Sparse Self-Federated Learning for Energy Efficient Cooperative Intelligence in Society 5.0

TL;DR

This paper introduces SParSeFuL, a resource-efficient federated learning method that reduces energy and bandwidth use, supporting sustainable IoT ecosystems aligned with Society 5.0's human-centered goals.

Contribution

It proposes a novel sparse, self-organizing federated learning approach that addresses environmental sustainability in IoT networks for Society 5.0.

Findings

Reduces communication bandwidth by neural network sparsification.

Lowers energy consumption in federated learning environments.

Supports scalable, sustainable IoT deployments.

Abstract

Federated Learning offers privacy-preserving collaborative intelligence but struggles to meet the sustainability demands of emerging IoT ecosystems necessary for Society 5.0-a human-centered technological future balancing social advancement with environmental responsibility. The excessive communication bandwidth and computational resources required by traditional FL approaches make them environmentally unsustainable at scale, creating a fundamental conflict with green AI principles as billions of resource-constrained devices attempt to participate. To this end, we introduce Sparse Proximity-based Self-Federated Learning (SParSeFuL), a resource-aware approach that bridges this gap by combining aggregate computing for self-organization with neural network sparsification to reduce energy and bandwidth consumption.