Label driven Knowledge Distillation for Federated Learning with non-IID Data

TL;DR

This paper introduces F2L, a hierarchical federated learning framework that employs label-driven knowledge distillation to improve scalability and robustness against non-IID data, achieving faster convergence and better efficiency.

Contribution

The paper proposes a novel hierarchical FL framework with label-driven knowledge distillation, enhancing scalability and robustness in non-IID data environments.

Findings

F2L significantly improves FL efficiency across global distillations.

F2L achieves rapid convergence during training.

The method effectively reduces divergence between client models.

Abstract

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.