{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T22:39:15Z","timestamp":1781563155321,"version":"3.54.5"},"reference-count":154,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T00:00:00Z","timestamp":1747180800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Comput. Sci."],"abstract":"<jats:p>Edge computing has emerged as a vital paradigm for processing data near its source, significantly reducing latency and improving data privacy. Simultaneously, large language models (LLMs) such as GPT-4 and BERT have showcased impressive capabilities in data analysis, natural language processing, and decision-making. This survey explores the intersection of these two domains, specifically focusing on the adaptation and optimization of LLMs for data analysis tasks in edge computing environments. We examine the challenges faced by resource-constrained edge devices, including limited computational power, energy efficiency, and network reliability. Additionally, we discuss how recent advancements in model compression, distributed learning, and edge-friendly architectures are addressing these challenges. Through a comprehensive review of the current research, we analyze the applications, challenges, and future directions of deploying LLMs in edge computing. This analysis aims to facilitate intelligent data analysis across various industries, including healthcare, smart cities, and the internet of things.<\/jats:p>","DOI":"10.3389\/fcomp.2025.1538277","type":"journal-article","created":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T05:38:45Z","timestamp":1747201125000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":11,"title":["Intelligent data analysis in edge computing with large language models: applications, challenges, and future directions"],"prefix":"10.3389","volume":"7","author":[{"given":"Xuanzheng","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhipeng","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xingfei","family":"Sui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,5,14]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"450","DOI":"10.3390\/s22020450","article-title":"Federated learning in edge computing: a systematic survey","volume":"22","author":"Abreha","year":"2022","journal-title":"Sensors"},{"key":"B2","first-page":"7028","article-title":"\u201cDesign and optimization of a tensorflow lite deep learning neural network for human activity recognition on a smartphone,\u201d","author":"Adi","year":"2021","journal-title":"2021 43rd Annual International Conference of the IEEE Engineering in Medicine"},{"key":"B3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2410.17397","article-title":"Quantum large language models via tensor network disentanglers","author":"Aizpurua","year":"2024","journal-title":"arXiv"},{"key":"B4","first-page":"2667","article-title":"\u201cSearching for efficient neural architectures for on-device ml on edge TPUS,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Akin","year":"2022"},{"key":"B5","doi-asserted-by":"publisher","first-page":"5206","DOI":"10.3390\/s23115206","article-title":"Integration of iot-enabled technologies and artificial intelligence (ai) for smart city scenario: recent advancements and future trends","volume":"23","author":"Alahi","year":"2023","journal-title":"Sensors"},{"key":"B6","doi-asserted-by":"publisher","first-page":"18706","DOI":"10.1109\/ACCESS.2021.3053233","article-title":"Multi-access edge computing architecture, data security and privacy: A review","volume":"9","author":"Ali","year":"2021","journal-title":"IEEE Access"},{"key":"B7","doi-asserted-by":"publisher","first-page":"4004","DOI":"10.1109\/JIOT.2020.3015432","article-title":"A survey on security and privacy issues in edge-computing-assisted internet of things","volume":"8","author":"Alwarafy","year":"2021","journal-title":"IEEE Internet Things J"},{"key":"B8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3005348","article-title":"Structured pruning of deep convolutional neural networks","volume":"13","author":"Anwar","year":"2017","journal-title":"ACM J. Emerg. Technol. Comp. Syst"},{"key":"B9","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1146\/annurev-med-052422-020437","article-title":"Wearable devices: implications for precision medicine and the future of health care","volume":"75","author":"Babu","year":"2024","journal-title":"Annu. Rev. Med"},{"key":"B10","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1145\/3366750.3366751","article-title":"\u201cUsing distillation to improve network performance after pruning and quantization,\u201d","volume-title":"Proceedings of the 2019 2nd International Conference on Machine Learning and Machine Intelligence, MLMI '19","author":"Bao","year":"2019"},{"key":"B11","doi-asserted-by":"publisher","first-page":"82108","DOI":"10.1109\/ACCESS.2020.2988935","article-title":"Edge computing-based localization technique to detecting behavior of dementia","volume":"8","author":"Barua","year":"2020","journal-title":"IEEE Access"},{"key":"B12","doi-asserted-by":"publisher","first-page":"102217","DOI":"10.1016\/j.inffus.2023.102217","article-title":"A survey of multimodal hybrid deep learning for computer vision: Architectures, applications, trends, and challenges","volume":"105","author":"Bayoudh","year":"2024","journal-title":"Inform. Fusion"},{"key":"B13","doi-asserted-by":"publisher","first-page":"7806","DOI":"10.1109\/TNNLS.2024.3430028","article-title":"On-device deep learning: survey on techniques improving energy efficiency of DNNS","volume":"36","author":"Boumendil","year":"2025","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2005.14165","article-title":"Language models are few-shot learners","author":"Brown","year":"2020","journal-title":"arXiv"},{"key":"B15","article-title":"\u201cDifferentially private secure multi-party computation for federated learning in financial applications,\u201d","volume-title":"Proceedings of the First ACM International Conference on AI in Finance, ICAIF '20","author":"Byrd","year":"2021"},{"key":"B16","doi-asserted-by":"publisher","first-page":"85714","DOI":"10.1109\/ACCESS.2020.2991734","article-title":"An overview on edge computing research","volume":"8","author":"Cao","year":"2020","journal-title":"IEEE Access"},{"key":"B17","doi-asserted-by":"crossref","DOI":"10.1145\/3274783.3274834","article-title":"\u201cMarvel: Enabling mobile augmented reality with low energy and low latency,\u201d","volume-title":"Proceedings of the 16th ACM Conference on Embedded Networked Sensor Systems, SenSys '18","author":"Chen","year":"2018"},{"key":"B18","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1145\/3451211","article-title":"Quantization of deep neural networks for accurate edge computing","volume":"17","author":"Chen","year":"","journal-title":"ACM J. Emerg. Technol. Comp. Syst"},{"key":"B19","first-page":"5350","article-title":"\u201cTowards mixed-precision quantization of neural networks via constrained optimization,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Chen","year":""},{"key":"B20","doi-asserted-by":"publisher","first-page":"830","DOI":"10.1109\/TSUSC.2024.3353176","article-title":"Advancements in accelerating deep neural network inference on aiot devices: A survey","volume":"9","author":"Cheng","year":"2024","journal-title":"IEEE Trans. Sustain. Comput."},{"key":"B21","doi-asserted-by":"publisher","first-page":"14575","DOI":"10.1109\/TMC.2024.3452502","article-title":"Task offloading via prioritized experience-based double dueling dqn in edge-assisted IIoT","volume":"23","author":"Chi","year":"2024","journal-title":"IEEE Trans. Mobile Comp"},{"key":"B22","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/IJCNN52387.2021.9534111","article-title":"\u201cSpatio-temporal pruning and quantization for low-latency spiking neural networks,\u201d","volume-title":"2021 International Joint Conference on Neural Networks (IJCNN)","author":"Chowdhury","year":"2021"},{"key":"B23","doi-asserted-by":"publisher","first-page":"2166","DOI":"10.1109\/TNSM.2020.3023305","article-title":"A decentralized framework for serverless edge computing in the internet of things","volume":"18","author":"Cicconetti","year":"2021","journal-title":"IEEE Trans. Netw. Serv. Managem"},{"key":"B24","doi-asserted-by":"publisher","first-page":"100520","DOI":"10.1016\/j.suscom.2021.100520","article-title":"Utilizing cloud FPGAs towards the open neural network standard","volume":"30","author":"Danopoulos","year":"2021","journal-title":"Sustain. Comp.: Inform. Syst"},{"key":"B25","doi-asserted-by":"publisher","first-page":"9225","DOI":"10.3390\/s23229225","article-title":"LLM Multimodal Traffic Accident Forecasting","volume":"23","author":"de Zarz\u00e0","year":"2023","journal-title":"Sensors"},{"key":"B26","doi-asserted-by":"publisher","first-page":"7457","DOI":"10.1109\/JIOT.2020.2984887","article-title":"Edge intelligence: The confluence of edge computing and artificial intelligence","volume":"7","author":"Deng","year":"2020","journal-title":"IEEE Intern. Things J"},{"key":"B27","doi-asserted-by":"crossref","DOI":"10.1117\/12.2518469","article-title":"\u201cDeep learning on mobile devices: a review,\u201d","volume-title":"Mobile Multimedia\/Image Processing, Security, and Applications 2019","author":"Deng","year":"2019"},{"key":"B28","first-page":"4171","article-title":"\u201cBERT: Pre-training of deep bidirectional transformers for language understanding,\u201d","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Devlin","year":"2019"},{"key":"B29","doi-asserted-by":"publisher","first-page":"2414","DOI":"10.3390\/s18082414","article-title":"Wearable health devices\u2014vital sign monitoring, systems and technologies","volume":"18","author":"Dias","year":"2018","journal-title":"Sensors"},{"key":"B30","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.neucom.2021.12.002","article-title":"Nap: Neural architecture search with pruning","volume":"477","author":"Ding","year":"2022","journal-title":"Neurocomputing"},{"key":"B31","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1109\/TBDATA.2018.2829886","article-title":"Differential privacy preserving of training model in wireless big data with edge computing","volume":"6","author":"Du","year":"2020","journal-title":"IEEE Trans. Big Data"},{"key":"B32","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1038\/s41591-018-0316-z","article-title":"A guide to deep learning in healthcare","volume":"25","author":"Esteva","year":"2019","journal-title":"Nat. Med"},{"key":"B33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1902.09574","article-title":"The state of sparsity in deep neural networks","author":"Gale","year":"2019","journal-title":"arXiv"},{"key":"B34","doi-asserted-by":"publisher","first-page":"100784","DOI":"10.1016\/j.measen.2023.100784","article-title":"Analysis of optimization algorithms for stability and convergence for natural language processing using deep learning algorithms","volume":"27","author":"Gangadhar","year":"2023","journal-title":"Measurement: Sens"},{"key":"B35","doi-asserted-by":"publisher","first-page":"1928","DOI":"10.1007\/s10439-024-03454-8","article-title":"Large language models and healthcare alliance: potential and challenges of two representative use cases","volume":"52","author":"Garc\u00eda-M\u00e9ndez","year":"2024","journal-title":"Ann. Biomed. Eng"},{"key":"B36","doi-asserted-by":"publisher","first-page":"1789","DOI":"10.1007\/s11263-021-01453-z","article-title":"Knowledge distillation: a survey","volume":"129","author":"Gou","year":"2021","journal-title":"Int. J. Comput. Vis"},{"key":"B37","first-page":"3800","article-title":"\u201cImproving the gating mechanism of recurrent neural networks,\u201d","volume-title":"Proceedings of the 37th International Conference on Machine Learning","author":"Gu","year":"2020"},{"key":"B38","first-page":"572","article-title":"\u201cCombining recurrent, convolutional, and continuous-time models with linear state space layers,\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Gu","year":"2021"},{"key":"B39","first-page":"14522","article-title":"\u201cScale-equivalent distillation for semi-supervised object detection,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Guo","year":"2022"},{"key":"B40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1510.00149","article-title":"Deep compression: compressing deep neural networks with pruning, trained quantization, and huffman coding","author":"Han","year":"2015","journal-title":"arXiv"},{"key":"B41","doi-asserted-by":"crossref","first-page":"691","DOI":"10.1007\/978-3-031-20056-4_40","article-title":"\u201cFEDX: Unsupervised federated learning with cross knowledge distillation,\u201d","volume-title":"Computer Vision-ECCV 2022","author":"Han","year":"2022"},{"key":"B42","first-page":"722","article-title":"\u201cNeuPIMS: NPU-PIM heterogeneous acceleration for batched llm inferencing,\u201d","volume-title":"Proceedings of the 29th ACM International Conference on Architectural Support for Programming Languages and Operating Systems","author":"Heo","year":"2024"},{"key":"B43","doi-asserted-by":"publisher","first-page":"38448","DOI":"10.1109\/ACCESS.2023.3267469","article-title":"A dynamic pruning method on multiple sparse structures in deep neural networks","volume":"11","author":"Hu","year":"2023","journal-title":"IEEE Access"},{"key":"B44","doi-asserted-by":"publisher","first-page":"100674","DOI":"10.1016\/j.iot.2022.100674","article-title":"Ai-based fog and edge computing: a systematic review, taxonomy and future directions","volume":"21","author":"Iftikhar","year":"2023","journal-title":"Intern. Things"},{"key":"B45","article-title":"\u201cAI benchmark: running deep neural networks on android smartphones,\u201d","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV) Workshops","author":"Ignatov","year":"2018"},{"key":"B46","doi-asserted-by":"publisher","first-page":"5263","DOI":"10.3390\/s23115263","article-title":"Blockchain-modeled edge-computing-based smart home monitoring system with energy usage prediction","volume":"23","author":"Iqbal","year":"2023","journal-title":"Sensors"},{"key":"B47","first-page":"2704","article-title":"\u201cQuantization and training of neural networks for efficient integer-arithmetic-only inference,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Jacob","year":"2018"},{"key":"B48","doi-asserted-by":"publisher","first-page":"156","DOI":"10.1007\/s11036-020-01702-4","article-title":"Machine learning and big data analytics for iot-enabled smart cities","volume":"26","author":"Jan","year":"2021","journal-title":"Mobile Netw. Appl"},{"key":"B49","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1109\/ISCA52012.2021.00011","article-title":"\u201cSparsity-aware and re-configurable NPU architecture for samsung flagship mobile SoC,\u201d","volume-title":"2021 ACM\/IEEE 48th Annual International Symposium on Computer Architecture (ISCA)","author":"Jang","year":"2021"},{"key":"B50","unstructured":"Sparse is enough in scaling transformers\n          \n          9895\n          9907\n          \n            \n              Jaszczur\n              S.\n            \n            \n              Chowdhery\n              A.\n            \n            \n              Mohiuddin\n              A.\n            \n            \n              Kaiser\n              L.\n            \n            \n              Gajewski\n              W.\n            \n            \n              Michalewski\n              H.\n            \n          \n          Adv. Neural Inf. Process. Syst\n          34\n          2021"},{"key":"B51","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TIM.2024.3351239","article-title":"Edge-computing-based knowledge distillation and multitask learning for partial discharge recognition","volume":"73","author":"Ji","year":"2024","journal-title":"IEEE Trans. Instrum. Meas"},{"key":"B52","doi-asserted-by":"crossref","DOI":"10.1145\/3544548.3581503","article-title":"\u201cUnderstanding the benefits and challenges of deploying conversational ai leveraging large language models for public health intervention,\u201d","volume-title":"Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems","author":"Jo","year":"2023"},{"key":"B53","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1561\/9781680837896","article-title":"Advances and open problems in federated learning","volume":"14","author":"Kairouz","year":"2021","journal-title":"Found. Trends Mach. Learn"},{"key":"B54","first-page":"615","article-title":"\u201cNeurosurgeon: Collaborative intelligence between the cloud and mobile edge,\u201d","volume-title":"ACM SIGARCH Computer Architecture News","author":"Kang","year":"2017"},{"key":"B55","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1109\/RTSS59052.2023.00034","article-title":"\u201cCollabVr: Reprojection-based edge-client collaborative rendering for real-time high-quality mobile virtual reality,\u201d","volume-title":"2023 IEEE Real-Time Systems Symposium (RTSS)","author":"Ke","year":"2023"},{"key":"B56","doi-asserted-by":"publisher","first-page":"10200","DOI":"10.1109\/JIOT.2020.2987070","article-title":"Edge-computing-enabled smart cities: a comprehensive survey","volume":"7","author":"Khan","year":"2020","journal-title":"IEEE Internet of Things Journal"},{"key":"B57","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1016\/j.future.2019.02.050","article-title":"Edge computing: A survey","volume":"97","author":"Khan","year":"2019","journal-title":"Future Generation Computer Systems"},{"key":"B58","doi-asserted-by":"publisher","first-page":"26419","DOI":"10.1109\/ACCESS.2023.3257864","article-title":"Quantization robust pruning with knowledge distillation","volume":"11","author":"Kim","year":"2023","journal-title":"IEEE Access"},{"key":"B59","first-page":"36187","article-title":"\u201cMemory-efficient fine-tuning of compressed large language models via sub-4-bit integer quantization,\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Kim","year":"2023"},{"key":"B60","first-page":"1","article-title":"\u201cExtending the onnx runtime framework for the processing-in-memory execution,\u201d","volume-title":"2022 International Conference on Electronics, Information, and Communication (ICEIC)","author":"Kim","year":"2022"},{"key":"B61","article-title":"Health-llm: Large language models for health prediction via wearable sensor data","author":"Kim","year":"2024","journal-title":"arXiv [preprint] arXiv"},{"key":"B62","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3597209","article-title":"Model-based diagnosis of real-time systems: Robustness against varying latency, clock drift, and out-of-order observations","volume":"22","author":"K\u00f6hl","year":"2023","journal-title":"ACM Trans. Embed. Comput. Syst"},{"key":"B63","doi-asserted-by":"publisher","DOI":"10.1145\/3555308","article-title":"Edge-computing-driven internet of things: A survey","author":"Kong","year":"2022","journal-title":"ACM Computing Surveys"},{"key":"B64","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2019.2899262","article-title":"Neuromemristive circuits for edge computing: a review","volume":"31","author":"Krestinskaya","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst"},{"key":"B65","unstructured":"\u201cAlbert: a lite bert for self-supervised learning of language representations,\u201d\n          \n          \n            \n              Lan\n              Z.\n            \n            \n              Chen\n              M.\n            \n            \n              Goodman\n              S.\n            \n            \n              Gimpel\n              K.\n            \n            \n              Sharma\n              P.\n            \n            \n              Soricut\n              R.\n            \n          \n          Addis Ababa\n          openreview.net\n          Proceedings of the 8th International Conference on Learning Representations (ICLR)\n          \n          2019"},{"key":"B66","first-page":"837","article-title":"\u201cSemi-supervised training for end-to-end models via weak distillation,\u201d","volume-title":"ICASSP 2019","author":"Li","year":"2019"},{"key":"B67","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1016\/j.future.2023.03.010","article-title":"Ubiquitous intelligent federated learning privacy-preserving scheme under edge computing","volume":"144","author":"Li","year":"2023","journal-title":"Future Generat. Comp. Syst"},{"key":"B68","doi-asserted-by":"publisher","first-page":"1417","DOI":"10.1109\/TSC.2022.3176576","article-title":"Service home identification of multiple-source iot applications in edge computing","volume":"16","author":"Li","year":"2023","journal-title":"IEEE Trans. Serv. Comp"},{"key":"B69","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3153964","article-title":"Distributed differential evolution with adaptive resource allocation","author":"Li","year":"2023","journal-title":"IEEE Trans. Cybern"},{"key":"B70","doi-asserted-by":"publisher","first-page":"2126","DOI":"10.3390\/math10122126","article-title":"A compact parallel pruning scheme for deep learning model and its mobile instrument deployment","volume":"10","author":"Li","year":"2022","journal-title":"Mathematics"},{"key":"B71","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.future.2021.10.006","article-title":"Big data analysis of the internet of things in the digital twins of smart city based on deep learning","volume":"128","author":"Li","year":"2022","journal-title":"Future Generat. Comp. Syst"},{"key":"B72","doi-asserted-by":"publisher","first-page":"370","DOI":"10.1016\/j.neucom.2021.07.045","article-title":"Pruning and quantization for deep neural network acceleration: a survey","volume":"461","author":"Liang","year":"2021","journal-title":"Neurocomputing"},{"key":"B73","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2307.08191","article-title":"Unleashing the potential of llms for quantum computing: A study in quantum architecture design","author":"Liang","year":"2023","journal-title":"arXiv"},{"key":"B74","doi-asserted-by":"publisher","first-page":"751","DOI":"10.1145\/3296957.3173191","article-title":"The architectural implications of autonomous driving: Constraints and acceleration","volume":"53","author":"Lin","year":"2018","journal-title":"SIGPLAN Not"},{"key":"B75","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1109\/MNET.011.2000215","article-title":"Keep your data locally: Federated-learning-based data privacy preservation in edge computing","volume":"35","author":"Liu","year":"2021","journal-title":"IEEE Netw"},{"key":"B76","doi-asserted-by":"publisher","first-page":"54","DOI":"10.3390\/s21010054","article-title":"Monocular depth estimation with joint attention feature distillation and wavelet-based loss function","volume":"21","author":"Liu","year":"2021","journal-title":"Sensors"},{"key":"B77","first-page":"757","volume-title":"Cloud, Edge, and Mobile Computing for Smart Cities","author":"Liu","year":"2021"},{"key":"B78","doi-asserted-by":"publisher","first-page":"8697","DOI":"10.1609\/aaai.v35i10.17054","article-title":"Post-training quantization with multiple points: Mixed precision without mixed precision","volume":"35","author":"Liu","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intellig"},{"key":"B79","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.neucom.2020.07.048","article-title":"Adaptive multi-teacher multi-level knowledge distillation","volume":"415","author":"Liu","year":"2020","journal-title":"Neurocomputing"},{"key":"B80","article-title":"\u201cFrequency-domain dynamic pruning for convolutional neural networks,\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Liu","year":"2018"},{"key":"B81","doi-asserted-by":"publisher","first-page":"11093","DOI":"10.1109\/JIOT.2023.3239944","article-title":"Edge computing on iot for machine signal processing and fault diagnosis: a review","volume":"10","author":"Lu","year":"2023","journal-title":"IEEE Intern. Things J"},{"key":"B82","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1016\/j.future.2020.08.037","article-title":"Retracted: Intelligent edge computing based on machine learning for smart city","volume":"115","author":"Lv","year":"2021","journal-title":"Future Generat. Comp. Syst"},{"key":"B83","doi-asserted-by":"publisher","first-page":"212177","DOI":"10.1109\/ACCESS.2020.3039714","article-title":"Head network distillation: splitting distilled deep neural networks for resource-constrained edge computing systems","volume":"8","author":"Matsubara","year":"2020","journal-title":"IEEE Access"},{"key":"B84","first-page":"1273","article-title":"\u201cCommunication-efficient learning of deep networks from decentralized data,\u201d","volume-title":"Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS)","author":"McMahan","year":"2017"},{"key":"B85","doi-asserted-by":"publisher","first-page":"93","DOI":"10.1007\/s11227-021-03868-4","article-title":"A latency-aware task scheduling algorithm for allocating virtual machines in a cost-effective and time-sensitive fog-cloud architecture","volume":"78","author":"Memari","year":"2022","journal-title":"J. Supercomput"},{"key":"B86","first-page":"16318","article-title":"\u201cOvercoming oscillations in quantization-aware training,\u201d","volume-title":"Proceedings of the 39th International Conference on Machine Learning","author":"Nagel","year":"2022"},{"key":"B87","doi-asserted-by":"publisher","first-page":"588","DOI":"10.1016\/j.jmsy.2022.01.010","article-title":"Towards edge computing in intelligent manufacturing: Past, present and future","volume":"62","author":"Nain","year":"2022","journal-title":"J. Manufact. Syst"},{"key":"B88","first-page":"4730","article-title":"\u201cADAMTL: Adaptive input-dependent inference for efficient multi-task learning,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Neseem","year":"2023"},{"key":"B89","doi-asserted-by":"publisher","first-page":"1622","DOI":"10.1109\/COMST.2021.3075439","article-title":"Federated learning for internet of things: A comprehensive survey","volume":"23","author":"Nguyen","year":"","journal-title":"IEEE Commun. Surv. Tutor"},{"key":"B90","doi-asserted-by":"publisher","first-page":"12806","DOI":"10.1109\/JIOT.2021.3072611","article-title":"Federated learning meets blockchain in edge computing: Opportunities and challenges","volume":"8","author":"Nguyen","year":"","journal-title":"IEEE Intern, Things J"},{"key":"B91","first-page":"883","article-title":"\u201cDNNFusion: accelerating deep neural networks execution with advanced operator fusion,\u201d","volume-title":"Proceedings of the 42nd ACM SIGPLAN International Conference on Programming Language Design and Implementation, PLDI 2021","author":"Niu","year":"2021"},{"key":"B92","doi-asserted-by":"publisher","first-page":"2489","DOI":"10.1007\/s41870-023-01320-9","article-title":"Lightweight convolutional neural network architecture implementation using TensorFlow lite","volume":"15","author":"Pandey","year":"2023","journal-title":"Int. J. Inform. Technol"},{"key":"B93","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3439950","article-title":"Deep learning for anomaly detection: A review","volume":"54","author":"Pang","year":"2021","journal-title":"ACM Comp. SurvCSUR)"},{"key":"B94","doi-asserted-by":"publisher","first-page":"7954","DOI":"10.1109\/JIOT.2020.3042428","article-title":"Operating latency sensitive applications on public serverless edge cloud platforms","volume":"8","author":"Pelle","year":"2021","journal-title":"IEEE Intern. Things J"},{"key":"B95","first-page":"1309","article-title":"\u201cDifferential privacy preservation for deep auto-encoders: An application of human behavior prediction,\u201d","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Phan","year":"2017"},{"key":"B96","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1109\/MWC.011.2000501","article-title":"Federated learning and wireless communications","volume":"28","author":"Qin","year":"2021","journal-title":"IEEE Wireless Commun"},{"key":"B97","doi-asserted-by":"publisher","first-page":"2462","DOI":"10.1109\/COMST.2020.3009103","article-title":"Edge computing in industrial internet of things: Architecture, advances and challenges","volume":"22","author":"Qiu","year":"2020","journal-title":"IEEE Commun. Surv. Tutorials"},{"key":"B98","unstructured":"Learning transferable visual models from natural language supervision\n          \n          8748\n          8763\n          \n            \n              Radford\n              A.\n            \n            \n              Kim\n              J. W.\n            \n            \n              Hallacy\n              C.\n            \n            \n              Ramesh\n              A.\n            \n            \n              Goh\n              G.\n            \n            \n              Agarwal\n              S.\n            \n          \n          Proc. Int. Conf. Mach. Learn\n          ICML)\n          38\n          2021"},{"key":"B99","unstructured":"Exploring the limits of transfer learning with a unified text-to-text transformer\n          \n          1\n          67\n          \n            \n              Raffel\n              C.\n            \n            \n              Shazeer\n              N.\n            \n            \n              Roberts\n              A.\n            \n            \n              Lee\n              K.\n            \n            \n              Narang\n              S.\n            \n            \n              Matena\n              M.\n            \n          \n          J. Mach. Learn. Res\n          21\n          2020"},{"key":"B100","doi-asserted-by":"publisher","first-page":"162","DOI":"10.1109\/MNET.2018.1800132","article-title":"An edge-computing based architecture for mobile augmented reality","volume":"33","author":"Ren","year":"","journal-title":"IEEE Network"},{"key":"B101","doi-asserted-by":"publisher","first-page":"5031","DOI":"10.1109\/TVT.2019.2904244","article-title":"Collaborative cloud and edge computing for latency minimization","volume":"68","author":"Ren","year":"","journal-title":"IEEE Trans. Vehicular Technol"},{"key":"B102","article-title":"\u201cBeyond exploding and vanishing gradients: analysing rnn training using attractors and smoothness,\u201d","author":"Ribeiro","year":"2020","journal-title":"Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics"},{"key":"B103","doi-asserted-by":"publisher","first-page":"1082","DOI":"10.3390\/s22031082","article-title":"Adopting the yolov4 architecture for low-latency multispectral pedestrian detection in autonomous driving","volume":"22","author":"Roszyk","year":"2022","journal-title":"Sensors"},{"key":"B104","doi-asserted-by":"publisher","first-page":"17556","DOI":"10.1109\/JSEN.2020.3048593","article-title":"Dlsense: Distributed learning-based smart virtual sensing for precision agriculture","volume":"21","author":"Saha","year":"2021","journal-title":"IEEE Sens. J"},{"key":"B105","first-page":"19123","article-title":"\u201cOptimal clipping and magnitude-aware differentiation for improved quantization-aware training,\u201d","author":"Sakr","year":"2022","journal-title":"Proceedings of the 39th International Conference on Machine Learning"},{"key":"B106","doi-asserted-by":"publisher","first-page":"32","DOI":"10.26599\/BDMA.2021.9020016","article-title":"Big data with cloud computing: Discussions and challenges","volume":"5","author":"Sandhu","year":"2022","journal-title":"Big Data Mining Analyt"},{"key":"B107","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1910.01108","article-title":"Distilbert, a distilled version of bert: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019","journal-title":"arXiv"},{"key":"B108","doi-asserted-by":"publisher","first-page":"959","DOI":"10.5829\/ije.2020.33.05b.29","article-title":"A hybrid deep learning architecture using 3d cnns and grus for human action recognition","volume":"33","author":"Savadi Hosseini","year":"2020","journal-title":"Int. J. Eng"},{"key":"B109","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1038\/s43588-021-00184-y","article-title":"Opportunities for neuromorphic computing algorithms and applications","volume":"2","author":"Schuman","year":"2022","journal-title":"Nat, Comp. Sci"},{"key":"B110","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1109\/JIOT.2016.2579198","article-title":"Edge computing: vision and challenges","volume":"3","author":"Shi","year":"2016","journal-title":"IEEE Intern. Things J"},{"key":"B111","doi-asserted-by":"publisher","first-page":"54188","DOI":"10.1109\/ACCESS.2023.3281832","article-title":"Decentralized learning in healthcare: A review of emerging techniques","volume":"11","author":"Shiranthika","year":"2023","journal-title":"IEEE Access"},{"key":"B112","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/JPROC.2022.3226481","article-title":"Efficient acceleration of deep learning inference on resource-constrained edge devices: a review","volume":"111","author":"Shuvo","year":"2022","journal-title":"Proc. IEEE"},{"key":"B113","doi-asserted-by":"publisher","first-page":"1160","DOI":"10.1109\/COMST.2021.3061981","article-title":"A survey on mobile augmented reality with 5G mobile edge computing: architectures, applications, and technical aspects","volume":"23","author":"Siriwardhana","year":"2021","journal-title":"IEEE Commun. Surv. Tutor"},{"key":"B114","doi-asserted-by":"publisher","first-page":"13693","DOI":"10.1609\/aaai.v34i09.7123","article-title":"Energy and policy considerations for modern deep learning research","volume":"34","author":"Strubell","year":"2020","journal-title":"Proc. AAAI Conf. Artif. Intellig"},{"key":"B115","doi-asserted-by":"publisher","first-page":"108760","DOI":"10.1016\/j.tws.2021.108760","article-title":"Lightweight hybrid materials and structures for energy absorption: a state-of-the-art review and outlook","volume":"172","author":"Sun","year":"2022","journal-title":"Thin-Walled Struct"},{"key":"B116","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1109\/MCOM.2016.1600492CM","article-title":"Edgeiot: Mobile edge computing for the internet of things","volume":"54","author":"Sun","year":"2019","journal-title":"IEEE Commun. Magaz"},{"key":"B117","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.195","article-title":"Mobilebert: A compact task-agnostic bert for resource-limited devices","author":"Sun","year":"2020","journal-title":"arXiv"},{"key":"B118","doi-asserted-by":"publisher","first-page":"1023","DOI":"10.1109\/TCE.2023.3318150","article-title":"A comprehensive survey on artificial intelligence empowered edge computing on consumer electronics","volume":"69","author":"Syu","year":"2023","journal-title":"IEEE Trans.Consumer Electron"},{"key":"B119","first-page":"2464","article-title":"\u201cBranchyNET: Fast inference via early exiting from deep neural networks,\u201d","volume-title":"Proceedings of the 23rd International Conference on Pattern Recognition (ICPR)","author":"Teerapittayanon","year":"2016"},{"key":"B120","doi-asserted-by":"crossref","first-page":"27","DOI":"10.1109\/ICDCSW53096.2021.00012","article-title":"\u201cPersonalized federated learning by structured and unstructured pruning under data heterogeneity,\u201d","volume-title":"2021 IEEE 41st International Conference on Distributed Computing Systems Workshops (ICDCSW)","author":"Vahidian","year":"2021"},{"key":"B121","first-page":"5998","article-title":"\u201cAttention is all you need,\u201d","volume-title":"Advances in Neural Information Processing Systems","author":"Vaswani","year":"2017"},{"key":"B122","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1812.00564","article-title":"Split learning for health: Distributed deep learning without sharing raw patient data","author":"Vepakomma","year":"2018","journal-title":"arXiv [Preprint]"},{"key":"B123","doi-asserted-by":"publisher","first-page":"111799","DOI":"10.1016\/j.enconman.2019.111799","article-title":"A review of deep learning for renewable energy forecasting","volume":"198","author":"Wang","year":"2019","journal-title":"Energy Convers. Managem"},{"key":"B124","doi-asserted-by":"publisher","first-page":"1205","DOI":"10.1109\/JSAC.2019.2904348","article-title":"Adaptive federated learning in resource constrained edge computing systems","volume":"37","author":"Wang","year":"2019","journal-title":"IEEE J. Select. Areas Commun"},{"key":"B125","doi-asserted-by":"publisher","first-page":"23156","DOI":"10.1109\/JIOT.2024.3387328","article-title":"Adaptive knowledge distillation-based lightweight intelligent fault diagnosis framework in iot edge computing","volume":"11","author":"Wang","year":"2024","journal-title":"IEEE Intern.Things J"},{"key":"B126","first-page":"14913","article-title":"\u201cConvolutional neural network pruning with structural redundancy reduction,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Wang","year":"2021"},{"key":"B127","doi-asserted-by":"publisher","first-page":"3454","DOI":"10.1109\/TIFS.2020.2988575","article-title":"Federated learning with differential privacy: Algorithms and performance analysis","volume":"15","author":"Wei","year":"2020","journal-title":"IEEE Trans. Inform. Forens. Security"},{"key":"B128","first-page":"8817","article-title":"\u201cBlockdrop: Dynamic inference paths in residual networks,\u201d","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Wu","year":"2020"},{"key":"B129","doi-asserted-by":"publisher","first-page":"100008","DOI":"10.1016\/j.hcc.2021.100008","article-title":"A survey of federated learning for edge computing: Research problems and solutions","volume":"1","author":"Xia","year":"2021","journal-title":"High-Confidence Comp"},{"key":"B130","doi-asserted-by":"publisher","first-page":"21370","DOI":"10.1109\/JIOT.2022.3179739","article-title":"Soft actor\u2013critic-based multilevel cooperative perception for connected autonomous vehicles","volume":"9","author":"Xie","year":"2022","journal-title":"IEEE Intern. Things J."},{"key":"B131","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1145\/3662006.3662066","article-title":"\u201cWIP: Efficient LLM prefilling with mobile NPU,\u201d","author":"Xu","year":"2024","journal-title":"Proceedings of the Workshop on Edge and Mobile Foundation Models"},{"key":"B132","first-page":"269","article-title":"\u201cLPVIT: Low-power semi-structured pruning for vision transformers,\u201d","author":"Xu","year":"2025"},{"key":"B133","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3649506","article-title":"Harnessing the power of llms in practice: a survey on chatgpt and beyond","volume":"18","author":"Yang","year":"2024","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"B134","doi-asserted-by":"crossref","first-page":"3346","DOI":"10.1145\/3581783.3613814","article-title":"\u201cMulti-scale spatial-spectral attention guided fusion network for pansharpening,\u201d","volume-title":"Proceedings of the 31st ACM International Conference on Multimedia, MM '23","author":"Yang","year":"2023"},{"key":"B135","doi-asserted-by":"crossref","first-page":"4346","DOI":"10.18653\/v1\/2020.acl-main.400","article-title":"\u201cMultimodal transformer for multimodal machine translation,\u201d","volume-title":"Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics","author":"Yao","year":"2020"},{"key":"B136","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3625558","article-title":"Heterogeneous federated learning: State-of-the-art and research challenges","volume":"56","author":"Ye","year":"2023","journal-title":"ACM Com. Surv"},{"key":"B137","doi-asserted-by":"publisher","first-page":"107899","DOI":"10.1016\/j.patcog.2021.107899","article-title":"Pruning by explaining: A novel criterion for deep neural network pruning","volume":"115","author":"Yeom","year":"2021","journal-title":"Pattern Recognit"},{"key":"B138","doi-asserted-by":"publisher","first-page":"48631","DOI":"10.1109\/ACCESS.2021.3066789","article-title":"Efficient computation offloading in edge computing enabled smart home","volume":"9","author":"Yu","year":"2021","journal-title":"IEEE Access"},{"key":"B139","doi-asserted-by":"publisher","first-page":"6900","DOI":"10.1109\/ACCESS.2017.2778504","article-title":"A survey on the edge computing for the internet of things","volume":"6","author":"Yu","year":"2018","journal-title":"IEEE Access"},{"key":"B140","doi-asserted-by":"publisher","first-page":"14284","DOI":"10.1609\/aaai.v35i16.17680","article-title":"Reinforced multi-teacher selection for knowledge distillation","volume":"35","author":"Yuan","year":"2021","journal-title":"Proc. AAAI Conf. Artif. Intellig"},{"key":"B141","doi-asserted-by":"publisher","first-page":"4326","DOI":"10.1109\/TPDS.2022.3187815","article-title":"Acctfm: An effective intra-layer model parallelization strategy for training large-scale transformer-based models","volume":"33","author":"Zeng","year":"2022","journal-title":"IEEE Trans. Parallel Distrib. Syst"},{"key":"B142","doi-asserted-by":"publisher","first-page":"4899","DOI":"10.1109\/JIOT.2024.3447036","article-title":"Distributed deep reinforcement learning based gradient quantization for federated learning enabled vehicle edge computing","volume":"12","author":"Zhang","year":"2025","journal-title":"IEEE Intern. Things J"},{"key":"B143","first-page":"1","article-title":"\u201cDelay-sensitive computation partitioning for mobile augmented reality applications,\u201d","volume-title":"2020 IEEE\/ACM 28th International Symposium on Quality of Service (IWQoS)","author":"Zhang","year":"2020"},{"key":"B144","doi-asserted-by":"publisher","first-page":"18209","DOI":"10.1109\/ACCESS.2018.2820162","article-title":"Data security and privacy-preserving in edge computing paradigm: Survey and open issues","volume":"6","author":"Zhang","year":"2018","journal-title":"IEEE Access"},{"key":"B145","doi-asserted-by":"publisher","first-page":"14085","DOI":"10.1109\/TMC.2024.3439511","article-title":"Quantum-inspired robust networking model with multiverse co-evolution for scale-free iot","volume":"23","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Mobile Comp"},{"key":"B146","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1145\/3240508.3240561","article-title":"\u201cJaguar: Low latency mobile augmented reality with flexible tracking,\u201d","volume-title":"Proceedings of the 26th ACM International Conference on Multimedia, MM '18","author":"Zhang","year":"2018"},{"key":"B147","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/RBME.2022.3210270","article-title":"Natural language processing for smart healthcare","volume":"17","author":"Zhou","year":"2022","journal-title":"IEEE Rev. Biomed. Eng"},{"key":"B148","doi-asserted-by":"publisher","first-page":"1905","DOI":"10.1109\/TIFS.2022.3174394","article-title":"Pflf: Privacy-preserving federated learning framework for edge computing","volume":"17","author":"Zhou","year":"","journal-title":"IEEE Trans. Inform. Forens. Secur"},{"key":"B149","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1109\/TIFS.2022.3227435","article-title":"Privacy-preserving and verifiable federated learning framework for edge computing","volume":"18","author":"Zhou","year":"","journal-title":"IEEE Trans. Inform. Forens. Secur"},{"key":"B150","doi-asserted-by":"publisher","first-page":"6908","DOI":"10.1109\/TMC.2023.3328333","article-title":"Dag-based dependent tasks offloading in mec-enabled iot with soft cooperation","volume":"23","author":"Zhou","year":"","journal-title":"IEEE Trans. Mobile Comp"},{"key":"B151","doi-asserted-by":"publisher","first-page":"890","DOI":"10.1109\/TMC.2021.3087198","article-title":"Energy-efficient service migration for multi-user heterogeneous dense cellular networks","volume":"22","author":"Zhou","year":"2023","journal-title":"IEEE Trans. Mobile Comp"},{"key":"B152","doi-asserted-by":"publisher","first-page":"4764","DOI":"10.1109\/TMC.2023.3297213","article-title":"Recommendation-driven multi-cell cooperative caching: A multi-agent reinforcement learning approach","volume":"23","author":"Zhou","year":"","journal-title":"IEEE Trans. Mobile Comp"},{"key":"B153","first-page":"32","article-title":"\u201cAdaptive quantization for deep neural network,\u201d","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","author":"Zhou","year":"2018"},{"key":"B154","doi-asserted-by":"publisher","first-page":"106889","DOI":"10.1016\/j.cie.2020.106889","article-title":"Predictive maintenance in the industry 4.0: A systematic literature review","volume":"150","author":"Zonta","year":"2020","journal-title":"Comp. Indust. Eng"}],"container-title":["Frontiers in Computer Science"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2025.1538277\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T05:39:05Z","timestamp":1747201145000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcomp.2025.1538277\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,14]]},"references-count":154,"alternative-id":["10.3389\/fcomp.2025.1538277"],"URL":"https:\/\/doi.org\/10.3389\/fcomp.2025.1538277","relation":{},"ISSN":["2624-9898"],"issn-type":[{"value":"2624-9898","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,14]]},"article-number":"1538277"}}