2023
DOI: 10.3390/axioms12070636
|View full text |Cite
|
Sign up to set email alerts
|

Federated Learning Incentive Mechanism Design via Shapley Value and Pareto Optimality

Abstract: Federated learning (FL) is a distributed machine learning framework that can effectively help multiple players to use data to train federated models while complying with their privacy, data security, and government regulations. Due to federated model training, an accurate model should be trained, and all federated players should actively participate. Therefore, it is crucial to design an incentive mechanism; however, there is a conflict between fairness and Pareto efficiency in the incentive mechanism. In this… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
0
0

Year Published

2024
2024
2025
2025

Publication Types

Select...
4

Relationship

1
3

Authors

Journals

citations
Cited by 4 publications
(2 citation statements)
references
References 31 publications
0
0
0
Order By: Relevance
“…In [28], an incentive design called heterogeneous client selection (IHCS) was proposed to enhance performance and mitigate security risks in FL, an approach that involves assigning a recognition value to each client using the Shapley value and is subsequently utilized to aggregate the probability of participation level. In [29], an incentive mechanism is introduced that combines the Shapley value and Pareto efficiency optimization. This approach entails incorporating a third-party entity to oversee the distribution of federated payoffs.…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…In [28], an incentive design called heterogeneous client selection (IHCS) was proposed to enhance performance and mitigate security risks in FL, an approach that involves assigning a recognition value to each client using the Shapley value and is subsequently utilized to aggregate the probability of participation level. In [29], an incentive mechanism is introduced that combines the Shapley value and Pareto efficiency optimization. This approach entails incorporating a third-party entity to oversee the distribution of federated payoffs.…”
Section: Related Workmentioning
confidence: 99%
“…Meanwhile, ref. [29] considers the fairness and Pareto optimality of benefit distribution in the case of certainty of participants' attitudes. Therefore, the method in this paper is more consistent with the practical application scenario, and it can solve the fairness and Pareto optimal consistency of gain distribution under uncertainty of participants' attitudes, which can motivate more participants to join in the FL.…”
Section: Illustrative Simulationsmentioning
confidence: 99%