Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
156 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Over-The-Air Federated Learning: Status Quo, Open Challenges, and Future Directions (2307.00974v1)

Published 3 Jul 2023 in eess.SP, cs.DC, cs.LG, and cs.NI

Abstract: The development of applications based on artificial intelligence and implemented over wireless networks is increasingly rapidly and is expected to grow dramatically in the future. The resulting demand for the aggregation of large amounts of data has caused serious communication bottlenecks in wireless networks and particularly at the network edge. Over-the-air federated learning (OTA-FL), leveraging the superposition feature of multi-access channels (MACs), enables users at the network edge to share spectrum resources and achieves efficient and low-latency global model aggregation. This paper provides a holistic review of progress in OTA-FL and points to potential future research directions. Specifically, we classify OTA-FL from the perspective of system settings, including single-antenna OTA-FL, multi-antenna OTA-FL, and OTA-FL with the aid of the emerging reconfigurable intelligent surface (RIS) technology, and the contributions of existing works in these areas are summarized. Moreover, we discuss the trust, security and privacy aspects of OTA-FL, and highlight concerns arising from security and privacy. Finally, challenges and potential research directions are discussed to promote the future development of OTA-FL in terms of improving system performance, reliability, and trustworthiness. Specifical challenges to be addressed include model distortion under channel fading, the ineffective OTA aggregation of local models trained on substantially unbalanced data, and the limited accessibility and verifiability of individual local models.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (92)
  1. K. Li, Y. Cui, W. Li, T. Lv, X. Yuan, S. Li, W. Ni, M. Simsek, and F. Dressler, “When Internet of Things meets Metaverse: Convergence of physical and cyber worlds,” IEEE Internet Things J., vol. 10, no. 5, pp. 4148–4173, 2023.
  2. E. Peltonen, M. Bennis, M. Capobianco, M. Debbah, A. Ding, F. Gil-Castiñeira, M. Jurmu, T. Karvonen, M. Kelanti, A. Kliks, et al., “6G white paper on edge intelligence,” arXiv preprint arXiv:2004.14850, 2020.
  3. Cambridge University Press, 2022.
  4. J. Zheng, K. Li, N. Mhaisen, W. Ni, E. Tovar, and M. Guizani, “Federated learning for online resource allocation in mobile edge computing: A deep reinforcement learning approach,” in Proc. IEEE Wireless Commun. Networking Conf. (WCNC), pp. 1–6, 2023.
  5. L. Pu, Q. Cui, X. L. I, B. Zhao, W. Ni, M. Ai, and X. Tao, “Federated learning-based heterogeneous load prediction and slicing for 5G systems and beyond,” in Proc. IEEE Global Commun. Conf. (GLOBECOM), pp. 166–172, 2022.
  6. K. Li, W. Ni, Y. Emami, and F. Dressler, “Data-driven flight control of Internet-of-Drones for sensor data aggregation using multi-agent deep reinforcement learning,” IEEE Wireless Commun., vol. 29, no. 4, pp. 18–23, 2022.
  7. J. Zheng, K. Li, N. Mhaisen, W. Ni, E. Tovar, and M. Guizani, “Exploring deep-reinforcement-learning-assisted federated learning for online resource allocation in privacy-preserving EdgeIoT,” IEEE Internet Things J., vol. 9, no. 21, pp. 21099–21110, 2022.
  8. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y. Arcas, “Communication-Efficient Learning of Deep Networks from Decentralized Data,” in Proc. Int. Conf. Artif. Intell. Stat. (AISTATS), pp. 1273–1282, 2017.
  9. W. Li, T. Lv, Y. Cao, W. Ni, and M. Peng, “Multi-carrier NOMA-empowered wireless federated learning with optimal power and bandwidth allocation,” IEEE Trans. Wireless Commun., 2023, early access.
  10. X. Chen, Z. Li, W. Ni, X. Wang, S. Zhang, S. Xu, and Q. Pei, “Two-phase deep reinforcement learning of dynamic resource allocation and client selection for hierarchical federated learning,” in Proc. IEEE Int. Conf. Commun. China (ICCC), pp. 518–523, 2022.
  11. B. Nazer and M. Gastpar, “Computation over multiple-access channels,” IEEE Trans. Inf. Theory, vol. 53, no. 10, pp. 3498–3516, 2007.
  12. D. C. Nguyen, M. Ding, P. N. Pathirana, A. Seneviratne, J. Li, and H. V. Poor, “Federated learning for Internet of Things: A comprehensive survey,” IEEE Commun. Surv. Tutorials, vol. 23, no. 3, pp. 1622–1658, 2021.
  13. M. Goldenbaum, H. Boche, and S. Stańczak, “Harnessing interference for analog function computation in wireless sensor networks,” IEEE Trans. Signal Process., vol. 61, no. 20, pp. 4893–4906, 2013.
  14. B. Luo, W. Xiao, S. Wang, J. Huang, and L. Tassiulas, “Tackling system and statistical heterogeneity for federated learning with adaptive client sampling,” in Proc. IEEE Int. Conf. Comput. Commun. (INFOCOM), pp. 1739–1748, 2022.
  15. G. Zhu, Y. Wang, and K. Huang, “Broadband analog aggregation for low-latency federated edge learning,” IEEE Trans. Wireless Commun., vol. 19, no. 1, pp. 491–506, 2020.
  16. Y. Sun, S. Zhou, Z. Niu, and D. Gündüz, “Dynamic scheduling for over-the-air federated edge learning with energy constraints,” IEEE J. Sel. Areas Commun., vol. 40, no. 1, pp. 227–242, 2022.
  17. G. Shi, S. Guo, J. Ye, N. Saeed, and S. Dang, “Multiple parallel federated learning via over-the-air computation,” IEEE Open J. Commun. Soc., vol. 3, pp. 1252–1264, 2022.
  18. J. Du, B. Jiang, C. Jiang, Y. Shi, and Z. Han, “Gradient and channel aware dynamic scheduling for over-the-air computation in federated edge learning systems,” IEEE J. Sel. Areas Commun., vol. 41, no. 4, pp. 1035–1050, 2023.
  19. X. Cao, G. Zhu, J. Xu, and S. Cui, “Transmission power control for over-the-air federated averaging at network edge,” IEEE J. Sel. Areas Commun., vol. 40, no. 5, pp. 1571–1586, 2022.
  20. X. Cao, G. Zhu, J. Xu, Z. Wang, and S. Cui, “Optimized power control design for over-the-air federated edge learning,” IEEE J. Sel. Areas Commun., vol. 40, no. 1, pp. 342–358, 2022.
  21. Y. Zou, Z. Wang, X. Chen, H. Zhou, and Y. Zhou, “Knowledge-guided learning for transceiver design in over-the-air federated learning,” IEEE Trans. Wireless Commun., vol. 22, no. 1, pp. 270–285, 2023.
  22. Z. Wang, Y. Zhou, Y. Shi, and W. Zhuang, “Interference management for over-the-air federated learning in multi-cell wireless networks,” IEEE J. Sel. Areas Commun., vol. 40, no. 8, pp. 2361–2377, 2022.
  23. S. Jing and C. Xiao, “Federated learning via over-the-air computation with statistical channel state information,” IEEE Trans. Wireless Commun., vol. 21, no. 11, pp. 9351–9365, 2022.
  24. X. Yu, B. Xiao, W. Ni, and X. Wang, “Optimal power control for over-the-air federated edge learning using statistical channel knowledge,” in Proc. IEEE Int. Conf. Wireless Commun. Signal Process. (WCSP), pp. 232–237, 2022.
  25. T. Sery and K. Cohen, “On analog gradient descent learning over multiple access fading channels,” IEEE Trans. Signal Process., vol. 68, pp. 2897–2911, 2020.
  26. X. Yu, B. Xiao, W. Ni, and X. Wang, “Optimal adaptive power control for over-the-air federated edge learning under fading channels,” IEEE Trans. Commun., pp. 1–1, 2023.
  27. X. Fan, Y. Wang, Y. Huo, and Z. Tian, “Joint optimization of communications and federated learning over the air,” IEEE Trans. Wireless Commun., vol. 21, no. 6, pp. 4434–4449, 2022.
  28. W. Guo, R. Li, C. Huang, X. Qin, K. Shen, and W. Zhang, “Joint device selection and power control for wireless federated learning,” IEEE J. Sel. Areas Commun., vol. 40, no. 8, pp. 2395–2410, 2022.
  29. C. Chen, Y.-H. Chiang, H. Lin, J. C. Lui, and Y. Ji, “Energy harvesting aware client selection for over-the-air federated learning,” in Proc. IEEE Global Commun. Conf. (GLOBECOM), pp. 5069–5074, 2022.
  30. X. Zhai, X. Chen, J. Xu, and D. W. Kwan Ng, “Hybrid beamforming for massive MIMO over-the-air computation,” IEEE Trans. Commun., vol. 69, no. 4, pp. 2737–2751, 2021.
  31. X. Li, G. Zhu, Y. Gong, and K. Huang, “Wirelessly powered data aggregation for IoT via over-the-air function computation: Beamforming and power control,” IEEE Trans. Wireless Commun., vol. 18, no. 7, pp. 3437–3452, 2019.
  32. G. Zhu and K. Huang, “MIMO over-the-air computation for high-mobility multimodal sensing,” IEEE Internet Things J., vol. 6, no. 4, pp. 6089–6103, 2019.
  33. X. Li, F. Liu, Z. Zhou, G. Zhu, S. Wang, K. Huang, and Y. Gong, “Integrated sensing, communication, and computation over-the-air: MIMO beamforming design,” IEEE Trans. Wireless Commun., pp. 1–1, 2023.
  34. D. Wen, G. Zhu, and K. Huang, “Reduced-dimension design of MIMO over-the-air computing for data aggregation in clustered IoT networks,” IEEE Trans. Wireless Commun., vol. 18, no. 11, pp. 5255–5268, 2019.
  35. X. Chen, A. Liu, and M.-J. Zhao, “High-mobility multi-modal sensing for IoT network via MIMO aircomp: A mixed-timescale optimization approach,” IEEE Commun. Lett., vol. 24, no. 10, pp. 2295–2299, 2020.
  36. K. Yang, T. Jiang, Y. Shi, and Z. Ding, “Federated learning via over-the-air computation,” IEEE Trans. Wireless Commun., vol. 19, no. 3, pp. 2022–2035, 2020.
  37. A. Bereyhi, A. Vagollari, S. Asaad, R. R. Müller, W. Gerstacker, and H. V. Poor, “Device scheduling in over-the-air federated learning via matching pursuit,” IEEE Trans. Signal Process., vol. 71, pp. 2188–2203, 2023.
  38. C. Zhong, H. Yang, and X. Yuan, “Over-the-air multi-task federated learning over MIMO interference channel,” arXiv preprint arXiv:2112.13603, 2021.
  39. S. Hu, X. Yuan, W. Ni, X. Wang, and A. Jamalipour, “RIS-assisted jamming rejection and path planning for UAV-borne IoT platform: A new deep reinforcement learning framework,” IEEE Internet Things J., 2023, early access.
  40. R. Saleem, W. Ni, M. Ikram, and A. Jamalipour, “Deep-reinforcement-learning-driven secrecy design for intelligent-reflecting-surface-based 6G-IoT networks,” IEEE Internet Things J., vol. 10, no. 10, pp. 8812–8824, 2023.
  41. Y. Cao, T. Lv, and W. Ni, “Intelligent reflecting surface aided multi-user mmWave communications for coverage enhancement,” in Proc. IEEE Int. Symp. Pers. Indoor Mob. Radio Commun. (PIMRC), pp. 1–6, 2020.
  42. C. Sun, W. Ni, Z. Bu, and X. Wang, “Energy minimization for intelligent reflecting surface-assisted mobile edge computing,” in Proc. IEEE Int. Conf. Commun. China (ICCC), pp. 254–259, 2021.
  43. X. Yuan, S. Hu, W. Ni, R. P. Liu, and X. Wang, “Joint user, channel, modulation-coding selection, and RIS configuration for jamming resistance in multiuser OFDMA systems,” IEEE Trans. Commun., vol. 71, no. 3, pp. 1631–1645, 2023.
  44. Y. Cao, T. Lv, and W. Ni, “Two-timescale optimization for intelligent reflecting surface-assisted MIMO transmission in fast-changing channels,” IEEE Trans. Wireless Commun., vol. 21, no. 12, pp. 10424–10437, 2022.
  45. Y. Cao, T. Lv, Z. Lin, and W. Ni, “Delay-constrained joint power control, user detection and passive beamforming in intelligent reflecting surface-assisted uplink mmWave system,” IEEE Trans. Cognit. Commun. Networking, vol. 7, no. 2, pp. 482–495, 2021.
  46. C. Sun, W. Ni, Z. Bu, and X. Wang, “Energy minimization for intelligent reflecting surface-assisted mobile edge computing,” IEEE Trans. Wireless Commun., vol. 21, no. 8, pp. 6329–6344, 2022.
  47. Z. Wang, J. Qiu, Y. Zhou, Y. Shi, L. Fu, W. Chen, and K. B. Letaief, “Federated learning via intelligent reflecting surface,” IEEE Trans. Wireless Commun., vol. 21, no. 2, pp. 808–822, 2022.
  48. H. Liu, X. Yuan, and Y.-J. A. Zhang, “Reconfigurable intelligent surface enabled federated learning: A unified communication-learning design approach,” IEEE Trans. Wireless Commun., vol. 20, no. 11, pp. 7595–7609, 2021.
  49. W. Fang, Y. Jiang, Y. Shi, Y. Zhou, W. Chen, and K. B. Letaief, “Over-the-air computation via reconfigurable intelligent surface,” IEEE Trans. Commun., vol. 69, no. 12, pp. 8612–8626, 2021.
  50. W. Zhang, J. Xu, W. Xu, X. You, and W. Fu, “Worst-case design for RIS-aided over-the-air computation with imperfect CSI,” IEEE Commun. Lett., vol. 26, no. 9, pp. 2136–2140, 2022.
  51. X. Zhai, G. Han, Y. Cai, and L. Hanzo, “Beamforming design based on two-stage stochastic optimization for RIS-assisted over-the-air computation systems,” IEEE Internet Things J., vol. 9, no. 7, pp. 5474–5488, 2022.
  52. J. Li, Y. Wu, and Y. Shi, “Reconfigurable intelligent surface assisted over-the-air computation in multi-cell networks,” in Proc. IEEE Int. Mediterr. Conf. Commun. Networking (MeditCom), pp. 43–48, 2022.
  53. X. Zhai, G. Han, Y. Cai, and L. Hanzo, “Joint beamforming aided over-the-air computation systems relying on both BS-side and user-side reconfigurable intelligent surfaces,” IEEE Trans. Wireless Commun., vol. 21, no. 12, pp. 10766–10779, 2022.
  54. Y. Hu, M. Chen, M. Chen, Z. Yang, M. Shikh-Bahaei, H. V. Poor, and S. Cui, “Energy minimization for federated learning with IRS-assisted over-the-air computation,” in Proc. IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP), pp. 3105–3109, 2021.
  55. L. Hu, Z. Wang, H. Zhu, and Y. Zhou, “RIS-assisted over-the-air federated learning in millimeter wave MIMO networks,” J. Commun. Inf. Networks, vol. 7, no. 2, pp. 145–156, 2022.
  56. J. Li, M. Fu, Y. Zhou, and Y. Shi, “Double-RIS assisted over-the-air computation,” in Proc. IEEE GC Wkshps, pp. 1–6, 2021.
  57. P. Kairouz, H. B. McMahan, B. Avent, A. Bellet, M. Bennis, A. N. Bhagoji, K. Bonawitz, Z. Charles, G. Cormode, R. Cummings, et al., “Advances and open problems in federated learning,” Found. Trends Mach. Learn., vol. 14, no. 1–2, pp. 1–210, 2021.
  58. C. Ma, J. Li, M. Ding, H. H. Yang, F. Shu, T. Q. S. Quek, and H. V. Poor, “On safeguarding privacy and security in the framework of federated learning,” IEEE Network, vol. 34, no. 4, pp. 242–248, 2020.
  59. RAND Corporation, 2011.
  60. S. A. Siddiqui, A. Mahmood, Q. Z. Sheng, H. Suzuki, and W. Ni, “Trust in vehicles: Toward context-aware trust and attack resistance for the Internet of Vehicles,” IEEE Trans. Intell. Transp. Syst., pp. 1–15, 2023, early access.
  61. X. Bao, C. Su, Y. Xiong, W. Huang, and Y. Hu, “FLChain: A blockchain for auditable federated learning with trust and incentive,” in Proc. Int. Conf. Big Data Comput. Commun. (BIGCOM), pp. 151–159, 2019.
  62. S. Huang, Y. Zhou, T. Wang, and Y. Shi, “Byzantine-resilient federated machine learning via over-the-air computation,” in Proc. IEEE ICC Wkshps, pp. 1–6, IEEE, 2021.
  63. C. Fung, C. J. Yoon, and I. Beschastnikh, “Mitigating sybils in federated learning poisoning,” arXiv preprint arXiv:1808.04866, 2018.
  64. Y. Wang, T. Li, S. Li, X. Yuan, and W. Ni, “New adversarial image detection based on sentiment analysis,” IEEE Trans. Neural Networks Learn. Syst., pp. 1–15, 2023, early access.
  65. Y. Wang, M. Zhao, S. Li, X. Yuan, and W. Ni, “Dispersed pixel perturbation-based imperceptible backdoor trigger for image classifier models,” IEEE Trans. Inf. Forensics Secur., vol. 17, pp. 3091–3106, 2022.
  66. A. N. Bhagoji, S. Chakraborty, P. Mittal, and S. Calo, “Analyzing federated learning through an adversarial lens,” in Int. Conf. Mach. Learn., pp. 634–643, PMLR, 2019.
  67. H. Sifaou and G. Y. Li, “Over-the-air federated learning under Byzantine attacks,” arXiv preprint arXiv:2205.02949, 2022.
  68. X. Fan, Y. Wang, Y. Huo, and Z. Tian, “BEV-SGD: Best effort voting SGD against byzantine attacks for analog-aggregation-based federated learning over the air,” IEEE Internet Things J., vol. 9, no. 19, pp. 18946–18959, 2022.
  69. M. Seif, R. Tandon, and M. Li, “Wireless federated learning with local differential privacy,” in Proc. IEEE Int. Symp. Inf. Theory (ISIT), pp. 2604–2609, 2020.
  70. D. Liu and O. Simeone, “Privacy for free: Wireless federated learning via uncoded transmission with adaptive power control,” IEEE J. Sel. Areas Commun., vol. 39, no. 1, pp. 170–185, 2021.
  71. Y. Koda, K. Yamamoto, T. Nishio, and M. Morikura, “Differentially private aircomp federated learning with power adaptation harnessing receiver noise,” in Proc. IEEE Global Commun. Conf. (GLOBECOM), pp. 1–6, 2020.
  72. N. Yan, K. Wang, C. Pan, and K. K. Chai, “Private federated learning with misaligned power allocation via over-the-air computation,” IEEE Commun. Lett., vol. 26, no. 9, pp. 1994–1998, 2022.
  73. J. Liao, Z. Chen, and E. G. Larsson, “Over-the-air federated learning with privacy protection via correlated additive perturbations,” in Proc. Annu. Allerton Conf. Commun. Control Comput. (Allerton), pp. 1–8, 2022.
  74. B. Hasırcıoğlu and D. Gündüz, “Private wireless federated learning with anonymous over-the-air computation,” in Proc. IEEE Int. Conf. Acoust. Speech Signal Process. (ICASSP), pp. 5195–5199, 2021.
  75. A. Elgabli, J. Park, C. B. Issaid, and M. Bennis, “Harnessing wireless channels for scalable and privacy-preserving federated learning,” IEEE Trans. Commun., vol. 69, no. 8, pp. 5194–5208, 2021.
  76. A. Sonee, S. Rini, and Y. Huang, “Wireless federated learning with limited communication and differential privacy,” in Proc. IEEE Global Commun. Conf. (GLOBECOM), pp. 01–06, 2021.
  77. X. Xue, M. K. Hasan, S. Yu, L. N. Kandel, and M. Song, “Over-the-air federated learning with enhanced privacy,” arXiv preprint arXiv:2212.11486, 2022.
  78. N. Yan, K. Wang, K. Zhi, C. Pan, K. K. Chai, and H. V. Poor, “Toward secure and private over-the-air federated learning,” arXiv preprint arXiv:2210.07669, 2022.
  79. G. Yu, X. Wang, C. Sun, P. Yu, W. Ni, and R. P. Liu, “Obfuscating the dataset: Impacts and applications,” ACM Trans. Intell. Syst. Technol., 2023.
  80. X. Yuan, W. Ni, M. Ding, K. Wei, J. Li, and H. V. Poor, “Amplitude-varying perturbation for balancing privacy and utility in federated learning,” IEEE Trans. Inf. Forensics Secur., vol. 18, pp. 1884–1897, 2023.
  81. R. Shokri, M. Stronati, C. Song, and V. Shmatikov, “Membership inference attacks against machine learning models,” in Proc. IEEE Symp. Secur. Privacy (S&P), pp. 3–18, 2017.
  82. L. Melis, C. Song, E. De Cristofaro, and V. Shmatikov, “Exploiting unintended feature leakage in collaborative learning,” in Proc. IEEE Symp. Secur. Privacy (S&P), pp. 691–706, 2019.
  83. M. Fredrikson, S. Jha, and T. Ristenpart, “Model inversion attacks that exploit confidence information and basic countermeasures,” in Proc. ACM SIGSAC Conf. Comput. Commun. Secur., pp. 1322–1333, 2015.
  84. M. Abadi, A. Chu, I. Goodfellow, H. B. McMahan, I. Mironov, K. Talwar, and L. Zhang, “Deep learning with differential privacy,” in Proc. ACM SIGSAC Conf. Comput. Commun. Secur., pp. 308–318, 2016.
  85. C. Dwork, A. Roth, et al., “The algorithmic foundations of differential privacy,” Foundations and Trends® in Theoretical Computer Science, vol. 9, no. 3–4, pp. 211–407, 2014.
  86. K. Wei, J. Li, M. Ding, C. Ma, H. H. Yang, F. Farokhi, S. Jin, T. Q. S. Quek, and H. V. Poor, “Federated learning with differential privacy: Algorithms and performance analysis,” IEEE Trans. Inf. Forensics Secur., vol. 15, pp. 3454–3469, 2020.
  87. H. H. Yang, Z. Chen, T. Q. S. Quek, and H. V. Poor, “Revisiting analog over-the-air machine learning: The blessing and curse of interference,” IEEE J. Sel. Top. Signal Process., vol. 16, no. 3, pp. 406–419, 2022.
  88. N. Zhang, M. Tao, J. Wang, and S. Shao, “Coded over-the-air computation for model aggregation in federated learning,” IEEE Commun. Lett., vol. 27, no. 1, pp. 160–164, 2023.
  89. M. Goldenbaum and S. Stanczak, “Robust analog function computation via wireless multiple-access channels,” IEEE Trans. Commun., vol. 61, no. 9, pp. 3863–3877, 2013.
  90. Q. Li, Y. Diao, Q. Chen, and B. He, “Federated learning on non-IID data silos: An experimental study,” in Proc. IEEE ICDE, pp. 965–978, 2022.
  91. S. Hu, X. Chen, W. Ni, E. Hossain, and X. Wang, “Distributed machine learning for wireless communication networks: Techniques, architectures, and applications,” IEEE Commun. Surv. Tutorials, vol. 23, no. 3, pp. 1458–1493, 2021.
  92. Y. Qu, X. Yuan, M. Ding, W. Ni, T. Rakotoarivelo, and D. Smith, “Learn to unlearn: A survey on machine unlearning,” arXiv preprint arXiv:2305.07512, 2023.
Citations (15)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now