RuCIL: Enabling Privacy-Enhanced Edge Computing for Federated Learning

Federated learning has emerged as a promising approach for collaborative machine learning while preserving data privacy in distributed settings. Despite recent advancements, challenges such as privacy preservation and communication overhead persist, limiting its practical utility. This work proposes a novel model - RuCIL - Resource utilization and Computational Impact metric-based model for Edge Learning that synergizes federated learning with edge computing, leveraging the computational capabilities of latest edge devices. By doing so, it optimizes privacy-preserving mechanisms and communication overhead of the model. This work not only addresses the limitations of federated learning but also paves the way for more efficient and privacy-conscious machine learning applications in distributed environments.