Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
119 tokens/sec
GPT-4o
56 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
6 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

An Auction-based Marketplace for Model Trading in Federated Learning (2402.01802v1)

Published 2 Feb 2024 in cs.LG, cs.AI, and cs.GT

Abstract: Federated learning (FL) is increasingly recognized for its efficacy in training models using locally distributed data. However, the proper valuation of shared data in this collaborative process remains insufficiently addressed. In this work, we frame FL as a marketplace of models, where clients act as both buyers and sellers, engaging in model trading. This FL market allows clients to gain monetary reward by selling their own models and improve local model performance through the purchase of others' models. We propose an auction-based solution to ensure proper pricing based on performance gain. Incentive mechanisms are designed to encourage clients to truthfully reveal their model valuations. Furthermore, we introduce a reinforcement learning (RL) framework for marketing operations, aiming to achieve maximum trading volumes under the dynamic and evolving market status. Experimental results on four datasets demonstrate that the proposed FL market can achieve high trading revenue and fair downstream task accuracy.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (57)
  1. Leaf: A benchmark for federated settings. arXiv preprint arXiv:1812.01097, 2018.
  2. A vcg-based fair incentive mechanism for federated learning. arXiv preprint arXiv:2008.06680, 2020.
  3. Fair: Quality-aware federated learning with precise user incentive and model aggregation. In IEEE INFOCOM 2021-IEEE Conference on Computer Communications, pp.  1–10. IEEE, 2021.
  4. Heterofl: Computation and communication efficient federated learning for heterogeneous clients. arXiv preprint arXiv:2010.01264, 2020.
  5. Optimal contract design for efficient federated learning with multi-dimensional private information. IEEE J. Sel. Areas Commun., 39(1):186–200, 2021.
  6. Joint service pricing and cooperative relay communication for federated learning. In 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), iThings/GreenCom/CPSCom/SmartData 2019, Atlanta, GA, USA, July 14-17, 2019, pp.  815–820. IEEE, 2019.
  7. TIFF: tokenized incentive for federated learning. In IEEE 15th International Conference on Cloud Computing, CLOUD 2022, Barcelona, Spain, July 10-16, 2022, pp.  407–416. IEEE, 2022.
  8. Federated learning for mobile keyboard prediction. arXiv preprint arXiv:1811.03604, 2018.
  9. Measuring the effects of non-identical data distribution for federated visual classification. arXiv preprint arXiv:1909.06335, 2019.
  10. Trading data for learning: Incentive mechanism for on-device federated learning. In IEEE Global Communications Conference, GLOBECOM 2020, Virtual Event, Taiwan, December 7-11, 2020, pp.  1–6. IEEE, 2020. doi: 10.1109/GLOBECOM42002.2020.9322475. URL https://doi.org/10.1109/GLOBECOM42002.2020.9322475.
  11. An exploratory analysis on users’ contributions in federated learning. In Second IEEE International Conference on Trust, Privacy and Security in Intelligent Systems and Applications, TPS-ISA 2020, Atlanta, GA, USA, October 28-31, 2020, pp.  20–29. IEEE, 2020.
  12. Reinforcement learning: A survey. Journal of artificial intelligence research, 4:237–285, 1996.
  13. Mechanisms that incentivize data sharing in federated learning. arXiv preprint arXiv:2207.04557, 2022.
  14. Federated optimization: Distributed machine learning for on-device intelligence. arXiv preprint arXiv:1610.02527, 2016.
  15. Krishna, V. Auction theory. Academic press, 2009.
  16. Learning multiple layers of features from tiny images. 2009.
  17. Auction based incentive design for efficient federated learning in cellular wireless networks. In 2020 IEEE Wireless Communications and Networking Conference, WCNC 2020, Seoul, Korea (South), May 25-28, 2020, pp.  1–6. IEEE, 2020.
  18. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11):2278–2324, 1998.
  19. Federated learning for keyword spotting. In Proc. of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP’19), pp.  6341–6345, 2019.
  20. Federated learning on non-iid data silos: An experimental study. In 2022 IEEE 38th International Conference on Data Engineering (ICDE), pp.  965–978. IEEE, 2022.
  21. Vertical federated learning: Taxonomies, threats, and prospects. arXiv preprint arXiv:2302.01550, 2023.
  22. Federated learning: Challenges, methods, and future directions. IEEE signal processing magazine, 37(3):50–60, 2020a.
  23. Ditto: Fair and robust federated learning through personalization. In International Conference on Machine Learning, pp. 6357–6368. PMLR, 2021a.
  24. Multi-site fmri analysis using privacy-preserving federated learning and domain adaptation: Abide results. Medical Image Analysis, 65:101765, 2020b.
  25. Fedbn: Federated learning on non-iid features via local batch normalization. arXiv preprint arXiv:2102.07623, 2021b.
  26. Towards federated learning in uav-enabled internet of vehicles: A multi-dimensional contract-matching approach. IEEE Trans. Intell. Transp. Syst., 22(8):5140–5154, 2021.
  27. Neural auction: End-to-end learning of auction mechanisms for e-commerce advertising. In Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining, pp.  3354–3364, 2021.
  28. Fedcoin: A peer-to-peer payment system for federated learning. In Federated learning: privacy and incentive, pp.  125–138. Springer, 2020.
  29. Vertical federated learning. arXiv preprint arXiv:2211.12814, 2022.
  30. Federated multi-task learning under a mixture of distributions. Advances in Neural Information Processing Systems, 34:15434–15447, 2021.
  31. Communication-efficient learning of deep networks from decentralized data. In Proc. of the Artificial intelligence and statistics (AISTATS’17), pp.  1273–1282, 2017.
  32. Asynchronous methods for deep reinforcement learning. In International conference on machine learning, pp. 1928–1937. PMLR, 2016.
  33. Myerson, R. B. Optimal auction design. Mathematics of operations research, 6(1):58–73, 1981.
  34. Incentivize to build: A crowdsourcing framework for federated learning. In 2019 IEEE Global Communications Conference, GLOBECOM 2019, Waikoloa, HI, USA, December 9-13, 2019, pp.  1–6. IEEE, 2019.
  35. Pei, J. A survey on data pricing: from economics to data science. IEEE Transactions on knowledge and Data Engineering, 34(10):4586–4608, 2020.
  36. Scaffold: Stochastic controlled averaging for federated learning. arXiv e-prints, pp.  arXiv–1910, 2019.
  37. Incentives for truthful information elicitation of continuous signals. In Brodley, C. E. and Stone, P. (eds.), Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, July 27 -31, 2014, Québec City, Québec, Canada, pp.  770–776. AAAI Press, 2014.
  38. Towards fairness-aware federated learning. IEEE Transactions on Neural Networks and Learning Systems, 2023.
  39. Profit allocation for federated learning. In Baru, C. K., Huan, J., Khan, L., Hu, X., Ak, R., Tian, Y., Barga, R. S., Zaniolo, C., Lee, K., and Ye, Y. F. (eds.), 2019 IEEE International Conference on Big Data (IEEE BigData), Los Angeles, CA, USA, December 9-12, 2019, pp.  2577–2586. IEEE, 2019.
  40. Sutton, R. S. Learning to predict by the methods of temporal differences. Machine learning, 3:9–44, 1988.
  41. Reinforcement learning: An introduction. MIT press, 2018.
  42. A game-theoretic approach for robust federated learning. International Journal of Engineering, 34(4):832–842, 2021.
  43. An incentive mechanism for cross-silo federated learning: A public goods perspective. In 40th IEEE Conference on Computer Communications, INFOCOM 2021, Vancouver, BC, Canada, May 10-13, 2021, pp.  1–10. IEEE, 2021. doi: 10.1109/INFOCOM42981.2021.9488705. URL https://doi.org/10.1109/INFOCOM42981.2021.9488705.
  44. Incentive mechanisms for federated learning: From economic and game theoretic perspective. IEEE Trans. Cogn. Commun. Netw., 8(3):1566–1593, 2022.
  45. True online temporal-difference learning. The Journal of Machine Learning Research, 17(1):5057–5096, 2016.
  46. Vertical federated learning: Challenges, methodologies and experiments. arXiv preprint arXiv:2202.04309, 2022.
  47. Fedserving: A federated prediction serving framework based on incentive mechanism. In 40th IEEE Conference on Computer Communications, INFOCOM 2021, Vancouver, BC, Canada, May 10-13, 2021, pp.  1–10. IEEE, 2021.
  48. Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv preprint arXiv:1708.07747, 2017.
  49. Federated learning for healthcare informatics. Journal of Healthcare Informatics Research, 5(1):1–19, 2021.
  50. Federated machine learning: Concept and applications. ACM Transactions on Intelligent Systems and Technology, 10(2):12:1–12:19, 2019a.
  51. Federated learning. Synthesis Lectures on Artificial Intelligence and Machine Learning, 13(3):1–207, 2019b.
  52. Federated hetero-task learning. arXiv preprint arXiv:2206.03436, 2022.
  53. Federated learning in vehicular edge computing: A selective model aggregation approach. IEEE Access, 8:23920–23935, 2020.
  54. Market your venue with mobile applications: Collaboration of online and offline businesses. In 2018 IEEE Conference on Computer Communications, INFOCOM 2018, Honolulu, HI, USA, April 16-19, 2018, pp.  1934–1942. IEEE, 2018.
  55. A learning-based incentive mechanism for federated learning. IEEE Internet Things J., 7(7):6360–6368, 2020.
  56. Optimizing multiple performance metrics with deep gsp auctions for e-commerce advertising. In Proceedings of the 14th ACM International Conference on Web Search and Data Mining, pp.  993–1001, 2021.
  57. Federated learning on non-iid data: A survey. Neurocomputing, 465:371–390, 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (6)
  1. Yue Cui (31 papers)
  2. Liuyi Yao (19 papers)
  3. Yaliang Li (117 papers)
  4. Ziqian Chen (5 papers)
  5. Bolin Ding (112 papers)
  6. Xiaofang Zhou (60 papers)
Citations (1)
View on Semantic Scholar

Summary

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

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

Tweets