RFDG: Reinforcement Federated Domain Generalization
- 2 August 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Knowledge and Data Engineering
- Vol. 36 (3) , 1285-1298
Abstract
During the training process of federated learning models, the domain information of the target test data on the server can differ greatly from the training data of each client, leading to a decrease in the performance of the federated model. Additionally, due to privacy protection during federated training, clients cannot see the target domain test data, and the distribution information of the target data cannot be used. This poses a new challenge for federated learning. Domain generalization techniques are often used in centralized frameworks to resolve such problems. In recent years, the domain generalization method based on feature decorrelation has enabled models to learn knowledge with a stronger generalization ability in unseen target domain data. However, existing methods require data centralization in the feature decorrelation process, which conflicts with data privacy protection in federated learning. To address these issues, we propose Reinforcement Federated Domain Generalization (RFDG), which incorporates domain generalization in federated learning via reinforcement learning. RFDG can improve the generalization ability of the federated model of unseen target domain test data. We design a reinforcement federated feature decorrelation policy that uses reinforcement learning technology to transform the sample reweight work into a parameterized sample reweight policy that can be shared among federated learning clients. We develop reinforcement federated experience replay techniques to supplement the feature information loss of local data due to the mini-batch mechanism during the policy learning process. When the policy is shared by each client, those features can be decorrelated from a global perspective, allowing the model to focus on capturing the fundamental association between features and labels to learn domain-invariant knowledge. We verified the effectiveness of our method through extensive experiments using four publicly available datasets.Keywords
Funding Information
- National Natural Science Foundation of China (62192784, U22B2038, 62172056, 62272058)
- Young Elite Scientists Sponsorship Program
- CAST (2022QNRC001)
This publication has 52 references indexed in Scilit:
- Deeper, Broader and Artier Domain Generalization2017
- Deep Domain Generalization With Structured Low-Rank ConstraintIEEE Transactions on Image Processing, 2017
- The EU General Data Protection Regulation (GDPR)2017
- Building machines that learn and think like peopleBehavioral and Brain Sciences, 2016
- Deep Learning with Differential Privacy2016
- Deep Residual Learning for Image Recognition2016
- Domain Invariant Transfer Kernel LearningIEEE Transactions on Knowledge and Data Engineering, 2014
- Microsoft COCO: Common Objects in Context2014
- Reinforcement learning in robotics: A surveyThe International Journal of Robotics Research, 2013
- Unbiased look at dataset bias2011