Federated learning compression designed for lightweight communications
This work addresses communication efficiency for FL in privacy-sensitive domains like military and medical applications, but it is incremental as it builds on existing compression methods.
The paper tackles the communication cost challenge in Federated Learning (FL) for edge devices by investigating compression techniques, demonstrating a method that compresses messages by up to 50% with less than 1% accuracy loss, competing with state-of-the-art approaches.
Federated Learning (FL) is a promising distributed method for edge-level machine learning, particularly for privacysensitive applications such as those in military and medical domains, where client data cannot be shared or transferred to a cloud computing server. In many use-cases, communication cost is a major challenge in FL due to its natural intensive network usage. Client devices, such as smartphones or Internet of Things (IoT) nodes, have limited resources in terms of energy, computation, and memory. To address these hardware constraints, lightweight models and compression techniques such as pruning and quantization are commonly adopted in centralised paradigms. In this paper, we investigate the impact of compression techniques on FL for a typical image classification task. Going further, we demonstrate that a straightforward method can compresses messages up to 50% while having less than 1% of accuracy loss, competing with state-of-the-art techniques.