Federated Multi-Target Domain Adaptation
arXiv:2108.07792
Abstract
Federated learning methods enable us to train machine learning models on distributed user data while preserving its privacy. However, it is not always feasible to obtain high-quality supervisory signals from users, especially for vision tasks. Unlike typical federated settings with labeled client data, we consider a more practical scenario where the distributed client data is unlabeled, and a centralized labeled dataset is available on the server. We further take the server-client and inter-client domain shifts into account and pose a domain adaptation problem with one source (centralized server data) and multiple targets (distributed client data). Within this new Federated Multi-Target Domain Adaptation (FMTDA) task, we analyze the model performance of exiting domain adaptation methods and propose an effective DualAdapt method to address the new challenges. Extensive experimental results on image classification and semantic segmentation tasks demonstrate that our method achieves high accuracy, incurs minimal communication cost, and requires low computational resources on client devices.
References in corpus (10)
- Rethinking Atrous Convolution for Semantic Image Segmentation
- mixup: Beyond Empirical Risk Minimization
- Deep Domain Confusion: Maximizing for Domain Invariance
- Measuring the Effects of Non-Identical Data Distribution for Federated Visual Classification
- Secure Federated Transfer Learning
- Beyond Sharing Weights for Deep Domain Adaptation
- DeepJDOT: Deep Joint Distribution Optimal Transport for Unsupervised Domain Adaptation
- A Unified Feature Disentangler for Multi-Domain Image Translation and Manipulation
- Salvaging Federated Learning by Local Adaptation
- Multi-target Unsupervised Domain Adaptation without Exactly Shared Categories