paper-with-me

홈 › Papers

OledFL: Unleashing the Potential of Decentralized Federated Learning via Opposite Lookahead Enhancement

2024-10-09 · Qinglun Li, Miao Zhang, Mengzhu Wang, Quanjun Yin, Li Shen

Decentralized Federated Learning (DFL) surpasses Centralized Federated Learning (CFL) in terms of faster training, privacy preservation, and light communication, making it a promising alternative in the field of federated learning. However, DFL still exhibits significant disparities with CFL in terms of generalization ability such as rarely theoretical understanding and degraded empirical performance due to severe inconsistency. In this paper, we enhance the consistency of DFL by developing an opposite lookahead enhancement technique (Ole), yielding OledFL to optimize the initialization of each client in each communication round, thus significantly improving both the generalization and convergence speed. Moreover, we rigorously establish its convergence rate in non-convex setting and characterize its generalization bound through uniform stability, which provides concrete reasons why OledFL can achieve both the fast convergence speed and high generalization ability. Extensive experiments conducted on the CIFAR10 and CIFAR100 datasets with Dirichlet and Pathological distributions illustrate that our OledFL can achieve up to 5\% performance improvement and 8$\times$ speedup, compared to the most popular DFedAvg optimizer in DFL.

📄 PDF Abstract BibTeX arXiv:2410.06482

Code (0)

등록된 구현이 없습니다.

Tasks

Federated Learning

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Adversarial Robustness Unhardening via Backdoor Attacks in Federated Learning

2023-10-17 · Taejin Kim, Jiarui Li, Shubhranshu Singh, Nikhil Madaan 외

In today's data-driven landscape, the delicate equilibrium between safeguarding user privacy and unleashing data potential stands as a paramount concern. Federated learning, which enables collaborative model training wit…

Adversarial RobustnessFederated Learning

FedWCM: Unleashing the Potential of Momentum-based Federated Learning in Long-Tailed Scenarios

2025-07-20 · Tianle Li, Yongzhi Huang, Linshan Jiang, Qipeng Xie 외 arxiv

Federated Learning (FL) enables decentralized model training while preserving data privacy. Despite its benefits, FL faces challenges with non-identically distributed (non-IID) data, especially in long-tailed scenarios w…

Federated Learning

A Decentralized Federated Learning Framework via Committee Mechanism with Convergence Guarantee

2021-08-01 · Chunjiang Che, XiaoLi Li, Chuan Chen, Xiaoyu He 외

Federated learning allows multiple participants to collaboratively train an efficient model without exposing data privacy. However, this distributed machine learning training method is prone to attacks from Byzantine cli…

Federated Learning

Fed-DART and FACT: A solution for Federated Learning in a production environment

2022-05-23 · Nico Weber, Patrick Holzer, Tania Jacob, Enislay Ramentol

Federated Learning as a decentralized artificial intelligence (AI) solution solves a variety of problems in industrial applications. It enables a continuously self-improving AI, which can be deployed everywhere at the ed…

Federated Learning

Decentralized Federated Learning: A Survey on Security and Privacy

2024-01-25 · Ehsan Hallaji, Roozbeh Razavi-Far, Mehrdad Saif, Boyu Wang 외

Federated learning has been rapidly evolving and gaining popularity in recent years due to its privacy-preserving features, among other advantages. Nevertheless, the exchange of model updates and gradients in this archit…

Federated LearningPrivacy PreservingSurvey