Dynamic Contract Design for Federated Learning in Smart Healthcare Applications
Date
2021-12-01Author
Lim, Wei Yang BryanGarg, Sahil
Xiong, Zehui
Niyato, Dusit
Leung, Cyril
Miao, Chunyan
Guizani, Mohsen
...show more authors ...show less authors
Metadata
Show full item recordAbstract
Currently, the data collected by the Internet of Healthcare Things, i.e., healthcare oriented Internet of Things (IoT), still rely on cloud-based centralized data aggregation and processing. To reduce the need for transmission of data to the cloud, the edge computing architecture may be adopted to facilitate machine learning at the edge of the network through leveraging on the amassed computation resources of pervasive IoT devices. In this article, federated learning (FL) is proposed to enable privacy-preserving collaborative model training at the edge of the network across distributed IoT users. However, the users in the FL network may have different willingness to participate (WTP), a hidden information unknown to the model owner. Furthermore, the development of healthcare applications typically requires sustainable user participation, e.g., for the continuous collection of data during which a user's WTP may change over time. As such, we leverage on the dynamic contract design to consider a two-period incentive mechanism that satisfies the intertemporal incentive compatibility (IIC), such that the self-revealing mechanism of the contract holds across both periods. The performance evaluation shows that our contract design satisfies the IIC constraints and derives greater profits than that of the uniform pricing scheme, thus validating its effectiveness in mitigating the adverse impacts of the information asymmetry.
Collections
- Computer Science & Engineering [2284 items ]