Label driven Knowledge Distillation for Federated Learning with non-IID Data
This addresses scalability and robustness issues in FL for applications like IoT networks with non-IID data, representing an incremental improvement.
The paper tackles the challenges of scalability and data heterogeneity in Federated Learning (FL) by proposing a Full-stack FL (F2L) framework with a hierarchical network architecture and a label-driven knowledge distillation (LKD) technique, which significantly improves overall FL efficiency and achieves rapid convergence in global distillation stages.
In real-world applications, Federated Learning (FL) meets two challenges: (1) scalability, especially when applied to massive IoT networks; and (2) how to be robust against an environment with heterogeneous data. Realizing the first problem, we aim to design a novel FL framework named Full-stack FL (F2L). More specifically, F2L utilizes a hierarchical network architecture, making extending the FL network accessible without reconstructing the whole network system. Moreover, leveraging the advantages of hierarchical network design, we propose a new label-driven knowledge distillation (LKD) technique at the global server to address the second problem. As opposed to current knowledge distillation techniques, LKD is capable of training a student model, which consists of good knowledge from all teachers' models. Therefore, our proposed algorithm can effectively extract the knowledge of the regions' data distribution (i.e., the regional aggregated models) to reduce the divergence between clients' models when operating under the FL system with non-independent identically distributed data. Extensive experiment results reveal that: (i) our F2L method can significantly improve the overall FL efficiency in all global distillations, and (ii) F2L rapidly achieves convergence as global distillation stages occur instead of increasing on each communication cycle.