paper-with-me

Papers

Achieving Personalized Federated Learning with Sparse Local Models

2022-01-27 · Tiansheng Huang, Shiwei Liu, Li Shen, Fengxiang He, Weiwei Lin, DaCheng Tao

Federated learning (FL) is vulnerable to heterogeneously distributed data, since a common global model in FL may not adapt to the heterogeneous data distribution of each user. To counter this issue, personalized FL (PFL) was proposed to produce dedicated local models for each individual user. However, PFL is far from its maturity, because existing PFL solutions either demonstrate unsatisfactory generalization towards different model architectures or cost enormous extra computation and memory. In this work, we propose federated learning with personalized sparse mask (FedSpa), a novel PFL scheme that employs personalized sparse masks to customize sparse local models on the edge. Instead of training an intact (or dense) PFL model, FedSpa only maintains a fixed number of active parameters throughout training (aka sparse-to-sparse training), which enables users' models to achieve personalization with cheap communication, computation, and memory cost. We theoretically show that the iterates obtained by FedSpa converge to the local minimizer of the formulated SPFL problem at rate of $\mathcal{O}(\frac{1}{\sqrt{T}})$. Comprehensive experiments demonstrate that FedSpa significantly saves communication and computation costs, while simultaneously achieves higher model accuracy and faster convergence speed against several state-of-the-art PFL methods.

📄 PDF Abstract BibTeX arXiv:2201.11380

Code (0)

등록된 구현이 없습니다.

Tasks

Federated LearningPersonalized 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

DisPFL: Towards Communication-Efficient Personalized Federated Learning via Decentralized Sparse Training

2022-06-01 · Rong Dai, Li Shen, Fengxiang He, Xinmei Tian 외

Personalized federated learning is proposed to handle the data heterogeneity problem amongst clients by learning dedicated tailored local models for each user. However, existing works are often built in a centralized way…

Federated LearningPersonalized Federated Learning

On Heterogeneously Distributed Data, Sparsity Matters

2021-09-29 · Tiansheng Huang, Shiwei Liu, Li Shen, Fengxiang He 외

Federated learning (FL) is particularly vulnerable to heterogeneously distributed data, since a common global model in FL may not adapt to the heterogeneous data distribution of each user. To counter this issue, personal…

Federated LearningPersonalized Federated Learning

H-FedSN: Personalized Sparse Networks for Efficient and Accurate Hierarchical Federated Learning for IoT Applications

2024-12-09 · Jiechao Gao, Yuangang Li, Yue Zhao, Brad Campbell

The proliferation of Internet of Things (IoT) has increased interest in federated learning (FL) for privacy-preserving distributed data utilization. However, traditional two-tier FL architectures inadequately adapt to mu…

Federated LearningPrivacy Preserving

FAM: fast adaptive federated meta-learning

2023-08-26 · Indrajeet Kumar Sinha, Shekhar Verma, Krishna Pratap Singh

In this work, we propose a fast adaptive federated meta-learning (FAM) framework for collaboratively learning a single global model, which can then be personalized locally on individual clients. Federated learning enable…

Federated LearningMeta-Learning

Fusion of Global and Local Knowledge for Personalized Federated Learning

2023-02-21 · Tiansheng Huang, Li Shen, Yan Sun, Weiwei Lin 외

Personalized federated learning, as a variant of federated learning, trains customized models for clients using their heterogeneously distributed data. However, it is still inconclusive about how to design personalized m…

Federated LearningPersonalized Federated Learning