FACT: Federated Adversarial Cross Training
Preprint
Abstract
Federated Learning (FL) facilitates distributed model development to aggregate multiple confidential data sources. The information transfer among clients can be compromised by distributional differences, i.e., by non-i.i.d. data. A particularly challenging scenario is the federated model adaptation to a target client without access to annotated data. We propose Federated Adversarial Cross Training (FACT), which uses the implicit domain differences between source clients to identify domain shifts in the target domain. In each round of FL, FACT cross initializes a pair of source clients to generate domain specialized representations which are then used as a direct adversary to learn a domain invariant data representation. We empirically show that FACT outperforms state-of-the-art federated, non-federated and source-free domain adaptation models on three popular multi-source-single-target benchmarks, and state-of-the-art Unsupervised Domain Adaptation (UDA) models on single-source-single-target experiments. We further study FACT's behavior with respect to communication restrictions and the number of participating clients.Keywords
All Related Versions
This publication has 4 references indexed in Scilit:
- Gradient Matching Federated Domain Adaptation for Brain Image ClassificationIEEE Transactions on Neural Networks and Learning Systems, 2022
- Multi-site fMRI analysis using privacy-preserving federated learning and domain adaptation: ABIDE resultsMedical Image Analysis, 2020
- A Secure Federated Transfer Learning FrameworkIEEE Intelligent Systems, 2020
- A theory of learning from different domainsMachine Learning, 2009