Federated Learning for Edge Networks: Resource Optimization and Incentive Mechanism
By Latif Ullah Khan, Nguyen H. Tran, Shashi Raj Pandey, Walid Saad, Zhu Han, Minh N. H. Nguyen, Choong Seon Hong. IEEE Communications Magazine, 2019
447 citations recorded by the source corpus.
Recent years have witnessed a rapid proliferation of smart Internet of Things (IoT) devices. IoT devices with intelligence require the use of effective machine learning paradigms. Federated learning can be a promising solution for enabling IoT-based smart applications. In this article, we present the primary design aspects for enabling federated learning at the network edge. We model the incentive- based interaction between a global server and participating devices for federated learning via a Stackelberg game to motivate the participation of the devices in the federated learning process. We present several open research challenges with their possible solutions. Finally, we provide an outlook on future research.
Subfields: Artificial Intelligence, Computer Science Applications, Sociology and Political Science
View Paper: https://www.semanticscholar.org/paper/2a3d09bbdfe21418ce75d6973f71028fa9192b89
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 Computer Science Applications
In Sociology and Political Science
Citations in the corpus
- Survey on 6G Frontiers: Trends, Applications, Requirements, Technologies and Future Research (2021, background): “[222] propose a Stackelberg game-based approach to incentivize the interaction between”
- Edge-Computing-Enabled Smart Cities: A Comprehensive Survey (2019, unknown): “enabling intelligent edge-based smart healthcare applications [90], [91].”
- A Survey on Federated Learning for Resource-Constrained IoT Devices (2021, unknown): “Khan et al. [117] designed an incentive-based FL model via a Stackelberg game for motivating client participation in the learning process.”
- 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.”
- Towards Federated Learning in UAV-Enabled Internet of Vehicles: A Multi-Dimensional Contract-Matching Approach (2020, methodology): “Following [44], [53], [54], the FL model accuracy Υ( ) is a concave function of the aggregate data collected across N subregions by the N selected UAVs.”
- Federated Learning for Open Banking (2021, background): “Different forms of incentives are possible, such as user-defined utility and money-based rewards, and have been well discussed in the literature [20,21,36,39].”
- A Survey on federated learning* (2020, background): “Khan et al. discussed Stackelberg-based incentive mechanism to set local iteration times adaptively to be effective as much as possible [62].”
- Decentralized Federated Learning: A Survey and Perspective (2023, background): “In the context of DFL, the feasibility of incentive mechanisms based on game theory, such as Stackelberg games [231], raises questions due to the requirements on game leaders, Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
- Federated Learning in Mobile Edge Networks: A Comprehensive Survey (2019, background): “In contrast to [135], [137]–[139], the authors in [140] propose an incentive design using a contract theoretic [141] approach to attract participants with high-quality data for FL.”
- Federated Learning for Smart Healthcare: A Survey (2021, background): “, latency and transmit power, consumed by raw data transmission, as the model gradients generally have much smaller sizes compared to their actual datasets [32].”
- FedCoin: A Peer-to-Peer Payment System for Federated Learning (2020, background): “In [Khan et al., 2019], a Stackelberg-game based incentive mechanism is designed to optimize the utilities of both FL clients and the FL server.”