Prior-Independent Auctions for the Demand Side of Federated Learning
This addresses the challenge of funding and incentivizing participation in federated learning for distributed clients, though it is incremental as it adapts existing auction design insights to this domain.
The paper tackles the problem of incentivizing client participation in federated learning by proposing FIPIA, a prior-independent auction mechanism to collect monetary contributions from self-interested clients, with experiments on MNIST, FashionMNIST, and CIFAR-10 datasets showing its effectiveness in maintaining model quality and incentive properties.
Federated learning (FL) is a paradigm that allows distributed clients to learn a shared machine learning model without sharing their sensitive training data. While largely decentralized, FL requires resources to fund a central orchestrator or to reimburse contributors of datasets to incentivize participation. Inspired by insights from prior-independent auction design, we propose a mechanism, FIPIA (Federated Incentive Payments via Prior-Independent Auctions), to collect monetary contributions from self-interested clients. The mechanism operates in the semi-honest trust model and works even if clients have a heterogeneous interest in receiving high-quality models, and the server does not know the clients' level of interest. We run experiments on the MNIST, FashionMNIST, and CIFAR-10 datasets to test clients' model quality under FIPIA and FIPIA's incentive properties.