DeepAI AI Chat
Log In Sign Up

Achieving Personalized Federated Learning with Sparse Local Models

by   Tiansheng Huang, et al.
South China University of Technology International Student Union
TU Eindhoven

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 𝒪(1/√(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.


page 1

page 2

page 3

page 4


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

Personalized federated learning is proposed to handle the data heterogen...

Personalized Federated Learning: A Unified Framework and Universal Optimization Techniques

We study the optimization aspects of personalized Federated Learning (FL...

Communication-Efficient and Personalized Federated Lottery Ticket Learning

The lottery ticket hypothesis (LTH) claims that a deep neural network (i...

User-Centric Federated Learning

Data heterogeneity across participating devices poses one of the main ch...

Fusion of Global and Local Knowledge for Personalized Federated Learning

Personalized federated learning, as a variant of federated learning, tra...

FedPara: Low-rank Hadamard Product Parameterization for Efficient Federated Learning

To overcome the burdens on frequent model uploads and downloads during f...

Federated Learning with Diversified Preference for Humor Recognition

Understanding humor is critical to creative language modeling with many ...