Price-Discrimination Game for Distributed Resource Management in Federated Learning

TL;DR

This paper introduces a price-discrimination game for federated learning that optimizes resource management and incentivizes clients by differentiating service prices based on their contributions and capabilities.

Contribution

It formulates a novel price-discrimination game addressing resource management, client selection, and incentives in federated learning, solved via a low-complexity distributed algorithm.

Findings

Effective differentiation of client pricing improves FL performance.

Proposed algorithm reduces computational complexity and communication overhead.

Simulation confirms the approach's effectiveness in real scenarios.

Abstract

In vanilla federated learning (FL) such as FedAvg, the parameter server (PS) and multiple distributed clients can form a typical buyer's market, where the number of PS/buyers of FL services is far less than the number of clients/sellers. In order to improve the performance of FL and reduce the cost of motivating clients to participate in FL, this paper proposes to differentiate the pricing for services provided by different clients rather than simply providing the same service pricing for different clients. The price is differentiated based on the performance improvements brought to FL and their heterogeneity in computing and communication capabilities. To this end, a price-discrimination game (PDG) is formulated to comprehensively address the distributed resource management problems in FL, including multi-objective trade-off, client selection, and incentive mechanism. As the PDG is a mixed-integer nonlinear programming (MINLP) problem, a distributed semi-heuristic algorithm with low computational complexity and low communication overhead is designed to solve it. The simulation result verifies the effectiveness of the proposed approach.