{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T07:07:32Z","timestamp":1776236852088,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1145\/3773274.3774270","type":"proceedings-article","created":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T11:40:28Z","timestamp":1767181228000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["FakeInf: Selective Deep Neural Network Inference for Latency and Energy-Aware Model Serving Pipelines"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9540-7342","authenticated-orcid":false,"given":"Demetris","family":"Trihinas","sequence":"first","affiliation":[{"name":"Computer Science, University of Nicosia, Nicosia, Cyprus"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2711-1949","authenticated-orcid":false,"given":"Moysis","family":"Symeonides","sequence":"additional","affiliation":[{"name":"Computer Science, University of Cyprus, Nicosia, Cyprus"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9861-0872","authenticated-orcid":false,"given":"Nicolae","family":"Cleju","sequence":"additional","affiliation":[{"name":"Technical University of Iasi, Iasi, Romania"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1815-5468","authenticated-orcid":false,"given":"George","family":"Pallis","sequence":"additional","affiliation":[{"name":"Computer Science, University of Cyprus, Nicosia, Cyprus"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4350-6058","authenticated-orcid":false,"given":"Marios","family":"Dikaiakos","sequence":"additional","affiliation":[{"name":"Computer Science, University of Cyprus, Nicosia, Cyprus"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,12,31]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"crossref","unstructured":"Jari Arkko Michael Bj\u00f6rn Wolfgang John Johan Sj\u00f6berg Mattias Wildeman Gustav Wikstr\u00f6m and Peter \u00d6hl\u00e9n. 2024. Beyond Bit-Pipes\u2013New Opportunities on the 6G Platform. Ericsson Technology Review 2024 6 (2024) 2\u20138.","DOI":"10.23919\/ETR.2024.10759701"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"crossref","unstructured":"Lisa Asciak Justicia Kyeremeh Xichun Luo Asimina Kazakidi Patricia Connolly Frederic Picard Kevin O\u2019Neill Sotirios\u00a0A Tsaftaris Grant\u00a0D Stewart and Wenmiao Shu. 2025. Digital twin assisted surgery concept opportunities and challenges. npj Digital Medicine 8 1 (2025) 32.","DOI":"10.1038\/s41746-024-01413-0"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"crossref","unstructured":"Akram Aslani and Mostafa Ghobaei-Arani. 2025. Machine learning inference serving models in serverless computing: a survey. Computing 107 1 (2025) 47.","DOI":"10.1007\/s00607-024-01377-9"},{"key":"e_1_3_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS.2018.00017"},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/EuCNC\/6GSummit60053.2024.10597063"},{"key":"e_1_3_3_2_7_2","first-page":"613","volume-title":"14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17)","author":"Crankshaw Daniel","year":"2017","unstructured":"Daniel Crankshaw, Xin Wang, Guilio Zhou, Michael\u00a0J. Franklin, Joseph\u00a0E. Gonzalez, and Ion Stoica. 2017. Clipper: A Low-Latency Online Prediction Serving System. In 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI 17). USENIX Association, Boston, MA, 613\u2013627."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"publisher","unstructured":"Radosvet Desislavov Fernando Mart\u00ednez-Plumed and Jos\u00e9 Hernandez-Orallo. 2023. Trends in AI inference energy consumption: Beyond the performance-vs-parameter laws of deep learning. Sustainable Computing: Informatics and Systems 38 (2023) 100857. 10.1016\/j.suscom.2023.100857","DOI":"10.1016\/j.suscom.2023.100857"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","unstructured":"Tiago\u00a0M. Fernandez-Carames and Paula Fraga-Lamas. 2024. Forging the Industrial Metaverse for Industry 5.0: Where Extended Reality IIoT Opportunistic Edge Computing and Digital Twins Meet. IEEE Access 12 (2024) 95778\u201395819. 10.1109\/ACCESS.2024.3422109","DOI":"10.1109\/ACCESS.2024.3422109"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"crossref","unstructured":"Zhen Gao Lei Yang and Yu Dai. 2024. Large-Scale Cooperative Task Offloading and Resource Allocation in Heterogeneous MEC Systems via Multiagent Reinforcement Learning. IEEE Internet of Things Journal 11 2 (2024) 2303\u20132321.","DOI":"10.1109\/JIOT.2023.3292387"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"crossref","unstructured":"Jangho Kim Simyung Chang and Nojun Kwak. 2021. PQK: Model Compression via Pruning Quantization and Knowledge Distillation. CoRR abs\/2106.14681 (2021). arXiv:https:\/\/arXiv.org\/abs\/2106.14681https:\/\/arxiv.org\/abs\/2106.14681","DOI":"10.21437\/Interspeech.2021-248"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Khaled\u00a0B. Letaief Wei Chen Yuanming Shi Jun Zhang and Ying-Jun\u00a0Angela Zhang. 2019. The Roadmap to 6G: AI Empowered Wireless Networks. IEEE Communications Magazine 57 8 (2019) 84\u201390. 10.1109\/MCOM.2019.1900271","DOI":"10.1109\/MCOM.2019.1900271"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"Yuanqi Li Arthi Padmanabhan Pengzhan Zhao Yufei Wang Guoqing\u00a0Harry Xu and Ravi Netravali. 2020. Reducto: On-Camera Filtering for Resource-Efficient Real-Time Video Analytics(SIGCOMM \u201920). Association for Computing Machinery New York NY USA 359\u2013376. 10.1145\/3387514.3405874","DOI":"10.1145\/3387514.3405874"},{"key":"e_1_3_3_2_14_2","unstructured":"Nestor Maslej Loredana Fattorini Raymond Perrault Yolanda Gil Vanessa Parli Njenga Kariuki Emily Capstick Anka Reuel Erik Brynjolfsson John Etchemendy Katrina Ligett Terah Lyons James Manyika Juan\u00a0Carlos Niebles Yoav Shoham Russell Wald Tobi Walsh Armin Hamrah Lapo Santarlasci Julia\u00a0Betts Lotufo Alexandra Rome Andrew Shi and Sukrut Oak. 2025. Artificial Intelligence Index Report 2025. arxiv:https:\/\/arXiv.org\/abs\/2504.07139\u00a0[cs.AI] https:\/\/arxiv.org\/abs\/2504.07139"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00100"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/RTSS55097.2022.00032"},{"key":"e_1_3_3_2_17_2","unstructured":"David\u00a0A. Patterson Joseph Gonzalez Quoc\u00a0V. Le Chen Liang Lluis-Miquel Munguia Daniel Rothchild David\u00a0R. So Maud Texier and Jeff Dean. 2021. Carbon Emissions and Large Neural Network Training. CoRR abs\/2104.10350 (2021)."},{"key":"e_1_3_3_2_18_2","unstructured":"Nadav Rotem Jordan Fix Saleem Abdulrasool Garret Catron Summer Deng Roman Dzhabarov Nick Gibson James Hegeman Meghan Lele Roman Levenstein Jack Montgomery Bert Maher Satish Nadathur Jakob Olesen Jongsoo Park Artem Rakhov Misha Smelyanskiy and Man Wang. 2019. Glow: Graph Lowering Compiler Techniques for Neural Networks. arxiv:https:\/\/arXiv.org\/abs\/1805.00907\u00a0[cs.PL]"},{"key":"e_1_3_3_2_19_2","unstructured":"Veronika Samborska. 2025. Scaling up: how increasing inputs has made artificial intelligence more capable. Our World in Data (2025). https:\/\/ourworldindata.org\/scaling-up-ai."},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/3341301.3359658"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/IoTDI54339.2022.00008"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/3613424.3614261"},{"key":"e_1_3_3_2_23_2","unstructured":"Surat Teerapittayanon Bradley McDanel and H.\u00a0T. Kung. 2017. BranchyNet: Fast Inference via Early Exiting from Deep Neural Networks. CoRR abs\/1709.01686 (2017). arXiv:https:\/\/arXiv.org\/abs\/1709.01686http:\/\/arxiv.org\/abs\/1709.01686"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"crossref","unstructured":"Demetris Trihinas Panagiotis Michael and Moysis Symeonides. 2024. Evaluating DL Model Scaling Trade-Offs During Inference via an Empirical Benchmark Analysis. Future Internet 16 12 (2024) 468.","DOI":"10.3390\/fi16120468"},{"key":"e_1_3_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1109\/IC2E61754.2024.00026"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Demetris Trihinas George Pallis and Marios\u00a0D Dikaiakos. 2018. Low-cost adaptive monitoring techniques for the internet of things. IEEE Transactions on Services Computing 14 2 (2018) 487\u2013501.","DOI":"10.1109\/TSC.2018.2808956"},{"key":"e_1_3_3_2_27_2","unstructured":"Hanrui Wang Zhekai Zhang and Song Han. 2020. SpAtten: Efficient Sparse Attention Architecture with Cascade Token and Head Pruning. CoRR abs\/2012.09852 (2020). arXiv:https:\/\/arXiv.org\/abs\/2012.09852https:\/\/arxiv.org\/abs\/2012.09852"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"crossref","unstructured":"B.\u00a0P. Welford. 1962. Note on a Method for Calculating Corrected Sums of Squares and Products. Technometrics 4 3 (1962) 419\u2013420.","DOI":"10.1080\/00401706.1962.10490022"},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Minrui Xu Hongyang Du Dusit Niyato Jiawen Kang Zehui Xiong Shiwen Mao Zhu Han Abbas Jamalipour Dong\u00a0In Kim Xuemin Shen et\u00a0al. 2024. Unleashing the power of edge-cloud generative AI in mobile networks: A survey of AIGC services. IEEE Communications Surveys & Tutorials 26 2 (2024) 1127\u20131170.","DOI":"10.1109\/COMST.2024.3353265"},{"key":"e_1_3_3_2_30_2","first-page":"265","volume-title":"CLOSER","author":"Yadhav Vinay","year":"2024","unstructured":"Vinay Yadhav, Andrew Williams, Ondrej Smid, Jimmy Kj\u00e4llman, Raihan\u00a0Ul Islam, Joacim Hal\u00e9n, and Wolfgang John. 2024. Benefits of Dynamic Computational Offloading for Mobile Devices.. In CLOSER. 265\u2013276."},{"key":"e_1_3_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDCS54860.2022.00107"},{"key":"e_1_3_3_2_32_2","doi-asserted-by":"crossref","unstructured":"Zhi Zhou Xu Chen En Li Liekang Zeng Ke Luo and Junshan Zhang. 2019. Edge Intelligence: Paving the Last Mile of Artificial Intelligence With Edge Computing. Proc. IEEE 107 8 (2019) 1738\u20131762.","DOI":"10.1109\/JPROC.2019.2918951"}],"event":{"name":"UCC '25: 2025 IEEE\/ACM 18th International Conference on Utility and Cloud Computing","location":"France France","acronym":"UCC '25","sponsor":["SIGARCH ACM Special Interest Group on Computer Architecture"]},"container-title":["Proceedings of the 18th IEEE\/ACM International Conference on Utility and Cloud Computing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3773274.3774270","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,31]],"date-time":"2025-12-31T11:41:49Z","timestamp":1767181309000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3773274.3774270"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12]]},"references-count":31,"alternative-id":["10.1145\/3773274.3774270","10.1145\/3773274"],"URL":"https:\/\/doi.org\/10.1145\/3773274.3774270","relation":{},"subject":[],"published":{"date-parts":[[2025,12]]},"assertion":[{"value":"2025-12-31","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}