{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T15:30:56Z","timestamp":1775662256715,"version":"3.50.1"},"reference-count":60,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2024,11,15]],"date-time":"2024-11-15T00:00:00Z","timestamp":1731628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office","doi-asserted-by":"crossref","award":["W911NF-23-1-0088"],"award-info":[{"award-number":["W911NF-23-1-0088"]}],"id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100002341","name":"Academy of Finland","doi-asserted-by":"crossref","award":["345008"],"award-info":[{"award-number":["345008"]}],"id":[{"id":"10.13039\/501100002341","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Science Foundation","award":["2112562"],"award-info":[{"award-number":["2112562"]}]},{"name":"NSF CNS","award":["2146838"],"award-info":[{"award-number":["2146838"]}]},{"name":"NSF-AoF FAIN","award":["2132573"],"award-info":[{"award-number":["2132573"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Internet Technol."],"published-print":{"date-parts":[[2024,11,30]]},"abstract":"<jats:p>The growing number of AI-driven applications in mobile devices has led to solutions that integrate deep learning models with the available edge-cloud resources. Due to multiple benefits such as reduction in on-device energy consumption, improved latency, improved network usage, and certain privacy improvements, split learning, where deep learning models are split away from the mobile device and computed in a distributed manner, has become an extensively explored topic. Incorporating compression-aware methods (where learning adapts to compression level of the communicated data) has made split learning even more advantageous. This method could even offer a viable alternative to traditional methods, such as federated learning techniques. In this work, we develop an adaptive compression-aware split learning method (\u201cdeprune\u201d) to improve and train deep learning models so that they are much more network-efficient, which would make them ideal to deploy in weaker devices with the help of edge-cloud resources. This method is also extended (\u201cprune\u201d) to very quickly train deep learning models through a transfer learning approach, which tradesoff little accuracy for much more network-efficient inference abilities. We show that the \u201cdeprune\u201d method can reduce network usage by 4\u00d7 when compared with a split-learning approach (that does not use our method) without loss of accuracy, while also improving accuracy over compression-aware split-learning by up to 4 percent. Lastly, we show that the \u201cprune\u201d method can reduce the training time for certain models by up to 6\u00d7 without affecting the accuracy when compared against a compression-aware split-learning approach.<\/jats:p>","DOI":"10.1145\/3687471","type":"journal-article","created":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T11:13:35Z","timestamp":1723547615000},"page":"1-26","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":10,"title":["Adaptive Compression-Aware Split Learning and Inference for Enhanced Network Efficiency"],"prefix":"10.1145","volume":"24","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5607-4689","authenticated-orcid":false,"given":"Akrit","family":"Mudvari","sequence":"first","affiliation":[{"name":"Yale University, New Haven, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8843-8457","authenticated-orcid":false,"given":"Antero","family":"Vainio","sequence":"additional","affiliation":[{"name":"University of Helsinki, Helsinki, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8206-8321","authenticated-orcid":false,"given":"Iason","family":"Ofeidis","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4220-3650","authenticated-orcid":false,"given":"Sasu","family":"Tarkoma","sequence":"additional","affiliation":[{"name":"University of Helsinki, Helsinki, Finland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0932-774X","authenticated-orcid":false,"given":"Leandros","family":"Tassiulas","sequence":"additional","affiliation":[{"name":"Yale University, New Haven, United States"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,11,15]]},"reference":[{"key":"e_1_3_3_2_2","unstructured":"2019. Retrieved June 2023 from https:\/\/www.gsma.com\/futurenetworks\/wiki\/cloud-ar-vr-whitepaper"},{"key":"e_1_3_3_3_2","unstructured":"Manoj Ghuhan Arivazhagan Vinay Aggarwal Aaditya Kumar Singh and Sunav Choudhary. 2019. Federated learning with personalization layers. arXiv preprint arXiv:1912.00818 (2019)."},{"key":"e_1_3_3_4_2","doi-asserted-by":"crossref","unstructured":"Juliano S. Assine Eduardo Valle and J. C. S. Santos Filho. 2021. Single-training collaborative object detectors adaptive to bandwidth and computation. arXiv preprint arXiv:2105.00591 (2021).","DOI":"10.1109\/ICASSP43922.2022.9746043"},{"key":"e_1_3_3_5_2","first-page":"8532","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Carreira-Perpin\u00e1n Miguel A.","year":"2018","unstructured":"Miguel A. Carreira-Perpin\u00e1n and Yerlan Idelbayev. 2018. \u201cLearning-compression\u201d algorithms for neural net pruning. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 8532\u20138541."},{"key":"e_1_3_3_6_2","first-page":"215","volume-title":"Proceedings of the 14th International Conference on Artificial Intelligence and Statistics","author":"Coates Adam","year":"2011","unstructured":"Adam Coates, Andrew Ng, and Honglak Lee. 2011. An analysis of single-layer networks in unsupervised feature learning. In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. JMLR Workshop and Conference Proceedings, 215\u2013223."},{"key":"e_1_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/ISLPED.2019.8824955"},{"key":"e_1_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2961959"},{"key":"e_1_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.3048613"},{"key":"e_1_3_3_10_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2437384"},{"key":"e_1_3_3_11_2","unstructured":"Song Han Huizi Mao and William J. Dally. 2015. Deep compression: Compressing deep neural networks with pruning trained quantization and huffman coding. arXiv preprint arXiv:1510.00149 (2015)."},{"key":"e_1_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/2906388.2906396"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.155"},{"key":"e_1_3_3_15_2","doi-asserted-by":"crossref","unstructured":"Geoffrey Hinton Li Deng Dong Yu George E. Dahl Abdel-rahman Mohamed Navdeep Jaitly Andrew Senior Vincent Vanhoucke Patrick Nguyen Tara N. Sainath and Brian Kingsbury. 2012. Deep neural networks for acoustic modeling in speech recognition: The shared views of four research groups. IEEE Signal Processing Magazine 29 6 (2012) 82\u201397.","DOI":"10.1109\/MSP.2012.2205597"},{"key":"e_1_3_3_16_2","unstructured":"Hengyuan Hu Rui Peng Yu-Wing Tai and Chi-Keung Tang. 2016. Network trimming: A data-driven neuron pruning approach towards efficient deep architectures. arXiv preprint arXiv:1607.03250 (2016)."},{"key":"e_1_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/WCNC49053.2021.9417376"},{"key":"e_1_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS.2018.00154"},{"key":"e_1_3_3_19_2","doi-asserted-by":"publisher","unstructured":"Xiaoqi Jiao Yichun Yin Lifeng Shang Xin Jiang Xiao Chen Linlin Li Fang Wang and Qun Liu. 2020. TinyBERT: Distilling BERT for natural language understanding. In Findings of the Association for Computational Linguistics: EMNLP 2020. Association for Computational Linguistics Online 4163\u20134174. 10.18653\/v1\/2020.findingsemnlp.372","DOI":"10.18653\/v1\/2020.findingsemnlp.372"},{"key":"e_1_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3093337.3037698"},{"key":"e_1_3_3_21_2","unstructured":"Yong-Deok Kim Eunhyeok Park Sungjoo Yoo Taelim Choi Lu Yang and Dongjun Shin. 2015. Compression of deep convolutional neural networks for fast and low power mobile applications. arXiv preprint arXiv:1511.06530 (2015)."},{"key":"e_1_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639121"},{"key":"e_1_3_3_23_2","unstructured":"A. Krizhevsky. 2009. Learning multiple layers of features from tiny images. Master\u2019s thesis University of Toronto (2009)."},{"key":"e_1_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_3_3_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2018.8486241"},{"key":"e_1_3_3_26_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"e_1_3_3_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3106401"},{"key":"e_1_3_3_28_2","doi-asserted-by":"crossref","unstructured":"Hadi Tabatabaee Malazi Saqib Rasool Chaudhry Aqeel Kazmi Andrei Palade Christian Cabrera Gary White and Siobh\u00e1n Clarke. 2022. Dynamic service placement in multi-access edge computing: A systematic literature review. IEEE Access 10 (March 2022) 32639\u201332688.","DOI":"10.1109\/ACCESS.2022.3160738"},{"key":"e_1_3_3_29_2","doi-asserted-by":"publisher","DOI":"10.1109\/WoWMoM54355.2022.00032"},{"key":"e_1_3_3_30_2","doi-asserted-by":"crossref","unstructured":"Yoshitomo Matsubara and Marco Levorato. 2020. Split computing for complex object detectors: Challenges and preliminary results. In Proceedings of the 4th International Workshop on Embedded and Mobile Deep Learning. 7\u201312.","DOI":"10.1145\/3410338.3412338"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412388"},{"key":"e_1_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNSM.2023.3331755"},{"key":"e_1_3_3_33_2","unstructured":"Tomas Mikolov Ilya Sutskever Kai Chen Greg S. Corrado and Jeff Dean. 2013. Distributed representations of words and phrases and their compositionality. In Advances in Neural Information Processing Systems C. J. Burges L. Bottou M. Welling Z. Ghahramani and K. Q. Weinberger (Eds.). Vol. 26. Curran Associates Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2013\/file\/9aa42b31882ec039965f3c4923ce901b-Paper.pdf"},{"key":"e_1_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01152"},{"key":"e_1_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.246"},{"key":"e_1_3_3_36_2","article-title":"Artificial intelligence and climate change: Ethical issues","author":"Nordgren Anders","year":"2022","unstructured":"Anders Nordgren. 2022. Artificial intelligence and climate change: Ethical issues. Journal of Information, Communication and Ethics in Society 21, 1 (2022), 1\u201315.","journal-title":"Journal of Information, Communication and Ethics in Society"},{"key":"e_1_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM.2019.8737449"},{"key":"e_1_3_3_38_2","first-page":"5113","volume-title":"Proceedings of the International Conference on Machine Learning","author":"Peng Hanyu","year":"2019","unstructured":"Hanyu Peng, Jiaxiang Wu, Shifeng Chen, and Junzhou Huang. 2019. Collaborative channel pruning for deep networks. In Proceedings of the International Conference on Machine Learning. PMLR, 5113\u20135122."},{"key":"e_1_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397166.3409149"},{"key":"e_1_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/TNET.2020.2980175"},{"key":"e_1_3_3_41_2","unstructured":"Alec Radford Karthik Narasimhan Tim Salimans and Ilya Sutskever. 2018. Improving language understanding by generative pre-training. OpenAI (2018). https:\/\/cdn.openai.com\/research-covers\/language-unsupervised\/language_understanding_paper.pdf. Accessed: June 2023."},{"key":"e_1_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_32"},{"key":"e_1_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"e_1_3_3_44_2","volume-title":"Artificial Intelligence (AI) Market Size, Growth, Report 2022-2030","author":"Research Precedence","year":"2023","unstructured":"Precedence Research. 2023. Artificial Intelligence (AI) Market Size, Growth, Report 2022-2030. Retrieved April 2024 from https:\/\/www.precedenceresearch.com\/artificial-intelligence-market"},{"key":"e_1_3_3_45_2","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein Alexander C. Berg and Li Fei-Fei. 2015. Imagenet large scale visual recognition challenge. International Journal of Computer Vision 115 3 (Dec 2015) 211\u2013252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_3_46_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2022.109380"},{"key":"e_1_3_3_47_2","doi-asserted-by":"publisher","unstructured":"Eric Samikwa Antonio Di Maio and Torsten Braun. 2024. DISNET: Distributed micro-split deep learning in heterogeneous dynamic IoT. IEEE Internet of Things Journal 11 4 (2024) 6199\u20136216. 10.1109\/JIOT.2023.3313514","DOI":"10.1109\/JIOT.2023.3313514"},{"key":"e_1_3_3_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCWorkshops49005.2020.9145068"},{"key":"e_1_3_3_49_2","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOMWKSHPS47286.2019.9093772"},{"key":"e_1_3_3_50_2","unstructured":"K. Simonyan and A. Zisserman. 2015. Very deep convolutional networks for large-scale image recognition. In 3rd International Conference on Learning Representations (ICLR\u201915). Computational and Biological Learning Society."},{"key":"e_1_3_3_51_2","unstructured":"Abhishek Singh Praneeth Vepakomma Otkrist Gupta and Ramesh Raskar. 2019. Detailed comparison of communication efficiency of split learning and federated learning. arXiv preprint arXiv:1909.09145 (2019)."},{"key":"e_1_3_3_52_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMST.2021.3101460"},{"key":"e_1_3_3_53_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i8.20825"},{"key":"e_1_3_3_54_2","doi-asserted-by":"crossref","unstructured":"Chandra Thapa M. A. P. Chamikara and Seyit A. Camtepe. 2021. Advancements of federated learning towards privacy preservation: From federated learning to split learning. In Federated Learning Systems. Studies in Computational Intelligence Vol. 965. Springer 79\u2013109. Published in June 2021.","DOI":"10.1007\/978-3-030-70604-3_4"},{"key":"e_1_3_3_55_2","doi-asserted-by":"crossref","unstructured":"Manas Wadhwa Gagan Raj Gupta Ashutosh Sahu Rahul Saini and Vidhi Mittal. 2023. PFSL: Personalized & fair split learning with data & label privacy for thin clients. In 2023 IEEE\/ACM 23rd International Symposium on Cluster Cloud and Internet Computing (CCGrid). IEEE 377\u2013390.","DOI":"10.1109\/CCGrid57682.2023.00043"},{"key":"e_1_3_3_56_2","doi-asserted-by":"publisher","DOI":"10.1109\/CRV.2018.00023"},{"key":"e_1_3_3_57_2","doi-asserted-by":"crossref","unstructured":"Jian Xue Jinyu Li Dong Yu Mike Seltzer and Yifan Gong. 2014. Singular value decomposition based low-footprint speaker adaptation and personalization for deep neural network. In IEEE 6359\u20136363.","DOI":"10.1109\/ICASSP.2014.6854828"},{"key":"e_1_3_3_58_2","unstructured":"Xin Yang Jiankai Sun Yuanshun Yao Junyuan Xie and Chong Wang. 2022. Differentially private label protection in split learning. arXiv preprint arXiv:2203.02073 (2022)."},{"key":"e_1_3_3_59_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM54844.2022.00074"},{"key":"e_1_3_3_60_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00289"},{"key":"e_1_3_3_61_2","unstructured":"Ligeng Zhu Zhijian Liu and Song Han. 2019. Deep Leakage from Gradients. In Advances in Neural Information Processing Systems H. Wallach H. Larochelle A. Beygelzimer F. d\u2019Alch\u00e9-Buc E. Fox and R. Garnett (Eds.). Vol. 32. Curran Associates Inc. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2019\/file\/60a6c4002cc7b29142def8871531281a-Paper.pdf"}],"container-title":["ACM Transactions on Internet Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3687471","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3687471","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:05:59Z","timestamp":1750291559000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3687471"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,15]]},"references-count":60,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,11,30]]}},"alternative-id":["10.1145\/3687471"],"URL":"https:\/\/doi.org\/10.1145\/3687471","relation":{},"ISSN":["1533-5399","1557-6051"],"issn-type":[{"value":"1533-5399","type":"print"},{"value":"1557-6051","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,15]]},"assertion":[{"value":"2024-01-10","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-07-18","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-11-15","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}