A Sustainable Incentive Scheme for Federated Learning
The DOI matches its Crossref record; 12 of the 12 references it cites were found in a registry or an index.
Abstract
In federated learning (FL), a federation distributedly trains a collective machine learning model by leveraging privacy preserving technologies. However, FL participants need to incur some cost for contributing to the FL models. The training and commercialization of the models will take time. Thus, there will be delays before the federation could pay back the participants. This temporary mismatch between contributions and rewards has not been accounted for by existing payoff-sharing schemes. To address this limitation, we propose the FL incentivizer (FLI). It dynamically divides a given budget in a context-aware manner among data owners in a federation by jointly maximizing the collective utility while minimizing the inequality among the data owners, in terms of the payoff received and the waiting time for receiving payoffs. Comparisons with five state-of-the-art payoff-sharing schemes show that FLI attracts high-quality data owners and achieves the highest expected revenue for a federation.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“This topic has received a lot of attention in the broader ML community [220, 138, 509, 309, 362, 74], but these methods either do not have a straightforward mapping to federated learning, or make the training process more complex which makes it difficult to adopt.”
From Advances and Open Problems in Federated Learning (2021) · cites this paper as [74]
Citations
Cites
Yang, Q., Liu, Y., Cheng, Y., Kang, Y., Chen, T., & Yu, H. (2019) · Synthesis lectures on artificial intelligence and machine learning · doi:10.2200/s00960ed2v01y201910aim043 · Cited by 261 · cited 3×
“Maximizing U satisfies Fairness criterion (1).”
BackgroundSelf-citationA Fairness-aware Incentive Scheme for Federated Learning
Yu, H., Liu, Z., Liu, Y., Chen, T., Cong, M., Weng, X., Niyato, D., & Yang, Q. (2020) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3375627.3375840 · Cited by 226 · cited 3×
“Minimizing ~ satisfies Fairness criteria (2) and (3).”
BackgroundMethodSelf-citationOn Designing Data Quality-Aware Truth Estimation and Surplus Sharing Method for Mobile Crowdsensing
Yang, S., Wu, F., Tang, S., Gao, X., Yang, B., & Chen, G. (2017) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2017.2676898 · Cited by 188
Towards Efficient Data Valuation Based on the Shapley Value
Jia, R., Dao, D., Wang, B., Hubis, F. A., Hynes, N., Gürel, N. M., Li, B., Zhang, C., Song, D. X., & Spanos, C. J. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.10275 · Cited by 168 · cited 1×
“Similar to Richardson et al. , 10 ; 9 Jia et al. computes a Shap-ley value to split reward among data owners.”
ResultLuo, T., Kanhere, S. S., Huang, J., Das, S. K., & Wu, F. (2017) · IEEE Communications Magazine · doi:10.1109/mcom.2017.1600746cm · Cited by 108
Cheng, Y., Liu, Y., & Yang, Q. (2019) · Cited by 62
Self-citationAlgorithmic Management for Improving Collective Productivity in Crowdsourcing
Yu, H., Miao, C., Chen, Y., Fauvel, S., Li, X., & Lesser, V. R. (2017) · Scientific Reports · doi:10.1038/s41598-017-12757-x · Cited by 53
Self-citationRewarding High-Quality Data via Influence FunctionsPreprint
Richardson, A., Filos-Ratsikas, A., & Faltings, B. V. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.11598 · Cited by 46 · cited 2×
“Similar to Richardson et al. , 10 ; 9 Jia et al. computes a Shap-ley value to split reward among data owners.”
BackgroundResultGame Theory for Data Science: Eliciting Truthful Information
Faltings, B. V., & Radanović, G. (2017) · Synthesis lectures on artificial intelligence and machine learning · doi:10.2200/s00788ed1v01y201707aim035 · Cited by 44
Profit Sharing and Efficiency in Utility Games
Gollapudi, S., Kollias, K., Panigrahi, D., & Pliatsika, V. (2017) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/lipics.esa.2017.43 · Cited by 32
Restoring Pure Equilibria to Weighted Congestion Games
Kollias, K., & Roughgarden, T. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-22012-8_43 · Cited by 28
Restoring Pure Equilibria to Weighted Congestion Games
Kollias, K., & Roughgarden, T. (2015) · ACM Transactions on Economics and Computation · doi:10.1145/2781678 · Cited by 28
Cited by
Advances and Open Problems in Federated Learning
Kairouz, P., & McMahan, H. B. (2021) · Foundations and Trends in Machine Learning · doi:10.1561/2200000083 · Cited by 7,772
Self-citationA Survey on Federated Learning for Resource-Constrained IoT Devices
Imteaj, A., Thakker, U., Wang, S., Li, J., & Amini, M. H. (2022) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3095077 · Cited by 774
“With the motivation of addressing issues related to costs and mismatch between client’s contributions and receiving incentives, Yu et al. [116], [122] proposed a payoff-sharing scheme named FL Incentivizer (FLI).”
Federated learning review: Fundamentals, enabling technologies, and future applications
Banabilah, S., Aloqaily, M., Alsayed, E., Malik, N., & Jararweh, Y. (2022) · Information Processing & Management · doi:10.1016/j.ipm.2022.103061 · Cited by 556
Federated Learning: Opportunities and Challenges
Mammen, P. M. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2101.05428 · Cited by 140
“Client-selection and incentive designs[37] are some notable techniques needed to facilitate this type of FL.”
BackgroundA state-of-the-art survey on solving non-IID data in Federated Learning
Ma, X., Zhu, J., Lin, Z., Chen, S., & Qin, Y. (2022) · Future Generation Computer Systems · doi:10.1016/j.future.2022.05.003 · Cited by 399
Metadata
- Authors
- Yu, H., Liu, Z., Liu, Y., Chen, T., Cong, M., Weng, X., Niyato, D., & Yang, Q.
- Affiliations
- Nanyang Technological University (SG)
- WeBank
- University of Hong Kong (HK)
- Peking University (CN)
- Hong Kong University of Science and Technology (HK)
- Venue
- IEEE Intelligent Systems
- Published
- 2020-07-01
- Volume
- 35
- Issue
- 4
- Pages
- 58-69
- ISSN
- 1541-1672 (ISSN-L)
- 1941-1294
- OpenAlex
- W3016378036
- Cited by
- 123
- References
- 12
- Citations by year
- 2026: 6 · 2025: 16 · 2024: 27 · 2023: 26 · 2022: 26 · 2021: 16 · 2020: 6
- FWCI
- 7.27
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Intelligent Systems (publishedVersion)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- Funders
- Nanyang Assistant Professorship
- NTU-WeBank JRI (NWJ-2019-007, AISG-GC-2019-003, NRF-NRFI05-2019-0002, NTU-SDU-CFAIR (NSC-2019-011))
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Blockchain Technology Applications and Security
- Physical Sciences › Computer Science › Computer Science Applications › Mobile Crowdsensing and Crowdsourcing
- Keywords
- federated learning, incentive mechanisms, privacy-preserving machine learning, revenue maximization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.