Sparse Self-Federated Learning for Energy Efficient Cooperative Intelligence in Society 5.0
This addresses sustainability challenges for resource-constrained IoT devices in Society 5.0, though it appears incremental as it builds on existing federated learning and sparsification methods.
The paper tackles the problem of federated learning's high resource consumption in IoT ecosystems by introducing Sparse Proximity-based Self-Federated Learning (SParSeFuL), which reduces energy and bandwidth usage through sparsification and self-organization.
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.