paper-with-me

Papers

Spectral Co-Distillation for Personalized Federated Learning

2024-01-29 · NeurIPS 2023 11 · Zihan Chen, Howard H. Yang, Tony Q. S. Quek, Kai Fong Ernest Chong

Personalized federated learning (PFL) has been widely investigated to address the challenge of data heterogeneity, especially when a single generic model is inadequate in satisfying the diverse performance requirements of local clients simultaneously. Existing PFL methods are inherently based on the idea that the relations between the generic global and personalized local models are captured by the similarity of model weights. Such a similarity is primarily based on either partitioning the model architecture into generic versus personalized components, or modeling client relationships via model weights. To better capture similar (yet distinct) generic versus personalized model representations, we propose \textit{spectral distillation}, a novel distillation method based on model spectrum information. Building upon spectral distillation, we also introduce a co-distillation framework that establishes a two-way bridge between generic and personalized model training. Moreover, to utilize the local idle time in conventional PFL, we propose a wait-free local training protocol. Through extensive experiments on multiple datasets over diverse heterogeneous data settings, we demonstrate the outperformance and efficacy of our proposed spectral co-distillation method, as well as our wait-free training protocol.

📄 PDF Abstract BibTeX arXiv:2401.17124

Code (1)

jimmyc96/spectral-dis-fl 공식 구현 pytorch

Tasks

Federated LearningPersonalized Federated Learning

Similar Papers 제목 키워드 기반

Towards Personalized Federated Learning via Comprehensive Knowledge Distillation

2024-11-06 · Pengju Wang, Bochao Liu, Weijia Guo, Yong Li 외

Federated learning is a distributed machine learning paradigm designed to protect data privacy. However, data heterogeneity across various clients results in catastrophic forgetting, where the model rapidly forgets previ…

Federated LearningKnowledge DistillationPersonalized Federated Learning

Personalized Federated Learning via Backbone Self-Distillation

2024-09-24 · Pengju Wang, Bochao Liu, Dan Zeng, Chenggang Yan 외

In practical scenarios, federated learning frequently necessitates training personalized models for each client using heterogeneous data. This paper proposes a backbone self-distillation approach to facilitate personaliz…

Federated LearningPersonalized Federated LearningTransfer Learning

Personalized Federated Learning through Global Knowledge Distillation and Local Head Adaptation

2026-09-15 · Polycarpo Souza Neto, José Mairton Barros da Silva Júnior, Charles Casimiro Cavalcante arxiv

Statistical heterogeneity limits federated learning when a single global classifier cannot represent client-specific label distributions. In this work, we propose Personalized Federated Knowledge Distillation with Head A…

Personalized Federated LearningKnowledge Distillation

Tailored Federated Learning: Leveraging Direction Regulation & Knowledge Distillation

2024-09-29 · Huidong Tang, Chen Li, Huachong Yu, Sayaka Kamei 외

Federated learning (FL) has emerged as a transformative training paradigm, particularly invaluable in privacy-sensitive domains like healthcare. However, client heterogeneity in data, computing power, and tasks poses a s…

Federated LearningKnowledge Distillation

FedSSP: Federated Graph Learning with Spectral Knowledge and Personalized Preference

2024-10-26 · Zihan Tan, Guancheng Wan, Wenke Huang, Mang Ye

Personalized Federated Graph Learning (pFGL) facilitates the decentralized training of Graph Neural Networks (GNNs) without compromising privacy while accommodating personalized requirements for non-IID participants. In …

Graph Learning