Federated learning privacy incentives: Reverse auctions and negotiations

Abstract

The incentive mechanism of federated learning has been a hot topic, but little research has been done on the compensation of privacy loss. To this end, this study uses the Local SGD federal learning framework and gives a theoretical analysis under the use of differential privacy protection. Based on the analysis, a multi‐attribute reverse auction model is proposed to be used for user selection as well as payment calculation for participation in federal learning. The model uses a mixture of economic and non‐economic attributes in making choices for users and is transformed into an optimisation equation to solve the user choice problem. In addition, a post‐auction negotiation model that uses the Rubinstein bargaining model as well as optimisation equations to describe the negotiation process and theoretically demonstrate the improvement of social welfare is proposed. In the experimental part, the authors find that their algorithm improves both the model accuracy and the F1‐score values relative to the comparison algorithms to varying degrees.

Neural dynamics for improving optimiser in deep learning with noise considered

“…For deep neural network training, stochastic gradient descent (SGD) is one of the increasingly popular algorithms [23]. In SGD, the standard equation is represented as $$${\theta }_{k+1}={\theta }_{k}-\lambda {\left(\frac{\partial J}{\partial \theta }\right)}_{k},$$$ where k represents the iteration step, and λ is denoted as the learning rate.…”

“…For deep neural network training, stochastic gradient descent (SGD) is one of the increasingly popular algorithms [23]. In SGD, the standard equation is represented as…”