paper-with-me

Papers

FedD2S: Personalized Data-Free Federated Knowledge Distillation

2024-02-16 · Kawa Atapour, S. Jamal Seyedmohammadi, Jamshid Abouei, Arash Mohammadi, Konstantinos N. Plataniotis

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.

📄 PDF Abstract BibTeX arXiv:2402.10846

Code (0)

등록된 구현이 없습니다.

Tasks

Data-free Knowledge DistillationFairnessFederated LearningKnowledge DistillationPersonalized Federated Learning

Methods 이 논문이 사용한 방법론

Knowledge Distillation A very simple way to improve the performance of almost any machine learning algorithm is to train many different models on the same data and then to average their predictions.…

Similar Papers 제목 키워드 기반

pFedDSH: Enabling Knowledge Transfer in Personalized Federated Learning through Data-free Sub-Hypernetwork

2025-08-07 · Thinh Nguyen, Le Huy Khiem, Van-Tuan Tran, Khoa D Doan 외 arxiv

Federated Learning (FL) enables collaborative model training across distributed clients without sharing raw data, offering a significant privacy benefit. However, most existing Personalized Federated Learning (pFL) metho…

Personalized Federated LearningContinual Learning

FedDr+: Stabilizing Dot-regression with Global Feature Distillation for Federated Learning

2024-06-04 · Seongyoon Kim, Minchan Jeong, Sungnyun Kim, Sungwoo Cho 외

Federated Learning (FL) has emerged as a pivotal framework for the development of effective global models (global FL) or personalized models (personalized FL) across clients with heterogeneous, non-iid data distribution.…

Federated Learningregression

Decoupling General and Personalized Knowledge in Federated Learning via Additive and Low-Rank Decomposition

2024-06-28 · Xinghao Wu, Xuefeng Liu, Jianwei Niu, Haolin Wang 외

To address data heterogeneity, the key strategy of Personalized Federated Learning (PFL) is to decouple general knowledge (shared among clients) and client-specific knowledge, as the latter can have a negative impact on …

Federated LearningGeneral KnowledgePersonalized Federated Learning

Personalization Disentanglement for Federated Learning: An explainable perspective

2023-06-06 · Peng Yan, Guodong Long

Personalized federated learning (PFL) jointly trains a variety of local models through balancing between knowledge sharing across clients and model personalization per client. This paper addresses PFL via explicit disent…

DisentanglementFederated LearningPersonalized Federated Learning

FedDWA: Personalized Federated Learning with Dynamic Weight Adjustment

2023-05-10 · Jiahao Liu, Jiang Wu, Jinyu Chen, Miao Hu 외

Different from conventional federated learning, personalized federated learning (PFL) is able to train a customized model for each individual client according to its unique requirement. The mainstream approach is to adop…

Federated LearningPersonalized Federated Learning