Papers
Topics
Authors
Recent
Search
2000 character limit reached

Fairness-Aware Multi-Server Federated Learning Task Delegation over Wireless Networks

Published 14 Mar 2024 in eess.SY and cs.SY | (2403.09153v1)

Abstract: In the rapidly advancing field of federated learning (FL), ensuring efficient FL task delegation while incentivising FL client participation poses significant challenges, especially in wireless networks where FL participants' coverage is limited. Existing Contract Theory-based methods are designed under the assumption that there is only one FL server in the system (i.e., the monopoly market assumption), which in unrealistic in practice. To address this limitation, we propose Fairness-Aware Multi-Server FL task delegation approach (FAMuS), a novel framework based on Contract Theory and Lyapunov optimization to jointly address these intricate issues facing wireless multi-server FL networks (WMSFLN). Within a given WMSFLN, a task requester products multiple FL tasks and delegate them to FL servers which coordinate the training processes. To ensure fair treatment of FL servers, FAMuS establishes virtual queues to track their previous access to FL tasks, updating them in relation to the resulting FL model performance. The objective is to minimize the time-averaged cost in a WMSFLN, while ensuring all queues remain stable. This is particularly challenging given the incomplete information regarding FL clients' participation cost and the unpredictable nature of the WMSFLN state, which depends on the locations of the mobile clients. Extensive experiments comparing FAMuS against five state-of-the-art approaches based on two real-world datasets demonstrate that it achieves 6.91% higher test accuracy, 27.34% lower cost, and 0.63% higher fairness on average than the best-performing baseline.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (42)
  1. Y. Shi, H. Yu, and C. Leung, “Towards fairness-aware federated learning,” IEEE Transactions on Neural Networks and Learning Systems, 2023.
  2. H. Fourati, R. Maaloul, and L. Chaari, “A survey of 5g network systems: challenges and machine learning approaches,” International Journal of Machine Learning and Cybernetics, vol. 12, pp. 385–431, 2021.
  3. P. Voigt and A. Von dem Bussche, “The eu general data protection regulation (gdpr),” A Practical Guide, 1st Ed., Cham: Springer International Publishing, vol. 10, no. 3152676, pp. 10–5555, 2017.
  4. 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,” Foundations and Trends® in Machine Learning, vol. 14, no. 1–2, pp. 1–210, 2021.
  5. L. Lyu, H. Yu, X. Ma, C. Chen, L. Sun, J. Zhao, Q. Yang, and P. S. Yu, “Privacy and robustness in federated learning: Attacks and defense,” IEEE Transactions on Neural Networks and Learning Systems, 2022.
  6. Q. Yang, Y. Liu, T. Chen, and Y. Tong, “Federated machine learning: Concept and applications,” ACM Transactions on Intelligent Systems and Technology, vol. 10, no. 2, pp. 12:1–12:19, 2019.
  7. S. Niknam, H. S. Dhillon, and J. H. Reed, “Federated learning for wireless communications: Motivation, opportunities, and challenges,” IEEE Communications Magazine, vol. 58, no. 6, pp. 46–51, 2020.
  8. Y. Liu, X. Yuan, Z. Xiong, J. Kang, X. Wang, and D. Niyato, “Federated learning for 6g communications: Challenges, methods, and future directions,” China Communications, vol. 17, no. 9, pp. 105–118, 2020.
  9. N. H. Tran, W. Bao, A. Zomaya, M. N. Nguyen, and C. S. Hong, “Federated learning over wireless networks: Optimization model design and analysis,” in IEEE INFOCOM 2019-IEEE conference on computer communications.   IEEE, 2019, pp. 1387–1395.
  10. J. Pang, J. Yu, R. Zhou, and J. C. Lui, “An incentive auction for heterogeneous client selection in federated learning,” IEEE Transactions on Mobile Computing, 2022.
  11. C. Ma, J. Konečnỳ, M. Jaggi, V. Smith, M. I. Jordan, P. Richtárik, and M. Takáč, “Distributed optimization with arbitrary local solvers,” optimization Methods and Software, vol. 32, no. 4, pp. 813–848, 2017.
  12. R. Zeng, C. Zeng, X. Wang, B. Li, and X. Chu, “A comprehensive survey of incentive mechanism for federated learning,” arXiv preprint arXiv:2106.15406, 2021.
  13. M. Dai, Z. Su, Y. Wang, and Q. Xu, “Contract theory based incentive scheme for mobile crowd sensing networks,” in 2018 international conference on selected topics in Mobile and wireless networking (MoWNeT).   IEEE, 2018, pp. 1–5.
  14. W. Y. B. Lim, Z. Xiong, C. Miao, D. Niyato, Q. Yang, C. Leung, and H. V. Poor, “Hierarchical incentive mechanism design for federated machine learning in mobile networks,” IEEE Internet of Things Journal, vol. 7, no. 10, pp. 9575–9588, 2020.
  15. J. Kang, Z. Xiong, D. Niyato, H. Yu, Y.-C. Liang, and D. I. Kim, “Incentive design for efficient federated learning in mobile networks: A contract theory approach,” in 2019 IEEE VTS Asia Pacific Wireless Communications Symposium (APWCS).   IEEE, 2019, pp. 1–5.
  16. J. Kang, Z. Xiong, D. Niyato, S. Xie, and J. Zhang, “Incentive mechanism for reliable federated learning: A joint optimization approach to combining reputation and contract theory,” IEEE Internet of Things Journal, vol. 6, no. 6, pp. 10 700–10 714, 2019.
  17. N. Ding, Z. Fang, and J. Huang, “Incentive mechanism design for federated learning with multi-dimensional private information,” in 2020 18th International Symposium on Modeling and Optimization in Mobile, Ad Hoc, and Wireless Networks (WiOPT).   IEEE, 2020, pp. 1–8.
  18. J. Lu, H. Liu, Z. Zhang, J. Wang, S. K. Goudos, and S. Wan, “Toward fairness-aware time-sensitive asynchronous federated learning for critical energy infrastructure,” IEEE Transactions on Industrial Informatics, vol. 18, no. 5, pp. 3462–3472, 2021.
  19. J. Weng, J. Weng, H. Huang, C. Cai, and C. Wang, “Fedserving: A federated prediction serving framework based on incentive mechanism,” in IEEE INFOCOM 2021-IEEE Conference on Computer Communications.   IEEE, 2021, pp. 1–10.
  20. R. Zeng, S. Zhang, J. Wang, and X. Chu, “Fmore: An incentive scheme of multi-dimensional auction for federated learning in mec,” in 2020 IEEE 40th international conference on distributed computing systems (ICDCS).   IEEE, 2020, pp. 278–288.
  21. X. Bao, C. Su, Y. Xiong, W. Huang, and Y. Hu, “Flchain: A blockchain for auditable federated learning with trust and incentive,” in 2019 5th International Conference on Big Data Computing and Communications (BIGCOM).   IEEE, 2019, pp. 151–159.
  22. S. R. Pandey, N. H. Tran, M. Bennis, Y. K. Tun, A. Manzoor, and C. S. Hong, “A crowdsourcing framework for on-device federated learning,” IEEE Transactions on Wireless Communications, vol. 19, no. 5, pp. 3241–3256, 2020.
  23. W. Y. B. Lim, J. S. Ng, Z. Xiong, J. Jin, Y. Zhang, D. Niyato, C. Leung, and C. Miao, “Decentralized edge intelligence: A dynamic resource allocation framework for hierarchical federated learning,” IEEE Transactions on Parallel and Distributed Systems, vol. 33, no. 3, pp. 536–550, 2021.
  24. T. H. T. Le, N. H. Tran, Y. K. Tun, Z. Han, and C. S. Hong, “Auction based incentive design for efficient federated learning in cellular wireless networks,” in 2020 IEEE Wireless Communications and Networking Conference (WCNC).   IEEE, 2020, pp. 1–6.
  25. Y. Deng, F. Lyu, J. Ren, Y.-C. Chen, P. Yang, Y. Zhou, and Y. Zhang, “Fair: Quality-aware federated learning with precise user incentive and model aggregation,” in IEEE INFOCOM 2021-IEEE Conference on Computer Communications.   IEEE, 2021, pp. 1–10.
  26. Y. Jiao, P. Wang, D. Niyato, B. Lin, and D. I. Kim, “Toward an automated auction framework for wireless federated learning services market,” IEEE Transactions on Mobile Computing, vol. 20, no. 10, pp. 3034–3048, 2020.
  27. K. Toyoda and A. N. Zhang, “Mechanism design for an incentive-aware blockchain-enabled federated learning platform,” in 2019 IEEE international conference on big data (Big Data).   IEEE, 2019, pp. 395–403.
  28. W. Y. B. Lim, J. Huang, Z. Xiong, J. Kang, D. Niyato, X.-S. Hua, C. Leung, and C. Miao, “Towards federated learning in uav-enabled internet of vehicles: A multi-dimensional contract-matching approach,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 8, pp. 5140–5154, 2021.
  29. N. Zhang, Q. Ma, and X. Chen, “Enabling long-term cooperation in cross-silo federated learning: A repeated game perspective,” IEEE Transactions on Mobile Computing, 2022.
  30. Y. Shi, Z. Liu, Z. Shi, and H. Yu, “Fairness-aware client selection for federated learning,” in 2023 IEEE International Conference on Multimedia and Expo (ICME).   IEEE, 2023, pp. 324–329.
  31. A. Josang and R. Ismail, “The beta reputation system,” in Proceedings of the 15th bled electronic commerce conference, vol. 5.   Citeseer, 2002, pp. 2502–2511.
  32. Y. Zhang, M. Pan, L. Song, Z. Dawy, and Z. Han, “A survey of contract theory-based incentive mechanism design in wireless networks,” IEEE wireless communications, vol. 24, no. 3, pp. 80–85, 2017.
  33. J. Du, E. Gelenbe, C. Jiang, H. Zhang, and Y. Ren, “Contract design for traffic offloading and resource allocation in heterogeneous ultra-dense networks,” IEEE Journal on Selected Areas in Communications, vol. 35, no. 11, pp. 2457–2467, 2017.
  34. A. Asheralieva and Y. Miyanaga, “Optimal contract design for joint user association and intercell interference mitigation in heterogeneous lte-a networks with asymmetric information,” IEEE Transactions on Vehicular Technology, vol. 66, no. 6, pp. 5284–5300, 2016.
  35. W. Y. B. Lim, S. Garg, Z. Xiong, D. Niyato, C. Leung, C. Miao, and M. Guizani, “Dynamic contract design for federated learning in smart healthcare applications,” IEEE Internet of Things Journal, vol. 8, no. 23, pp. 16 853–16 862, 2020.
  36. M. J. Neely and S. Supittayapornpong, “Dynamic markov decision policies for delay constrained wireless scheduling,” IEEE Transactions on Automatic Control, vol. 58, no. 8, pp. 1948–1961, 2013.
  37. J. G. Andrews, F. Baccelli, and R. K. Ganti, “A tractable approach to coverage and rate in cellular networks,” IEEE Transactions on communications, vol. 59, no. 11, pp. 3122–3134, 2011.
  38. Z. Zheng, L. Song, Z. Han, G. Y. Li, and H. V. Poor, “A stackelberg game approach to proactive caching in large-scale mobile edge networks,” IEEE Transactions on Wireless Communications, vol. 17, no. 8, pp. 5198–5211, 2018.
  39. Y. Gao, Y. Xiao, M. Wu, M. Xiao, and J. Shao, “Dynamic social-aware peer selection for cooperative relay management with d2d communications,” IEEE Transactions on Communications, vol. 67, no. 5, pp. 3124–3139, 2019.
  40. A. Hoglund, D. P. Van, T. Tirronen, O. Liberg, Y. Sui, and E. A. Yavuz, “3gpp release 15 early data transmission,” IEEE Communications Standards Magazine, vol. 2, no. 2, pp. 90–96, 2018.
  41. B. McMahan, E. Moore, D. Ramage, S. Hampson, and B. A. y Arcas, “Communication-efficient learning of deep networks from decentralized data,” in Artificial intelligence and statistics.   PMLR, 2017, pp. 1273–1282.
  42. R. K. Jain, D.-M. W. Chiu, W. R. Hawe et al., “A quantitative measure of fairness and discrimination,” Eastern Research Laboratory, Digital Equipment Corporation, Hudson, MA, vol. 21, 1984.

Summary

No one has generated a summary of this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Summarize

Paper to Video (Beta)

Whiteboard

No one has generated a whiteboard explanation for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Sign Up to Generate

Open Problems

We haven't generated a list of open problems mentioned in this paper yet.

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

Continue Learning

We haven't generated follow-up questions for this paper yet.

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

Authors (3)

  1. Yulan Gao 
  2. Chao Ren 
  3. Han Yu 

Collections

Sign up for free to add this paper to one or more collections.

User Circle Single Streamline Icon: https://streamlinehq.com Sign Up