Incentivizing Federated Learning
This addresses the challenge of incentivizing data sharing in federated learning for applications relying on distributed collaboration, offering a non-monetary solution to improve global model performance.
The paper tackles the problem of insufficient data contribution in federated learning due to privacy and cost concerns by proposing an incentive mechanism that rewards significant contributors with better model performance instead of monetary payments, theoretically proving that clients will use all available data under certain conditions.
Federated Learning is an emerging distributed collaborative learning paradigm used by many of applications nowadays. The effectiveness of federated learning relies on clients' collective efforts and their willingness to contribute local data. However, due to privacy concerns and the costs of data collection and model training, clients may not always contribute all the data they possess, which would negatively affect the performance of the global model. This paper presents an incentive mechanism that encourages clients to contribute as much data as they can obtain. Unlike previous incentive mechanisms, our approach does not monetize data. Instead, we implicitly use model performance as a reward, i.e., significant contributors are paid off with better models. We theoretically prove that clients will use as much data as they can possibly possess to participate in federated learning under certain conditions with our incentive mechanism