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

2025-07-10

AI Summary

To address the urgent need for green AI in Society 5.0–enabled sustainable IoT, conventional federated learning (FL) proves inadequate due to its high communication overhead and computational energy consumption—especially on billions of resource-constrained devices. This paper proposes an energy-efficient collaborative intelligence architecture that, for the first time, integrates neural network sparsification into a self-organized FL framework. It combines proximity-based device clustering with selective parameter aggregation, enabling autonomous device coordination while significantly reducing communication frequency and local computation load. The approach preserves model accuracy while achieving up to 60% reduction in edge-side energy consumption. By jointly optimizing communication efficiency and computational sustainability, the method substantially enhances scalability and environmental compatibility of collaborative learning in large-scale, heterogeneous IoT deployments.

Technology Category

• Machine Learning: Efficient ML / Green AI
• Search and Optimization: Learning to Search
• Intelligent Robots: Learning & Optimization for ROB

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Search and Retrieval-Augmented AI: Efficiency and scalability of Web search engines

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.

Problem

• Addresses unsustainable energy consumption in Federated Learning
• Reduces communication bandwidth for resource-constrained IoT devices
• Balances AI efficiency with environmental responsibility in Society 5.0

Innovation

• Sparse Proximity-based Self-Federated Learning
• Aggregate computing for self-organization
• Neural network sparsification for efficiency