HierarchyFL: Heterogeneous Federated Learning via Hierarchical Self-Distillation
This addresses the challenge of deploying large-scale heterogeneous AIoT devices in federated learning, though it appears incremental as it builds on existing methods for model heterogeneity.
The paper tackles the problem of model inaccuracy and slow convergence in federated learning due to model heterogeneity among AIoT devices, proposing HierarchyFL, which improves model performance through hierarchical self-distillation and an ensemble library.
Federated learning (FL) has been recognized as a privacy-preserving distributed machine learning paradigm that enables knowledge sharing among various heterogeneous artificial intelligence (AIoT) devices through centralized global model aggregation. FL suffers from model inaccuracy and slow convergence due to the model heterogeneity of the AIoT devices involved. Although various existing methods try to solve the bottleneck of the model heterogeneity problem, most of them improve the accuracy of heterogeneous models in a coarse-grained manner, which makes it still a great challenge to deploy large-scale AIoT devices. To alleviate the negative impact of this problem and take full advantage of the diversity of each heterogeneous model, we propose an efficient framework named HierarchyFL, which uses a small amount of public data for efficient and scalable knowledge across a variety of differently structured models. By using self-distillation and our proposed ensemble library, each hierarchical model can intelligently learn from each other on cloud servers. Experimental results on various well-known datasets show that HierarchyFL can not only maximize the knowledge sharing among various heterogeneous models in large-scale AIoT systems, but also greatly improve the model performance of each involved heterogeneous AIoT device.