FedNC: A Secure and Efficient Federated Learning Method with Network Coding
This work addresses privacy breaches and system inefficiencies in Federated Learning, offering a new approach that could benefit distributed learning systems, though it appears incremental as it adapts an existing technique (Network Coding) to FL.
The paper tackles privacy and efficiency challenges in Federated Learning by introducing FedNC, a novel framework that uses Network Coding to mix local model parameters via random linear combinations, resulting in improved security, efficiency, and robustness as shown in theoretical and experimental analyses.
Federated Learning (FL) is a promising distributed learning mechanism which still faces two major challenges, namely privacy breaches and system efficiency. In this work, we reconceptualize the FL system from the perspective of network information theory, and formulate an original FL communication framework, FedNC, which is inspired by Network Coding (NC). The main idea of FedNC is mixing the information of the local models by making random linear combinations of the original parameters, before uploading for further aggregation. Due to the benefits of the coding scheme, both theoretical and experimental analysis indicate that FedNC improves the performance of traditional FL in several important ways, including security, efficiency, and robustness. To the best of our knowledge, this is the first framework where NC is introduced in FL. As FL continues to evolve within practical network frameworks, more variants can be further designed based on FedNC.