参考文献

[1] CAI H, GAN C, WANG T, et al. Once-for-all: Train one network and specialize it for efficient deployment[J]. arXiv preprint arXiv:1908.09791, 2019.

[2] GUO P, HU B, HU W. Mistify: Automating {DNN} Model Porting for {On-Device} Inference at the Edge[C]. Proceedings of the 18th USENIX Symposium on Networked Systems Design and Implementation(NSDI). 2021: 705-719.

[3] GUPTA J K, EGOROV M, Kochenderfer M. Cooperative multi-agent control using deep reinfor-cement learning[C]//Proceedings of the International conference on autonomous agents and multiagent systems (AAMAS). Cham, Springer, 2017:66-83.

[4] ABDELFATTAH M S, MEHROTRA A, DUDZIAK L, et al. Zero-cost proxies for lightweight NAS[J]. arXiv preprint arXiv:2101.08134, 2021.

[5] ZHANG J, LETAIEF K B. Mobile edge intelligence and computing for the internet of vehicles[J]. Proceedings of the IEEE, 2019, 108(2):246-261.

[6] WEISER M. The computer for the 21st century[J]. ACM SIGMOBILE mobile computing and communications review, 1999, 3(3):3-11.

[7] 艾瑞网. 2020年中国智能物联网（AIoT）白皮书[EB]. 2021. https://report.iresearch.cn/report_pdf.aspx?id=3529.

[8] ZHANG J, TAO D. Empowering things with intelligence:a survey of the progress, challenges, and opportunities in artificial intelligence of things[J]. IEEE Internet of Things Journal, 2020, 8(10):7789-7817.

[9] SONG H, BAI J, YI Y, et al. Artificial intelligence enabled Internet of Things: Network archi-tecture and spectrum access[J]. IEEE Computational Intelligence, 2020, 15(1):44-51.

[10] CHEN J, RAN X. Deep learning with edge computing: A review[J]. Proceedings of the IEEE, 2019, 107(8): 1655-1674.

[11] LIM W Y B, LUONG N C, HOANG D T, et al. Federated learning in mobile edge networks: A comprehensive survey[J]. IEEE Communications Surveys&Tutorials, 2020, 22(3): 2031-2063.

[12] 梅宏，曹东刚，谢涛. 泛在操作系统：面向人机物融合泛在计算的新蓝海[J]. 中国科学院院刊，2022 (1):30-37.

[13] 郭斌，刘思聪，於志文.人机物融合群智计算[M].北京：机械工业出版社，2022.

[14] WU D, ZHANG D, XU C, et al. Device-free WiFi human sensing: From pattern-based to modelbased appro--aches[J]. IEEE Communications Magazine, 2017, 55(10): 91-97.

[15] WANG Z, GUO B, YU Z, et al. Wi-Fi CSI-based behavior recognition: From signals and actions to activities[J]. IEEE Communications Magazine, 2018, 56(5): 109-115.

[16] 刘云浩.群智感知计算[J].中国计算机学会通讯，2012, 8(10):38-41.

[17] 於志文，郭斌，王亮.群智感知计算[M].北京：清华大学出版社，2021.

[18] 郭斌，仵允港，王虹力，等. 深度学习模型终端环境自适应方法研究[J]. 中国科学：信息科学，2020, 50(11):1630-1644.

[19] ELSKEN T, METZEN J H, HUTTER F. Neural architecture search: A survey[J]. The Journal of Machine Learning Research, 2019, 20(1): 1997-2017.

[20] WILLIAMS S, WATERMAN A, PATTERSON D. Roofline: An Insightful Visual Performance Model for Floating-Point Programs and Multicore Architectures[J]. Communications of the ACM, 2009, 52(4): 65-76.

[21] LIN J, CHEN W M , LIN Y, et al. MCUNet: Tiny Deep Learning on IoT Devices[J]. Advances in Neural Information Processing Systems (NIPS), 2020, 33: 11711-11722.

[22] SILVER D, HUANG A, MADDISON C J, et al. Mastering the game of go with deep neural networks and tree search[J]. Nature, 2016, 529(7587):484-489.

[23] TZENG E, HOFFMAN J, SAENKO K, et al. Adversarial discriminative domain adaptation[C]//Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR). 2017:7167-7176.

[24] VILALTA R, DRISSI Y. A perspective view and survey of meta-learning[J]. Artificial intelligence review, 2002, 18(2):77-95.

[25] MIRZADEH S I, Farajtabar M, Li A, et al. Improved knowledge distillation via teacher assistant[C]//. Proceedings of the AAAI Conference on Artificial Intelligence (AAAI). 2020, 34(04):5191-5198.

[26] KOLCUN R, POPESCU D A, Safronov V, et al. The case for retraining of ML models for IoT device identification at the edge[J]. arXiv preprint arXiv:2011.08605, 2020. ApJGq8P9pKQqQD6MAoHBK8S3VpZCBnxrziVwZEvUiEOloNq5+743s8cuAEVO5qoF