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

--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 un-sustainable at scale, creating a fundamental conflict with green AI principles as billions of resource-constrained devices attempt to participate. T o 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. A. Context The Internet of Things (IoT) landscape is rapidly evolving, with systems growing increasingly complex and ubiquitous. This expansion necessitates novel paradigms capable of scaling to meet emerging societal challenges. Society 5.0 [1], the vision of a human-centered society that balances economic advancement with social problem-solving, emphasizes a shift from centralized infrastructures toward decentralized, self-organizing systems that can effectively manage the complexity of modern requirements.