A Contribution-based Device Selection Scheme in Federated Learning
arXiv:2203.05369 · doi:10.1109/LCOMM.2022.3181678
Abstract
In a Federated Learning (FL) setup, a number of devices contribute to the training of a common model. We present a method for selecting the devices that provide updates in order to achieve improved generalization, fast convergence, and better device-level performance. We formulate a min-max optimization problem and decompose it into a primal-dual setup, where the duality gap is used to quantify the device-level performance. Our strategy combines \emph{exploration} of data freshness through a random device selection with \emph{exploitation} through simplified estimates of device contributions. This improves the performance of the trained model both in terms of generalization and personalization. A modified Truncated Monte-Carlo (TMC) method is applied during the exploitation phase to estimate the device's contribution and lower the communication overhead. The experimental results show that the proposed approach has a competitive performance, with lower communication overhead and competitive personalization performance against the baseline schemes.
arXiv commentThis work has been accepted for publication in IEEE Communications Letters
References in corpus (8)
- Client Selection for Federated Learning with Heterogeneous Resources in Mobile Edge
- A Crowdsourcing Framework for On-Device Federated Learning
- Multi-Armed Bandit Based Client Scheduling for Federated Learning
- Towards Efficient Data Valuation Based on the Shapley Value
- Lower Bounds and Optimal Algorithms for Personalized Federated Learning
- Edge-assisted Democratized Learning Towards Federated Analytics
- A Marketplace for Trading AI Models based on Blockchain and Incentives for IoT Data
- Self-organizing Democratized Learning: Towards Large-scale Distributed Learning Systems