Rehearsal-free Federated Domain-incremental Learning
Sun, Rui Duan, Haoran Dong, Jiahua Ojha, Varun Kumar Shah, Tejal Ranjan, Rajiv
Sun, Rui
Duan, Haoran
Dong, Jiahua
Ojha, Varun Kumar
Shah, Tejal
Ranjan, Rajiv
Supervisor
Department
Computer Vision
Embargo End Date
Type
Conference proceeding
Date
2025
License
Language
English
Collections
Research Projects
Organizational Units
Journal Issue
Abstract
We introduce a rehearsal-free federated domain incremental learning framework, RefFiL, based on a global prompt-sharing paradigm to alleviate catastrophic forgetting challenges in federated domain-incremental learning, where unseen domains are continually learned. Typical methods for mitigating forgetting, such as the use of additional datasets and the retention of private data from earlier tasks, are not viable in federated learning (FL) due to devices' limited resources. Our method, RefFiL, addresses this by learning domain-invariant knowledge and incorporating various domain-specific prompts from the domains represented by different FL participants. A key feature of RefFiL is the generation of local finegrained prompts by our domain adaptive prompt generator, which effectively learns from local domain knowledge while maintaining distinctive boundaries on a global scale. We also introduce a domain-specific prompt contrastive learning loss that differentiates between locally generated prompts and those from other domains, enhancing RefFiL's precision and effectiveness. Compared to existing methods, RefFiL significantly alleviates catastrophic forgetting without requiring extra memory space, making it ideal for privacy-sensitive and resource-constrained devices.
Citation
R. Sun, H. Duan, J. Dong, V. Ojha, T. Shah and R. Ranjan, "Rehearsal-free Federated Domain-incremental Learning," 2025 IEEE 45th International Conference on Distributed Computing Systems (ICDCS), Glasgow, United Kingdom, 2025, pp. 835-845, doi: 10.1109/ICDCS63083.2025.00086.
Source
Proceedings - International Conference on Distributed Computing Systems
Conference
45th IEEE International Conference on Distributed Computing Systems, ICDCS 2025
Keywords
Continual Learning, Distributed Machine Learning, Edge AI, Federated Learning
Subjects
Source
45th IEEE International Conference on Distributed Computing Systems, ICDCS 2025
Publisher
IEEE