LGAIDCIVFeb 16, 2024

FedD2S: Personalized Data-Free Federated Knowledge Distillation

arXiv:2402.10846v17 citationsh-index: 23
Originality Incremental advance
AI Analysis

It addresses the problem of suboptimal personalization in federated learning for clients with non-iid data, offering an incremental improvement over existing methods.

The paper tackles data heterogeneity in federated learning by proposing FedD2S, a personalized federated knowledge distillation method with a deep-to-shallow layer-dropping mechanism, which shows superior performance with accelerated convergence and improved fairness across multiple image datasets.

This paper addresses the challenge of mitigating data heterogeneity among clients within a Federated Learning (FL) framework. The model-drift issue, arising from the noniid nature of client data, often results in suboptimal personalization of a global model compared to locally trained models for each client. To tackle this challenge, we propose a novel approach named FedD2S for Personalized Federated Learning (pFL), leveraging knowledge distillation. FedD2S incorporates a deep-to-shallow layer-dropping mechanism in the data-free knowledge distillation process to enhance local model personalization. Through extensive simulations on diverse image datasets-FEMNIST, CIFAR10, CINIC0, and CIFAR100-we compare FedD2S with state-of-the-art FL baselines. The proposed approach demonstrates superior performance, characterized by accelerated convergence and improved fairness among clients. The introduced layer-dropping technique effectively captures personalized knowledge, resulting in enhanced performance compared to alternative FL models. Moreover, we investigate the impact of key hyperparameters, such as the participation ratio and layer-dropping rate, providing valuable insights into the optimal configuration for FedD2S. The findings demonstrate the efficacy of adaptive layer-dropping in the knowledge distillation process to achieve enhanced personalization and performance across diverse datasets and tasks.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes