A Survey of Model Compression and Its Feedback Mechanism in Federated Learning

In this paper, we review various model compression methods used in extensive neural networks, such as Quantization, Pruning, Knowledge Distillation, and Weight Sharing. We also focus on their implementation in federated learning environments. Especially, we delve into the feedback model compression mechanism in federated learning. This survey provides valuable insights into the potential advantages and challenges of this approach. Furthermore, the paper presents forward-looking perspectives, charting potential future developments in this dynamic field. It serves as a guide for researchers and practitioners aiming to refine model compression strategies in federated learning, contributing to the growth and practicality of this field.