paper-with-me

홈 › Papers

Enhance Local Consistency in Federated Learning: A Multi-Step Inertial Momentum Approach

2023-02-11 · Yixing Liu, Yan Sun, Zhengtao Ding, Li Shen, Bo Liu, DaCheng Tao

Federated learning (FL), as a collaborative distributed training paradigm with several edge computing devices under the coordination of a centralized server, is plagued by inconsistent local stationary points due to the heterogeneity of the local partial participation clients, which precipitates the local client-drifts problems and sparks off the unstable and slow convergence, especially on the aggravated heterogeneous dataset. To address these issues, we propose a novel federated learning algorithm, named FedMIM, which adopts the multi-step inertial momentum on the edge devices and enhances the local consistency for free during the training to improve the robustness of the heterogeneity. Specifically, we incorporate the weighted global gradient estimations as the inertial correction terms to guide both the local iterates and stochastic gradient estimation, which can reckon the global objective optimization on the edges' heterogeneous dataset naturally and maintain the demanding consistent iteration locally. Theoretically, we show that FedMIM achieves the $\mathcal{O}(\frac{1}{\sqrt{SKT}})$ convergence rate with a linear speedup property with respect to the number of selected clients $S$ and proper local interval $K$ in communication round $T$ without convex assumption. Empirically, we conduct comprehensive experiments on various real-world datasets and demonstrate the efficacy of the proposed FedMIM against several state-of-the-art baselines.

📄 PDF Abstract BibTeX arXiv:2302.05726

Code (0)

등록된 구현이 없습니다.

Tasks

Edge-computingFederated Learning

Similar Papers 제목 키워드 기반

From Deterioration to Acceleration: A Calibration Approach to Rehabilitating Step Asynchronism in Federated Optimization

2021-12-17 · Feijie Wu, Song Guo, Haozhao Wang, Zhihao Qu 외

In the setting of federated optimization, where a global model is aggregated periodically, step asynchronism occurs when participants conduct model training by efficiently utilizing their computational resources. It is w…

Cross-Training with Multi-View Knowledge Fusion for Heterogenous Federated Learning

2024-05-30 · Zhuang Qi, Lei Meng, Weihao He, Ruohan Zhang 외

Federated learning benefits from cross-training strategies, which enables models to train on data from distinct sources to improve the generalization capability. However, the data heterogeneity between sources may lead m…

Federated LearningRepresentation Learning

FedProphet: Memory-Efficient Federated Adversarial Training via Theoretic-Robustness and Low-Inconsistency Cascade Learning

2024-09-12 · Minxue Tang, Yitu Wang, Jingyang Zhang, Louis DiValentin 외

Federated Learning (FL) provides a strong privacy guarantee by enabling local training across edge devices without training data sharing, and Federated Adversarial Training (FAT) further enhances the robustness against a…

Adversarial RobustnessFederated Learning

FedAS: Bridging Inconsistency in Personalized Federated Learning

2024-01-01 · CVPR 2024 1 · Xiyuan Yang, Wenke Huang, Mang Ye

Personalized Federated Learning (PFL) is primarily designed to provide customized models for each client to better fit the non-iid distributed client data which is a inherent challenge in Federated Learning. However …

Federated LearningPersonalized Federated Learning

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…