paper-with-me

홈 › Papers

FedTSA: A Cluster-based Two-Stage Aggregation Method for Model-heterogeneous Federated Learning

2024-07-06 · Boyu Fan, Chenrui Wu, Xiang Su, Pan Hui

Despite extensive research into data heterogeneity in federated learning (FL), system heterogeneity remains a significant yet often overlooked challenge. Traditional FL approaches typically assume homogeneous hardware resources across FL clients, implying that clients can train a global model within a comparable time frame. However, in practical FL systems, clients often have heterogeneous resources, which impacts their training capacity. This discrepancy underscores the importance of exploring model-heterogeneous FL, a paradigm allowing clients to train different models based on their resource capabilities. To address this challenge, we introduce FedTSA, a cluster-based two-stage aggregation method tailored for system heterogeneity in FL. FedTSA begins by clustering clients based on their capabilities, then performs a two-stage aggregation: conventional weight averaging for homogeneous models in Stage 1, and deep mutual learning with a diffusion model for aggregating heterogeneous models in Stage 2. Extensive experiments demonstrate that FedTSA not only outperforms the baselines but also explores various factors influencing model performance, validating FedTSA as a promising approach for model-heterogeneous FL.

📄 PDF Abstract BibTeX arXiv:2407.05098

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

A Semi-Supervised Federated Learning Framework with Hierarchical Clustering Aggregation for Heterogeneous Satellite Networks

2025-07-30 · Zhuocheng Liu, Zhishu Shen, Qiushi Zheng, Tiehua Zhang 외 arxiv

Low Earth Orbit (LEO) satellites are emerging as key components of 6G networks, with many already deployed to support large-scale Earth observation and sensing related tasks. Federated Learning (FL) presents a promising …

Federated Learning

Differentially Private Clustered Federated Learning with Privacy-Preserving Initialization and Normality-Driven Aggregation

2026-04-22 · Jie Xu, Haaris Mehmood, Rogier Van Dalen, Karthikeyan Saravanan 외 arxiv

Federated learning (FL) enables training of a global model while keeping raw data on end-devices. Despite this, FL has shown to leak private user information and thus in practice, it is often coupled with methods such as…

Federated Learning

Decoupled Federated Learning on Long-Tailed and Non-IID data with Feature Statistics

2024-03-13 · Zhuoxin Chen, Zhenyu Wu, Yang Ji

Federated learning is designed to enhance data security and privacy, but faces challenges when dealing with heterogeneous data in long-tailed and non-IID distributions. This paper explores an overlooked scenario where ta…

Federated Learning

One-shot Robust Federated Learning of Independent Component Analysis

2025-05-26 · Dian Jin, Xin Bing, Yuqian Zhang arxiv

This paper studies robust one-shot aggregation for distributed and federated Independent Component Analysis (ICA). In this setting, each client computes a local ICA estimator, while the server aims to recover a common gl…

Enhanced Federated Deep Multi-View Clustering under Uncertainty Scenario

2025-11-19 · Bingjun Wei, Xuemei Cao, Jiafen Liu, Haoyang Liang 외 arxiv

Traditional Federated Multi-View Clustering assumes uniform views across clients, yet practical deployments reveal heterogeneous view completeness with prevalent incomplete, redundant, or corrupted data. While recent app…