FedNow: An Efficiency-Aware Incentive Mechanism Enables Privacy Protection and Efficient Resource Utilization in Federated Edge Learning
Source abstract
Abstract
Federated edge learning (FEL) has recently attracted great interest due to its real-time response and energy-efficient characteristics. Most existing work focuses on designing algorithms to improve model performance, ignoring the malicious behavior and personal decision-making of self-interested edge servers. Although some efforts have been devoted to incentivizing honest edge server engagement by compensating training costs, this rarely considers resource efficiency and often assumes that edge servers provide complete information to the platform, which may lead to the risk of private attribute leakage. Hence, we aim to achieve an incentive mechanism that promotes secure and efficient model training between the platform and edge servers. However, edge servers’ multi-dimensional private attributes and training strategies make the optimization problem nonconvex, and incomplete information further increases the complexity of the analysis. In order to address these challenges and by integrating contract theory and exponential mechanism, we propose an efficiency-aware incentive mechanism, FedNow, which enables edge servers to personally determine their local training rounds while motivating their participation without giving access to their true training strategies and private attributes. Specifically, we enabld edge servers to add noise to their submitted training strategy to hide their true training rounds; then, we carefully designed an efficiency score function to select honest and efficient edge servers without disclosing their private attributes. In order to demonstrate that FedNow strictly outperforms existing schemes in terms of total costs, we theoretically derived sufficient conditions for making the total costs of FedNow lower than existing schemes and designed a greedy algorithm that uses the Monte Carlo method to find feasible near-optimal solutions in polynomial time. Our extensive experimental assessment using synthetic and real datasets shows the superiority of FedNow.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Privacy-Preserving Technologies in Data · Mobile Crowdsensing and Crowdsourcing · Stochastic Gradient Optimization Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Science and Technology, Wuhan University of Science and Technology, Wuhan 430065, China
School of Cyber Science and Engineering, Huazhong University of Science and Technology, Wuhan 430074, China
Funding
National Natural Science Foundation of China · Zhejiang Provincial Natural Science Foundation of China · Key Research and Development Program of Hubei Province · Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System (Wuhan University of Science and Technology)
References (44)
Show source-provided references
1. A survey on wearable sensor-based systems for health monitoring and prognosis10.1109/TSMCC.2009.2032660 ↗
2. Anguita, D., Ghio, A., Oneto, L., Parra, X., and Reyes-Ortiz, J.L. (2013, January 24–26). A public domain dataset for human activity recognition using smartphones. Proceedings of the Esann, Bruges, Belgium.
3. Toward an intelligent edge: Wireless communication meets machine learning10.1109/MCOM.001.1900103 ↗
4. Adaptive batch size for federated learning in resource-constrained edge computing10.1109/TMC.2021.3075291 ↗
5. Federated learning for data privacy preservation in vehicular cyber-physical systems10.1109/MNET.011.1900317 ↗
6. Xiao, Y., Zhang, X., Li, Y., Shi, G., Krunz, M., Nguyen, D.N., and Hoang, D.T. (2023). Time-sensitive learning for heterogeneous federated edge intelligence. IEEE Trans. Mob. Comput., early access.10.1109/TMC.2023.3237374 ↗
7. Hfel: Joint edge association and resource allocation for cost-efficient hierarchical federated edge learning10.1109/TWC.2020.3003744 ↗
8. Lyu, L., and Chen, C. (2021). A novel attribute reconstruction attack in federated learning. arXiv.
9. Characterizing application scheduling on edge, fog, and cloud computing resources10.1002/spe.2699 ↗
10. Stich, S.U. (2018). Local sgd converges fast and communicates little. arXiv.
11. Liu, B., Shen, W., Li, P., and Zhu, X. (2019, January 14–19). Accelerate mini-batch machine learning training with dynamic batch size fitting. Proceedings of the 2019 International Joint Conference on Neural Networks (IJCNN), Budapest, Hungary.10.1109/IJCNN.2019.8851944 ↗
12. More effective distributed ml via a stale synchronous parallel parameter server
13. An adaptive synchronous parallel strategy for distributed machine learning10.1109/ACCESS.2018.2820899 ↗
14. Chen, C., Wang, W., and Li, B. (May, January 29). Round-robin synchronization: Mitigating communication bottlenecks in parameter servers. Proceedings of the IEEE INFOCOM 2019—IEEE Conference on Computer Communications, Paris, France.10.1109/INFOCOM.2019.8737587 ↗
15. Adaptive federated learning in resource constrained edge computing systems10.1109/JSAC.2019.2904348 ↗
16. Tran, N.H., Bao, W., Zomaya, A., Nguyen, M.N., and Hong, C.S. (May, January 29). Federated learning over wireless networks: Optimization model design and analysis. Proceedings of the IEEE INFOCOM 2019—IEEE Conference on Computer Communications, Paris, France.10.1109/INFOCOM.2019.8737464 ↗
17. Zeng, R., Zhang, S., Wang, J., and Chu, X. (December, January 29). Fmore: An incentive scheme of multi-dimensional auction for federated learning in mec. Proceedings of the 2020 IEEE 40th International Conference on Distributed Computing Systems (ICDCS), Singapore.10.1109/ICDCS47774.2020.00094 ↗
18. Incentive mechanism for reliable federated learning: A joint optimization approach to combining reputation and contract theory10.1109/JIOT.2019.2940820 ↗
19. Tang, M., and Wong, V.W. (2021, January 10–13). An incentive mechanism for cross-silo federated learning: A public goods perspective. Proceedings of the IEEE INFOCOM 2021—IEEE Conference on Computer Communications, Vancouver, BC, Canada.10.1109/INFOCOM42981.2021.9488705 ↗
20. Federated learning with fair incentives and robust aggregation for uav-aided crowdsensing10.1109/TNSE.2021.3138928 ↗
21. Toward self-learning edge intelligence in 6g10.1109/MCOM.001.2000388 ↗
22. Cipar, J., Ho, Q., Kim, J.K., Lee, S., Ganger, G.R., Gibson, G., Keeton, K., and Xing, E. (2013, January 13–15). Solving the straggler problem with bounded staleness. Proceedings of the 14th Workshop on Hot Topics in Operating Systems (HotOS XIV), Santa Ana Pueblo, NM, USA.
23. Tyagi, S., and Sharma, P. (2020, January 17–21). Taming resource heterogeneity in distributed ml training with dynamic batching. Proceedings of the 2020 IEEE International Conference on Autonomic Computing and Self-Organizing Systems (ACSOS), Washington, DC, USA.10.1109/ACSOS49614.2020.00041 ↗
24. Ye, Q., Zhou, Y., Shi, M., Sun, Y., and Lv, J. (2020). Dbs: Dynamic batch size for distributed deep neural network training. arXiv.
25. Multi-armed bandit-based client scheduling for federated learning10.1109/TWC.2020.3008091 ↗
26. Shi, W., Zhou, S., and Niu, Z. (2020, January 7–11). Device scheduling with fast convergence for wireless federated learning. Proceedings of the ICC 2020—2020 IEEE International Conference on Communications (ICC), Dublin, Ireland.10.1109/ICC40277.2020.9149138 ↗
27. Chen, M., Poor, H.V., Saad, W., and Cui, S. (2020, January 7–11). Convergence time minimization of federated learning over wireless networks. Proceedings of the ICC 2020—2020 IEEE International Conference on Communications (ICC), Dublin, Ireland.10.1109/ICC40277.2020.9148815 ↗
28. Feng, S., Niyato, D., Wang, P., Kim, D.I., and Liang, Y.-C. (2019, January 14–17). Joint service pricing and cooperative relay communication for federated learning. Proceedings of the 2019 International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData), Atlanta, GA, USA.10.1109/iThings/GreenCom/CPSCom/SmartData.2019.00148 ↗
29. Motivating workers in federated learning: A stackelberg game perspective10.1109/LNET.2019.2947144 ↗
30. Optimal contract design for efficient federated learning with multi-dimensional private information10.1109/JSAC.2020.3036944 ↗
31. McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B.A. (2017, January 20–22). Communication-efficient learning of deep networks from decentralized data. Proceedings of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) 2017, Fort Lauderdale, FL, USA.
32. A pi consensus controller for networked clocks synchronization10.3182/20080706-5-KR-1001.01741 ↗
33. Privaim: A dual-privacy preserving and quality-aware incentive mechanism for federated learning
34. Ding, N., Gao, L., and Huang, J. (2023, January 17–20). Joint participation incentive and network pricing design for federated learning. Proceedings of the IEEE INFOCOM 2023—IEEE Conference on Computer Communications, New York City, NY, USA.10.1109/INFOCOM53939.2023.10229084 ↗
35. Li, M., Zhang, T., Chen, Y., and Smola, A.J. (2014, January 24–27). Efficient mini-batch training for stochastic optimization. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.10.1145/2623330.2623612 ↗
36. Optimal distributed online prediction using mini-batches
37. Infedge: A blockchain-based incentive mechanism in hierarchical federated learning for end-edge-cloud communications10.1109/JSAC.2022.3213323 ↗
38. Lu, J., Liu, H., Jia, R., Zhang, Z., Wang, X., and Wang, J. (2023). Incentivizing proportional fairness for multi-task allocation in crowdsensing. IEEE Trans. Serv. Comput.10.1109/TSC.2023.3325636 ↗
39. Towards personalized federated learning via group collaboration in iiot10.1109/TII.2022.3223234 ↗
40. Toward fairness-aware time-sensitive asynchronous federated learning for critical energy infrastructure10.1109/TII.2021.3117861 ↗
41. Ying, C., Jin, H., Wang, X., and Luo, Y. (2020, January 21–24). Double insurance: Incentivized federated learning with differential privacy in mobile crowdsensing. Proceedings of the 2020 International Symposium on Reliable Distributed Systems (SRDS), Shanghai, China.10.1109/SRDS51746.2020.00016 ↗
42. An efficiency-boosting client selection scheme for federated learning with fairness guarantee
43. Distributed optimization with arbitrary local solvers10.1080/10556788.2016.1278445 ↗
44. Eiffel: Efficient and fair scheduling in adaptive federated learning10.1109/TPDS.2022.3187365 ↗