Advancing IIoT with Over-the-Air Federated Learning: The Role of Iterative Magnitude Pruning

The industrial Internet of Things (IIoT) leverages interconnected smart devices combined with machine learning (ML) to transform manufacturing. A key enhancement within IIoT is the adoption of federated learning (FL), which ensures data privacy and security by enabling edge sensors, or peripheral intelligence units (PIUs), to process data locally without sharing sensitive information over the network. Nonetheless, PIUs are constrained by limited memory, computational power, and challenges like bandwidth restrictions and environmental noise, necessitating the use of compact yet robust deep neural network (DNN) models. To address this, model compression techniques such as pruning are employed to streamline DNNs by removing superfluous connections, optimizing them for PIU resources. Specifically, we propose iterative magnitude pruning (IMP) within an over-the-air FL (OTA-FL) network to enhance DNN efficiency in IIoT. We provide a tutorial overview and also present a case study on the efficacy of IMP in managing the unique challenges of noise and bandwidth in IIoT. This work also provides future directions for enhancing and optimizing deep compression techniques to acquire compact, robust, and high-performing DNN models for IIoT in OTA-FL networks.