paper-with-me

홈 › Papers

Boosting the Performance of Decentralized Federated Learning via Catalyst Acceleration

2024-10-09 · Qinglun Li, Miao Zhang, Yingqi Liu, Quanjun Yin, Li Shen, Xiaochun Cao

Decentralized Federated Learning has emerged as an alternative to centralized architectures due to its faster training, privacy preservation, and reduced communication overhead. In decentralized communication, the server aggregation phase in Centralized Federated Learning shifts to the client side, which means that clients connect with each other in a peer-to-peer manner. However, compared to the centralized mode, data heterogeneity in Decentralized Federated Learning will cause larger variances between aggregated models, which leads to slow convergence in training and poor generalization performance in tests. To address these issues, we introduce Catalyst Acceleration and propose an acceleration Decentralized Federated Learning algorithm called DFedCata. It consists of two main components: the Moreau envelope function, which primarily addresses parameter inconsistencies among clients caused by data heterogeneity, and Nesterov's extrapolation step, which accelerates the aggregation phase. Theoretically, we prove the optimization error bound and generalization error bound of the algorithm, providing a further understanding of the nature of the algorithm and the theoretical perspectives on the hyperparameter choice. Empirically, we demonstrate the advantages of the proposed algorithm in both convergence speed and generalization performance on CIFAR10/100 with various non-iid data distributions. Furthermore, we also experimentally verify the theoretical properties of DFedCata.

📄 PDF Abstract BibTeX arXiv:2410.07272

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

DCatalyst: A Unified Accelerated Framework for Decentralized Optimization

2025-01-30 · Tianyu Cao, Xiaokai Chen, Gesualdo Scutari

We study decentralized optimization over a network of agents, modeled as graphs, with no central server. The goal is to minimize $f+r$, where $f$ represents a (strongly) convex function averaging the local agents' losses…

Local Superior Soups: A Catalyst for Model Merging in Cross-Silo Federated Learning

2024-10-31 · Minghui Chen, Meirui Jiang, Xin Zhang, Qi Dou 외

Federated learning (FL) is a learning paradigm that enables collaborative training of models using decentralized data. Recently, the utilization of pre-trained weight initialization in FL has been demonstrated to effecti…

Federated Learning

Catalyst Acceleration for First-order Convex Optimization: from Theory to Practice

2017-12-15 · Hongzhou Lin, Julien Mairal, Zaid Harchaoui

We introduce a generic scheme for accelerating gradient-based optimization methods in the sense of Nesterov. The approach, called Catalyst, builds upon the inexact accelerated proximal point algorithm for minimizing a co…

Federated Learning for Open Banking

2021-08-24 · Guodong Long, Yue Tan, Jing Jiang, Chengqi Zhang

Open banking enables individual customers to own their banking data, which provides fundamental support for the boosting of a new ecosystem of data marketplaces and financial services. In the near future, it is foreseeab…

Federated Learning

Efficient Algorithms for Federated Saddle Point Optimization

2021-02-12 · Charlie Hou, Kiran K. Thekumparampil, Giulia Fanti, Sewoong Oh

We consider strongly convex-concave minimax problems in the federated setting, where the communication constraint is the main bottleneck. When clients are arbitrarily heterogeneous, a simple Minibatch Mirror-prox achieve…