Federated Learning Incentive Mechanism Design via Enhanced Shapley Value Method

Xun, Yang; Tan, Weijie; Peng, Changgen; Xiang, Shuwen; Niu, Kun

doi:10.1155/2022/9690657

Cited by 9 publications

(8 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are some solutions already been proposed using Shapley value for different industries. S. Li et al [45] and Yang et al [46] provide a solution to distribute profit fairly to improve supply chain management. Similarly, in other domains, research incorporated Shapley value to improve the performance of the system.…”

Section: B Incentive Distribution Mechanismsmentioning

confidence: 99%

See 1 more Smart Citation

Optimizing Industrial IoT Data Security Through Blockchain-Enabled Incentive-Driven Game Theoretic Approach for Data Sharing

Sohail,

Anjum,

Saeed

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Connecting smart industrial components to computer networks revolutionizes business operations. However, in the Industrial Internet of Things (IIoT), the sharing of data has bandwidth, computational, and privacy issues. Researchers presented cloud computing and fine-grained access control to overcome these challenges. However, traditional centralized computing systems involve single points of failure. To mitigate these challenges, we have proposed a secure and incentive-based data-sharing framework for IIoT systems using blockchain technology. We leverage blockchain due to its ability to provide secure and tamper-resistant data storage and sharing as participants store their data on a distributed ledger (DL), preventing unauthorized access. A security protocol is designed that utilizes the properties of elliptic curve cryptography (ECC). Moreover, Shapley value is employed to calculate revenue and distribute it fairly. To perform the formal security evaluation, we have conducted extensive simulations using the Automated Validation of Internet Security Protocols and Applications (AVISPA) and Scyther protocol simulation tools, which demonstrated that our protocol is robust against various adversarial attacks. The experimental results show that the proposed incentive distribution framework demonstrated fairness in the distribution of revenue among participants.

show abstract

Section: B Incentive Distribution Mechanismsmentioning

confidence: 99%

“…Require secure environment for data exchange, does not support data trustworthiness [46] To improve the trade-off between Pareto efficiency and distribution…”

Section: Shapley Valuementioning

confidence: 99%

Optimizing Industrial IoT Data Security Through Blockchain-Enabled Incentive-Driven Game Theoretic Approach for Data Sharing

Sohail,

Anjum,

Saeed

et al. 2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…In [27], the authors conducted an investigation into different factors that impact FL. Additionally, they proposed an FL incentive mechanism that leverages an improved Shapley value method.…”

Section: Related Workmentioning

confidence: 99%

Federated Learning Incentive Mechanism with Supervised Fuzzy Shapley Value

Yang,

Xiang,

Peng

et al. 2024

Axioms

View full text Add to dashboard Cite

The distributed training of federated machine learning, referred to as federated learning (FL), is discussed in models by multiple participants using local data without compromising data privacy and violating laws. In this paper, we consider the training of federated machine models with uncertain participation attitudes and uncertain benefits of each federated participant, and to encourage all participants to train the desired FL models, we design a fuzzy Shapley value incentive mechanism with supervision. In this incentive mechanism, if the supervision of the supervised mechanism detects that the payoffs of a federated participant reach a value that satisfies the Pareto optimality condition, the federated participant receives a distribution of federated payoffs. The results of numerical experiments demonstrate that the mechanism successfully achieves a fair and Pareto optimal distribution of payoffs. The contradiction between fairness and Pareto-efficient optimization is solved by introducing a supervised mechanism.

show abstract

“…In addition, to address the fact that the calculation of the Shapley value in FL requires a certain communication cost, in [25], the authors proposed a Shapley value based on a contribution evaluation metric called the vertical federated Shapley value (VerFedSV) and verified the fairness of VerFedSV through experiments. In [26], the authors considered several factors affecting FL and proposed an FL incentive mechanism according to the enhanced Shapley value method, and numerical experiments verified that the payoffs allocated among all participants can be fairer when using the enhanced Shapley value method.…”

Section: Related Workmentioning

confidence: 99%

Federated Learning Incentive Mechanism Design via Shapley Value and Pareto Optimality

Xun

Xiang

Peng

et al. 2023

Axioms

View full text Add to dashboard Cite

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 paper, we propose an incentive mechanism via the combination of the Shapley value and Pareto efficiency optimization, in which a third party is introduced to supervise the federated payoff allocation. If the payoff can reach Pareto optimality, the federated payoff is allocated by the Shapley value method; otherwise, the relevant federated players are punished. Numerical and simulation experiments show that the mechanism can achieve fair payoff allocation and Pareto optimality payoff allocation. The Nash equilibrium of this mechanism is formed when Pareto optimality payoff allocation is achieved.

show abstract

Federated Learning Incentive Mechanism Design via Enhanced Shapley Value Method

Cited by 9 publications

References 33 publications

Optimizing Industrial IoT Data Security Through Blockchain-Enabled Incentive-Driven Game Theoretic Approach for Data Sharing

Optimizing Industrial IoT Data Security Through Blockchain-Enabled Incentive-Driven Game Theoretic Approach for Data Sharing

Federated Learning Incentive Mechanism with Supervised Fuzzy Shapley Value

Federated Learning Incentive Mechanism Design via Shapley Value and Pareto Optimality

Contact Info

Product

Resources

About