Prior-Independent Auctions for the Demand Side of Federated Learning
arXiv:2103.14375
Abstract
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.
References in corpus (9)
- Deep Learning with Differential Privacy
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Communication-Efficient Learning of Deep Networks from Decentralized Data
- Towards Federated Learning at Scale: System Design
- Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
- Inverting Gradients -- How easy is it to break privacy in federated learning?
- Subsampled Rényi Differential Privacy and Analytical Moments Accountant
- D2P-Fed: Differentially Private Federated Learning With Efficient Communication
- Mechanism Design for Multi-Party Machine Learning