Federated Learning with Domain Generalization

by   Liling Zhang, et al.

Federated Learning (FL) enables a group of clients to jointly train a machine learning model with the help of a centralized server. Clients do not need to submit their local data to the server during training, and hence the local training data of clients is protected. In FL, distributed clients collect their local data independently, so the dataset of each client may naturally form a distinct source domain. In practice, the model trained over multiple source domains may have poor generalization performance on unseen target domains. To address this issue, we propose FedADG to equip federated learning with domain generalization capability. FedADG employs the federated adversarial learning approach to measure and align the distributions among different source domains via matching each distribution to a reference distribution. The reference distribution is adaptively generated (by accommodating all source domains) to minimize the domain shift distance during alignment. In FedADG, the alignment is fine-grained since each class is aligned independently. In this way, the learned feature representation is supposed to be universal, so it can generalize well on the unseen domains. Extensive experiments on various datasets demonstrate that FedADG has better performance than most of the previous solutions even if they have an additional advantage that allows centralized data access. To support study reproducibility, the project codes are available in https://github.com/wzml/FedADG


page 1

page 2

page 3

page 4


Acceleration of Federated Learning with Alleviated Forgetting in Local Training

Federated learning (FL) enables distributed optimization of machine lear...

Cross-Silo Prototypical Calibration for Federated Learning with Non-IID Data

Federated Learning aims to learn a global model on the server side that ...

Physics-Driven Spectrum-Consistent Federated Learning for Palmprint Verification

Palmprint as biometrics has gained increasing attention recently due to ...

FedILC: Weighted Geometric Mean and Invariant Gradient Covariance for Federated Learning on Non-IID Data

Federated learning is a distributed machine learning approach which enab...

Multi-Source Domain Adaptation Based on Federated Knowledge Alignment

Federated Learning (FL) facilitates distributed model learning to protec...

Federated Domain Generalization: A Survey

Machine learning typically relies on the assumption that training and te...

Please sign up or login with your details

Forgot password? Click here to reset