Incentive Design for Efficient Federated Learning in Mobile Networks: A Contract Theory Approach

By Jiawen Kang, Zehui Xiong, Dusist Niyato, Han Yu, Ying-Chang Liang, Dong In Kim. 2019

249 citations recorded by the source corpus.

To strengthen data privacy and security, federated learning as an emerging machine learning technique is proposed to enable large-scale nodes, e.g., mobile devices, to distributedly train and globally share models without revealing their local data. This technique can not only significantly improve privacy protection for mobile devices, but also ensure good performance of the trained results collectively. Currently, most the existing studies focus on optimizing federated learning algorithms to improve model training performance. However, incentive mechanisms to motivate the mobile devices to join model training have been largely overlooked. The mobile devices suffer from considerable overhead in terms of computation and communication during the federated model training process. Without well-designed incentive, self-interested mobile devices will be unwilling to join federated learning tasks, which hinders the adoption of federated learning. To bridge this gap, in this paper, we adopt the contract theory to design an effective incentive mechanism for simulating the mobile devices with high-quality (i.e., high-accuracy) data to participate in federated learning. Numerical results demonstrate that the proposed mechanism is efficient for federated learning with improved learning accuracy.

Subfields: Artificial Intelligence, Electrical and Electronic Engineering, Federated & Distributed Learning, Game & Decision Theory

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Electrical and Electronic Engineering

In Federated & Distributed Learning

In Game & Decision Theory

Citations in the corpus

Advances and Open Problems in Federated Learning (2019, background): “[225, 224]), but is particularly relevant in the cross-silo setting, where participants may also be business competitors.”
Federated Learning: Challenges, Methods, and Future Directions (2019, neutral): “[57] take into account”
FedMD: Heterogenous Federated Learning via Model Distillation (2019, background): “to enable active sampling [6, 7] and improve fault tolerance [8].”
Federated Learning: Opportunities and Challenges (2021, background): “To encourage/improve device participation in FL, works such as [15, 16, 37, 39] propose a reputation based incentive mechanism i.”
Federated Learning With Blockchain for Autonomous Vehicles: Analysis and Design Challenges (2020, background): “One may also adopt the contract theory approach along the lines of [11] to design an effective incentive mechanism for attracting vehicles with highly valuable data to participate in the learning.”
Federated Learning in Edge Computing: A Systematic Survey (2022, background): “In addition, Jiawen K. et al. [213] developed the contract theory to design an effective incentive mechanism for simulating mobile devices with high-quality (e.g., high-precision) data to participate in federated learning.”
Incentive Mechanism for Reliable Federated Learning: A Joint Optimization Approach to Combining Reputation and Contract Theory (2019, background): “where ζ is the effective capacitance parameter of computing chipset for worker n [26].”
A Survey on Federated Learning Systems: Vision, Hype and Reality for Data Privacy and Protection (2019, background): “Incentive mechanisms [79], [80] can encourage the participation of the parties and”
A Survey on Federated Learning: The Journey From Centralized to Distributed On-Site Learning and Beyond (2021, background): “It is considered in [61] that some clients, if selected by the server, tend not to waste their resources with the limited computation and communication capabilities.”
Federated Learning With Quantized Global Model Updates (2020, background): “Active device selection schemes have been introduced to alleviate signiﬁcant variability in FL systems, where a subset of devices share the resources and participate at each iteration of training [19–23].”
Throughput-Optimal Topology Design for Cross-Silo Federated Learning (2020, background): “To the best of our knowledge, energetic considerations for federated learning have not been adequately explored, but for a few papers considering FL for mobile devices [42, 97].”
Towards Federated Learning in UAV-Enabled Internet of Vehicles: A Multi-Dimensional Contract-Matching Approach (2020, background): “For example, the study in [42] adopts a contract-theoretic approach to motivate workers to contribute more computation resource for efﬁcient FL.”
Federated Learning for Healthcare Informatics (2019, background): “in federal learning tasks, which will hinder the adoption of federated learning [53].”
Federated learning for 6G communications: Challenges, methods, and future directions (2020, background): “As a result, incentive mechanisms for honest and active participation are a core and urgent research topic [7], [21], [39]–[42].”
A Survey on federated learning* (2020, background): “For the sake of resource constraint, Kang et al. took overhead in heterogeneous client into consideration to motivate more high-quality devices [34].”
Federated Machine Learning: Survey, Multi-Level Classification, Desirable Criteria and Future Directions in Communication and Networking Systems (2021, background): “The authors of [181] study the problem of incentivizing mobile devices to participate in the federated learning paradigm by the model owner.”