Federated Learning on Non-iid Data via Local and Global Distillation
arXiv:2306.14443 · doi:10.1109/ICWS60048.2023.00083
Abstract
Most existing federated learning algorithms are based on the vanilla FedAvg scheme. However, with the increase of data complexity and the number of model parameters, the amount of communication traffic and the number of iteration rounds for training such algorithms increases significantly, especially in non-independently and homogeneously distributed scenarios, where they do not achieve satisfactory performance. In this work, we propose FedND: federated learning with noise distillation. The main idea is to use knowledge distillation to optimize the model training process. In the client, we propose a self-distillation method to train the local model. In the server, we generate noisy samples for each client and use them to distill other clients. Finally, the global model is obtained by the aggregation of local models. Experimental results show that the algorithm achieves the best performance and is more communication-efficient than state-of-the-art methods.
Accpeted in IEEE ICWS 2023
References in corpus (12)
- Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms
- Federated Optimization: Distributed Machine Learning for On-Device Intelligence
- Tackling the Objective Inconsistency Problem in Heterogeneous Federated Optimization
- Ensemble Distillation for Robust Model Fusion in Federated Learning
- FedMD: Heterogenous Federated Learning via Model Distillation
- Differential Private Knowledge Transfer for Privacy-Preserving Cross-Domain Recommendation
- Clustered Sampling: Low-Variance and Improved Representativity for Clients Selection in Federated Learning
- Local-Global Knowledge Distillation in Heterogeneous Federated Learning with Non-IID Data
- FedHe: Heterogeneous Models and Communication-Efficient Federated Learning
- FedCM: Federated Learning with Client-level Momentum
- Exploiting Data Sparsity in Secure Cross-Platform Social Recommendation
- FedDTG:Federated Data-Free Knowledge Distillation via Three-Player Generative Adversarial Networks