paper-with-me

홈 › Papers

Towards Optimal Heterogeneous Client Sampling in Multi-Model Federated Learning

2025-04-07 · Haoran Zhang, Zejun Gong, Zekai Li, Marie Siew, Carlee Joe-Wong, Rachid El-Azouzi

Federated learning (FL) allows edge devices to collaboratively train models without sharing local data. As FL gains popularity, clients may need to train multiple unrelated FL models, but communication constraints limit their ability to train all models simultaneously. While clients could train FL models sequentially, opportunistically having FL clients concurrently train different models -- termed multi-model federated learning (MMFL) -- can reduce the overall training time. Prior work uses simple client-to-model assignments that do not optimize the contribution of each client to each model over the course of its training. Prior work on single-model FL shows that intelligent client selection can greatly accelerate convergence, but na\"ive extensions to MMFL can violate heterogeneous resource constraints at both the server and the clients. In this work, we develop a novel convergence analysis of MMFL with arbitrary client sampling methods, theoretically demonstrating the strengths and limitations of previous well-established gradient-based methods. Motivated by this analysis, we propose MMFL-LVR, a loss-based sampling method that minimizes training variance while explicitly respecting communication limits at the server and reducing computational costs at the clients. We extend this to MMFL-StaleVR, which incorporates stale updates for improved efficiency and stability, and MMFL-StaleVRE, a lightweight variant suitable for low-overhead deployment. Experiments show our methods improve average accuracy by up to 19.1% over random sampling, with only a 5.4% gap from the theoretical optimum (full client participation).

📄 PDF Abstract BibTeX arXiv:2504.05138

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Optimal Client Sampling in Federated Learning with Client-Level Heterogeneous Differential Privacy

2025-05-19 · Jiahao Xu, Rui Hu, Olivera Kotevska

Federated Learning with client-level differential privacy (DP) provides a promising framework for collaboratively training models while rigorously protecting clients' privacy. However, classic approaches like DP-FedAvg s…

Federated Learning

Federated Multi-Armed Bandits

2021-01-28 · Chengshuai Shi, Cong Shen

Federated multi-armed bandits (FMAB) is a new bandit paradigm that parallels the federated learning (FL) framework in supervised learning. It is inspired by practical applications in cognitive radio and recommender syste…

Federated LearningMulti-Armed BanditsRecommendation Systems

Beyond ADMM: A Unified Client-variance-reduced Adaptive Federated Learning Framework

2022-12-03 · Shuai Wang, Yanqing Xu, Zhiguo Wang, Tsung-Hui Chang 외

As a novel distributed learning paradigm, federated learning (FL) faces serious challenges in dealing with massive clients with heterogeneous data distribution and computation and communication resources. Various client-…

Federated Learningimage-classificationImage ClassificationSemi-Supervised Image Classification

Federated Learning with Heterogeneous Differential Privacy

2021-10-28 · Nasser Aldaghri, Hessam Mahdavifar, Ahmad Beirami

Federated learning (FL) takes a first step towards privacy-preserving machine learning by training models while keeping client data local. Models trained using FL may still leak private client information through model u…

Federated LearningPrivacy Preserving

Adaptive LoRA Experts Allocation and Selection for Federated Fine-Tuning

2025-09-18 · Lei Wang, Jieming Bian, Letian Zhang, Jie Xu arxiv

Large Language Models (LLMs) have demonstrated impressive capabilities across various tasks, but fine-tuning them for domain-specific applications often requires substantial domain-specific data that may be distributed a…

parameter-efficient fine-tuningFederated Learning