paper-with-me

홈 › Papers

FedSUM Family: Efficient Federated Learning Methods under Arbitrary Client Participation

2025-12-20 · Runze You, Shi Pu arxiv

Federated Learning (FL) methods are often designed for specific client participation patterns, limiting their applicability in practical deployments. We introduce the FedSUM family of algorithms, which supports arbitrary client participation without additional assumptions on data heterogeneity. Our framework models participation variability with two delay metrics, the maximum delay $τ_{\max}$ and the average delay $τ_{\text{avg}}$. The FedSUM family comprises three variants: FedSUM-B (basic version), FedSUM (standard version), and FedSUM-CR (communication-reduced version). We provide unified convergence guarantees demonstrating the effectiveness of our approach across diverse participation patterns, thereby broadening the applicability of FL in real-world scenarios.

📄 PDF Abstract BibTeX arXiv:2512.18275

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Similar Papers 제목 키워드 기반

Personalized Federated Learning via Gradient Modulation for Heterogeneous Text Summarization

2023-04-23 · Rongfeng Pan, Jianzong Wang, Lingwei Kong, Zhangcheng Huang 외

Text summarization is essential for information aggregation and demands large amounts of training data. However, concerns about data privacy and security limit data collection and model training. To eliminate this concer…

Federated LearningPersonalized Federated LearningText Summarization

A Unified Analysis of Stochastic Gradient Methods for Nonconvex Federated Optimization

2020-06-12 · Zhize Li, Peter Richtárik

In this paper, we study the performance of a large family of SGD variants in the smooth nonconvex regime. To this end, we propose a generic and flexible assumption capable of accurate modeling of the second moment of the…

FDA-Opt: Communication-Efficient Federated Fine-Tuning of Language Models

2025-05-07 · Michail Theologitis, Vasilis Samoladas, Antonios Deligiannakis

Federated Learning (FL) enables the utilization of vast, previously inaccessible data sources. At the same time, pre-trained Language Models (LMs) have taken the world by storm and for good reason. They exhibit remarkabl…

Federated Learning

Rethinking Byzantine Robustness in Federated Recommendation from Sparse Aggregation Perspective

2025-01-06 · Zhongjian Zhang, Mengmei Zhang, Xiao Wang, Lingjuan Lyu 외

To preserve user privacy in recommender systems, federated recommendation (FR) based on federated learning (FL) emerges, keeping the personal data on the local client and updating a model collaboratively. Unlike FL, FR h…

Federated LearningRecommendation Systems

FedGS: Federated Graph-based Sampling with Arbitrary Client Availability

2022-11-25 · Zheng Wang, Xiaoliang Fan, Jianzhong Qi, Haibing Jin 외

While federated learning has shown strong results in optimizing a machine learning model without direct access to the original data, its performance may be hindered by intermittent client availability which slows down th…

Federated Learning