GRP-FED: Addressing Client Imbalance in Federated Learning via Global-Regularized Personalization

08/31/2021
by   Yen-Hsiu Chou, et al.
0

Since data is presented long-tailed in reality, it is challenging for Federated Learning (FL) to train across decentralized clients as practical applications. We present Global-Regularized Personalization (GRP-FED) to tackle the data imbalanced issue by considering a single global model and multiple local models for each client. With adaptive aggregation, the global model treats multiple clients fairly and mitigates the global long-tailed issue. Each local model is learned from the local data and aligns with its distribution for customization. To prevent the local model from just overfitting, GRP-FED applies an adversarial discriminator to regularize between the learned global-local features. Extensive results show that our GRP-FED improves under both global and local scenarios on real-world MIT-BIH and synthesis CIFAR-10 datasets, achieving comparable performance and addressing client imbalance.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
06/24/2021

Federated Noisy Client Learning

Federated learning (FL) collaboratively aggregates a shared global model...
research
10/13/2021

Communication-Efficient Online Federated Learning Framework for Nonlinear Regression

Federated learning (FL) literature typically assumes that each client ha...
research
01/25/2023

Integrating Local Real Data with Global Gradient Prototypes for Classifier Re-Balancing in Federated Long-Tailed Learning

Federated Learning (FL) has become a popular distributed learning paradi...
research
07/27/2023

Federated Model Aggregation via Self-Supervised Priors for Highly Imbalanced Medical Image Classification

In the medical field, federated learning commonly deals with highly imba...
research
05/23/2023

Federated Generalized Category Discovery

Generalized category discovery (GCD) aims at grouping unlabeled samples ...
research
06/30/2022

Towards Federated Long-Tailed Learning

Data privacy and class imbalance are the norm rather than the exception ...
research
06/02/2023

Federated Learning of Models Pre-Trained on Different Features with Consensus Graphs

Learning an effective global model on private and decentralized datasets...

Please sign up or login with your details

Forgot password? Click here to reset