asserted-by":"publisher","DOI":"10.1145\/3234150"},{"key":"e_1_3_2_112_2","unstructured":"IEEE 2011 Workshop on Automatic Speech Recognition and Understanding 2011 The Kaldi speech recognition toolkit"},{"key":"e_1_3_2_113_2","volume-title":"CCL","author":"Qiu Y.","year":"2018","unstructured":"Y. Qiu, Hongzheng Li, Shen Li, Yingdi Jiang, Renfen Hu, and L. Yang. 2018. Revisiting correlations between intrinsic and extrinsic evaluations of word embeddings. In CCL."},{"key":"e_1_3_2_114_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"e_1_3_2_115_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1264"},{"key":"e_1_3_2_116_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.690"},{"key":"e_1_3_2_117_2","article-title":"YOLOv3: An incremental improvement","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi. 2018. YOLOv3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018).","journal-title":"arXiv preprint arXiv:1804.02767"},{"key":"e_1_3_2_118_2","first-page":"91","volume-title":"Advances in Neural Information Processing Systems","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster R-CNN: Towards real-time object detection with region proposal networks. In Advances in Neural Information Processing Systems. 91\u201399."},{"key":"e_1_3_2_119_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.001.2000243"},{"key":"e_1_3_2_120_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126289"},{"key":"e_1_3_2_121_2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_122_2","doi-asserted-by":"publisher","DOI":"10.1145\/2968456.2974004"},{"key":"e_1_3_2_123_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"e_1_3_2_124_2","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ab3985"},{"key":"e_1_3_2_125_2","doi-asserted-by":"publisher","DOI":"10.1109\/SECON52354.2021.9491600"},{"key":"e_1_3_2_126_2","volume-title":"2nd International Conference on Learning Representations","author":"Sermanet Pierre","year":"2014","unstructured":"Pierre Sermanet, David Eigen, Xiang Zhang, Micha\u00ebl Mathieu, Rob Fergus, and Yann LeCun. 2014. OverFeat: Integrated recognition, localization and detection using convolutional networks. In 2nd International Conference on Learning Representations."},{"key":"e_1_3_2_127_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops49005.2020.9145068"},{"key":"e_1_3_2_128_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"e_1_3_2_129_2","volume-title":"3rd International Conference on Learning Representations","author":"Simonyan Karen","year":"2015","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In 3rd International Conference on Learning Representations."},{"key":"e_1_3_2_130_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00214"},{"key":"e_1_3_2_131_2","first-page":"4077","volume-title":"Advances in Neural Information Processing Systems","author":"Snell Jake","year":"2017","unstructured":"Jake Snell, Kevin Swersky, and Richard Zemel. 2017. Prototypical networks for few-shot learning. In Advances in Neural Information Processing Systems. 4077\u20134087."},{"key":"e_1_3_2_132_2","first-page":"1631","volume-title":"Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing","author":"Socher Richard","year":"2013","unstructured":"Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D. Manning, Andrew Y. Ng, and Christopher Potts. 2013. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing. 1631\u20131642."},{"key":"e_1_3_2_133_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.504"},{"key":"e_1_3_2_134_2","doi-asserted-by":"publisher","DOI":"10.5555\/2627435.2670313"},{"key":"e_1_3_2_135_2","article-title":"How to train your ViT? Data, augmentation, and regularization in vision transformers","author":"Steiner Andreas","year":"2021","unstructured":"Andreas Steiner, Alexander Kolesnikov, Xiaohua Zhai, Ross Wightman, Jakob Uszkoreit, and Lucas Beyer. 2021. How to train your ViT? Data, augmentation, and regularization in vision transformers. arXiv preprint arXiv:2106.10270 (2021).","journal-title":"arXiv preprint arXiv:2106.10270"},{"key":"e_1_3_2_136_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"e_1_3_2_137_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"e_1_3_2_138_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.220"},{"key":"e_1_3_2_139_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00293"},{"key":"e_1_3_2_140_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01079"},{"key":"e_1_3_2_141_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2016.7900006"},{"key":"e_1_3_2_142_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2017.226"},{"key":"e_1_3_2_143_2","article-title":"The information bottleneck method","author":"Tishby Naftali","year":"2000","unstructured":"Naftali Tishby, Fernando C. Pereira, and William Bialek. 2000. The information bottleneck method. arXiv preprint physics\/0004057 (2000).","journal-title":"arXiv preprint physics\/0004057"},{"key":"e_1_3_2_144_2","first-page":"1","volume-title":"2015 IEEE Information Theory Workshop (ITW\u201915)","author":"Tishby Naftali","year":"2015","unstructured":"Naftali Tishby and Noga Zaslavsky. 2015. Deep learning and the information bottleneck principle. In 2015 IEEE Information Theory Workshop (ITW\u201915). IEEE, 1\u20135."},{"key":"e_1_3_2_145_2","article-title":"YOLOv5","unstructured":"Ultralytics. [n.d.]. YOLOv5. https:\/\/github.com\/ultralytics\/yolov5.","journal-title":"https:\/\/github.com\/ultralytics\/yolov5"},{"key":"e_1_3_2_146_2","first-page":"5998","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N. Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. In Advances in Neural Information Processing Systems, I. Guyon, U. V. Luxburg, S. Bengio, H. Wallach, R. Fergus, S. Vishwanathan, and R. Garnett (Eds.), Vol. 30. Curran Associates, Inc., 5998\u20136008."},{"key":"e_1_3_2_147_2","volume-title":"International Conference on Learning Representations","author":"Wang Alex","year":"2019","unstructured":"Alex Wang, Amanpreet Singh, Julian Michael, Felix Hill, Omer Levy, and Samuel R. Bowman. 2019. GLUE: A multi-task benchmark and analysis platform for natural language understanding. In International Conference on Learning Representations."},{"key":"e_1_3_2_148_2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1900140"},{"key":"e_1_3_2_149_2","doi-asserted-by":"crossref","first-page":"178","DOI":"10.1109\/SiPS47522.2019.9020551","volume-title":"2019 IEEE International Workshop on Signal Processing Systems (SiPS\u201919)","author":"Wang Meiqi","year":"2019","unstructured":"Meiqi Wang, Jianqiao Mo, Jun Lin, Zhongfeng Wang, and Li Du. 2019. DynExit: A dynamic early-exit strategy for deep residual networks. In 2019 IEEE International Workshop on Signal Processing Systems (SiPS\u201919). IEEE, 178\u2013183."},{"key":"e_1_3_2_150_2","first-page":"22","volume-title":"Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL\u201907)","author":"Wang Mengqiu","year":"2007","unstructured":"Mengqiu Wang, Noah A. Smith, and Teruko Mitamura. 2007. What is the jeopardy model? A quasi-synchronous grammar for QA. In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL\u201907). 22\u201332."},{"key":"e_1_3_2_151_2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.2979669"},{"key":"e_1_3_2_152_2","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00290"},{"key":"e_1_3_2_153_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1101"},{"key":"e_1_3_2_154_2","article-title":"Zero time waste: Recycling predictions in early exit neural networks","volume":"34","author":"Wo\u0142czyk Maciej","year":"2021","unstructured":"Maciej Wo\u0142czyk, Bartosz W\u00f3jcik, Klaudia Ba\u0142azy, Igor Podolak, Jacek Tabor, Marek \u015amieja, and Tomasz Trzcinski. 2021. Zero time waste: Recycling predictions in early exit neural networks. Advances in Neural Information Processing Systems 34 (2021).","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_155_2","first-page":"38","article-title":"Transformers: State-of-the-art natural language processing","year":"2020","unstructured":"Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Clement Delangue, Anthony Moi, Pierric Cistac, Tim Rault, Remi Louf, Morgan Funtowicz, Joe Davison, Sam Shleifer, Patrick von Platen, Clara Ma, Yacine Jernite, Julien Plu, Canwen Xu, Teven Le Scao, Sylvain Gugger, Mariama Drame, Quentin Lhoest, and Alexander Rush. 2020. Transformers: State-of-the-art natural language processing. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations. 38\u201345.","journal-title":"Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations"},{"key":"e_1_3_2_156_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.sustainlp-1.11"},{"key":"e_1_3_2_157_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.204"},{"key":"e_1_3_2_158_2","volume-title":"Computer Vision (ECCV\u201920)","author":"Xing Qunliang","year":"2020","unstructured":"Qunliang Xing, Mai Xu, Tianyi Li, and Zhenyu Guan. 2020. Early exit or not: Resource-efficient blind quality enhancement for compressed images. In Computer Vision (ECCV\u201920). Springer International Publishing."},{"key":"e_1_3_2_159_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00244"},{"key":"e_1_3_2_160_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_18"},{"key":"e_1_3_2_161_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.643"},{"key":"e_1_3_2_162_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_18"},{"key":"e_1_3_2_163_2","first-page":"10670","volume-title":"International Conference on Machine Learning","author":"Yang Yibo","year":"2020","unstructured":"Yibo Yang, Robert Bamler, and Stephan Mandt. 2020. Variational Bayesian quantization. In International Conference on Machine Learning. PMLR, 10670\u201310680."},{"key":"e_1_3_2_164_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1237"},{"key":"e_1_3_2_165_2","doi-asserted-by":"publisher","DOI":"10.1145\/3384419.3430898"},{"key":"e_1_3_2_166_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2019.05.003"},{"key":"e_1_3_2_167_2","article-title":"Understanding convolutional neural networks with information theory: An initial exploration","author":"Yu Shujian","year":"2020","unstructured":"Shujian Yu, Kristoffer Wickstr\u00f8m, Robert Jenssen, and Jos\u00e9 C. Pr\u00edncipe. 2020. Understanding convolutional neural networks with information theory: An initial exploration. IEEE Transactions on Neural Networks and Learning Systems Vol. 32, 1 (2020), 435\u2013442.","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"e_1_3_2_168_2","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.87"},{"key":"e_1_3_2_169_2","doi-asserted-by":"publisher","DOI":"10.1109\/MNET.001.1800506"},{"key":"e_1_3_2_170_2","doi-asserted-by":"publisher","DOI":"10.1109\/MCOM.2018.1701370"},{"key":"e_1_3_2_171_2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2977528"},{"key":"e_1_3_2_172_2","volume-title":"NIPS","author":"Zhang X.","year":"2015","unstructured":"X. Zhang, J. Zhao, and Y. LeCun. 2015. Character-level convolutional networks for text classification. In NIPS."},{"key":"e_1_3_2_173_2","article-title":"BERT loses patience: Fast and robust inference with early exit","volume":"33","author":"Zhou Wangchunshu","year":"2020","unstructured":"Wangchunshu Zhou, Canwen Xu, Tao Ge, Julian McAuley, Ke Xu, and Furu Wei. 2020. BERT loses patience: Fast and robust inference with early exit. Advances in Neural Information Processing Systems 33 (2020), 18330\u201318341.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_174_2","volume-title":"International Conference on Learning Representations","author":"Zoph Barret","year":"2017","unstructured":"Barret Zoph and Quoc Le. 2017. Neural architecture search with reinforcement learning. In International Conference on Learning Representations."},{"key":"e_1_3_2_175_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00907"}],"container-title":["ACM Computing Surveys"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3527155","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3527155","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3527155","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T13:51:00Z","timestamp":1750168260000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3527155"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,3]]},"references-count":174,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2023,5,31]]}},"alternative-id":["10.1145\/3527155"],"URL":"https:\/\/doi.org\/10.1145\/3527155","relation":{},"ISSN":["0360-0300","1557-7341"],"issn-type":[{"value":"0360-0300","type":"print"},{"value":"1557-7341","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,3]]},"assertion":[{"value":"2021-03-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-03-14","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-12-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}