Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
44 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Don't Forget What I did?: Assessing Client Contributions in Federated Learning (2403.07151v1)

Published 11 Mar 2024 in cs.LG, cs.AI, and cs.CR

Abstract: Federated Learning (FL) is a collaborative ML approach, where multiple clients participate in training an ML model without exposing the private data. Fair and accurate assessment of client contributions is an important problem in FL to facilitate incentive allocation and encouraging diverse clients to participate in a unified model training. Existing methods for assessing client contribution adopts co-operative game-theoretic concepts, such as Shapley values, but under simplified assumptions. In this paper, we propose a history-aware game-theoretic framework, called FLContrib, to assess client contributions when a subset of (potentially non-i.i.d.) clients participate in each epoch of FL training. By exploiting the FL training process and linearity of Shapley value, we develop FLContrib that yields a historical timeline of client contributions as FL training progresses over epochs. Additionally, to assess client contribution under limited computational budget, we propose a scheduling procedure that considers a two-sided fairness criteria to perform expensive Shapley value computation only in a subset of training epochs. In experiments, we demonstrate a controlled trade-off between the correctness and efficiency of client contributions assessed via FLContrib. To demonstrate the benefits of history-aware client contributions, we apply FLContrib to detect dishonest clients conducting data poisoning in FL training.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (37)
  1. 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.
  2. C. Zhang, Y. Xie, H. Bai, B. Yu, W. Li, and Y. Gao, “A survey on federated learning,” Knowledge-Based Systems, vol. 216, p. 106775, 2021.
  3. L. U. Khan, W. Saad, Z. Han, E. Hossain, and C. S. Hong, “Federated learning for internet of things: Recent advances, taxonomy, and open challenges,” IEEE Communications Surveys & Tutorials, vol. 23, no. 3, pp. 1759–1799, 2021.
  4. X. Yin, Y. Zhu, and J. Hu, “A comprehensive survey of privacy-preserving federated learning: A taxonomy, review, and future directions,” ACM Computing Surveys (CSUR), vol. 54, no. 6, pp. 1–36, 2021.
  5. S. Tavara, A. Schliep, and D. Basu, “Federated learning of oligonucleotide drug molecule thermodynamics with differentially private admm-based svm,” in Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 459–467, Springer, 2021.
  6. E. Cyffers, A. Bellet, and D. Basu, “From noisy fixed-point iterations to private admm for centralized and federated learning,” arXiv preprint arXiv:2302.12559, 2023.
  7. 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.
  8. H. Yu, Z. Liu, Y. Liu, T. Chen, M. Cong, X. Weng, D. Niyato, and Q. Yang, “A fairness-aware incentive scheme for federated learning,” in Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society, pp. 393–399, 2020.
  9. 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.
  10. Y. Fraboni, R. Vidal, and M. Lorenzi, “Free-rider attacks on model aggregation in federated learning,” in International Conference on Artificial Intelligence and Statistics, pp. 1846–1854, PMLR, 2021.
  11. Z. Zhu, J. Shu, X. Zou, and X. Jia, “Advanced free-rider attacks in federated learning,” in the 1st NeurIPS Workshop on New Frontiers in Federated Learning Privacy, Fairness, Robustness, Personalization and Data Ownership, 2021.
  12. A. Richardson, A. Filos-Ratsikas, and B. Faltings, “Rewarding high-quality data via influence functions,” arXiv preprint arXiv:1908.11598, 2019.
  13. L. Lyu, X. Xu, Q. Wang, and H. Yu, “Collaborative fairness in federated learning,” Federated Learning: Privacy and Incentive, pp. 189–204, 2020.
  14. G. Wang, C. X. Dang, and Z. Zhou, “Measure contribution of participants in federated learning,” in 2019 IEEE international conference on big data (Big Data), pp. 2597–2604, IEEE, 2019.
  15. S. Wei, Y. Tong, Z. Zhou, and T. Song, “Efficient and fair data valuation for horizontal federated learning,” Federated Learning: Privacy and Incentive, pp. 139–152, 2020.
  16. T. Wang, J. Rausch, C. Zhang, R. Jia, and D. Song, “A principled approach to data valuation for federated learning,” Federated Learning: Privacy and Incentive, pp. 153–167, 2020.
  17. T. Nishio, R. Shinkuma, and N. B. Mandayam, “Estimation of individual device contributions for incentivizing federated learning,” in 2020 IEEE Globecom Workshops (GC Wkshps, pp. 1–6, IEEE, 2020.
  18. A. Ghorbani and J. Zou, “Data shapley: Equitable valuation of data for machine learning,” in International conference on machine learning, pp. 2242–2251, PMLR, 2019.
  19. Z. Liu, Y. Chen, H. Yu, Y. Liu, and L. Cui, “Gtg-shapley: Efficient and accurate participant contribution evaluation in federated learning,” ACM Transactions on Intelligent Systems and Technology (TIST), vol. 13, no. 4, pp. 1–21, 2022.
  20. L. S. Shapley et al., “A value for n-person games,” 1953.
  21. 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. 10700–10714, 2019.
  22. J. Castro Cantalejo, D. Gómez González, and J. A. Tejada Cazorla, “Polynomial calculation of the shapley value based on sampling,” 2009.
  23. T. van Campen, H. Hamers, B. Husslage, and R. Lindelauf, “A new approximation method for the shapley value applied to the wtc 9/11 terrorist attack,” Social Network Analysis and Mining, vol. 8, pp. 1–12, 2018.
  24. J. Zhang, Q. Sun, J. Liu, L. Xiong, J. Pei, and K. Ren, “Efficient sampling approaches to shapley value approximation,” Proceedings of the ACM on Management of Data, vol. 1, no. 1, pp. 1–24, 2023.
  25. T. Song, Y. Tong, and S. Wei, “Profit allocation for federated learning,” in 2019 IEEE International Conference on Big Data (Big Data), pp. 2577–2586, IEEE, 2019.
  26. Z. Fan, H. Fang, Z. Zhou, J. Pei, M. P. Friedlander, C. Liu, and Y. Zhang, “Improving fairness for data valuation in horizontal federated learning,” in 2022 IEEE 38th International Conference on Data Engineering (ICDE), pp. 2440–2453, IEEE, 2022.
  27. 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, pp. 1273–1282, PMLR, 2017.
  28. S. Zezulka and K. Genin, “Performativity and prospective fairness,” arXiv preprint arXiv:2310.08349, 2023.
  29. A. Papadaki, N. Martinez, M. Bertran, G. Sapiro, and M. Rodrigues, “Minimax demographic group fairness in federated learning,” in Proceedings of the 2022 ACM Conference on Fairness, Accountability, and Transparency, pp. 142–159, 2022.
  30. X. Lin, X. Xu, S.-K. Ng, C.-S. Foo, and B. K. H. Low, “Fair yet asymptotically equal collaborative learning,” arXiv preprint arXiv:2306.05764, 2023.
  31. V. Do, S. Corbett-Davies, J. Atif, and N. Usunier, “Two-sided fairness in rankings via lorenz dominance,” Advances in Neural Information Processing Systems, vol. 34, pp. 8596–8608, 2021.
  32. B. Becker and R. Kohavi, “Adult.” UCI Machine Learning Repository, 1996. DOI: https://doi.org/10.24432/C5XW20.
  33. J. Angwin, J. Larson, S. Mattu, and L. Kirchner, “Machine bias risk assessments in criminal sentencing,” ProPublica, May, vol. 23, 2016.
  34. A. Krizhevsky, “Learning multiple layers of features from tiny images,” tech. rep., 2009.
  35. P. Fearnhead, “Exact and efficient bayesian inference for multiple changepoint problems,” Statistics and computing, vol. 16, pp. 203–213, 2006.
  36. R. Tavenard, J. Faouzi, G. Vandewiele, F. Divo, G. Androz, C. Holtz, M. Payne, R. Yurchak, M. Rußwurm, K. Kolar, and E. Woods, “Tslearn, a machine learning toolkit for time series data,” Journal of Machine Learning Research, vol. 21, no. 118, pp. 1–6, 2020.
  37. P. Jaccard, “Étude comparative de la distribution florale dans une portion des alpes et des jura,” Bull Soc Vaudoise Sci Nat, vol. 37, pp. 547–579, 1901.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (9)
  1. Bishwamittra Ghosh (14 papers)
  2. Debabrota Basu (47 papers)
  3. Fu Huazhu (2 papers)
  4. Wang Yuan (4 papers)
  5. Renuga Kanagavelu (4 papers)
  6. Jiang Jin Peng (1 paper)
  7. Liu Yong (7 papers)
  8. Goh Siow Mong Rick (2 papers)
  9. Wei Qingsong (1 paper)

Summary

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

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