Sustainable Federated Learning

Abstract

Potential environmental impact of machine learning by large-scale wireless networks is a major challenge for the sustainability of future smart ecosystems. In this paper, we introduce sustainable machine learning in federated learning settings, using rechargeable devices that can collect energy from the ambient environment. We propose a practical federated learning framework that leverages intermittent energy arrivals for training, with provable convergence guarantees. Our framework can be applied to a wide range of machine learning settings in networked environments, including distributed and federated learning in wireless and edge networks. Our experiments demonstrate that the proposed framework can provide significant performance improvement over the benchmark energy-agnostic federated learning settings.

12 pages, 1 figure

References in corpus (12)

• Adam: A Method for Stochastic Optimization
• Communication-Efficient Learning of Deep Networks from Decentralized Data
• Federated Learning: Strategies for Improving Communication Efficiency
• Privacy-preserving Traffic Flow Prediction: A Federated Learning Approach
• Differentially Private Federated Learning: A Client Level Perspective
• Applied Federated Learning: Improving Google Keyboard Query Suggestions
• Fair Resource Allocation in Federated Learning
• Electrical Load Forecasting Using Edge Computing and Federated Learning
• Local SGD Converges Fast and Communicates Little
• Optimal Client Sampling for Federated Learning
• Active Federated Learning
• Client Selection in Federated Learning: Convergence Analysis and Power-of-Choice Selection Strategies