ATLAS: Adaptive Tuning of Layer Sharing for Multi-Task Federated Learning
Federated Learning (FL) enables distributed learning by sharing model parameters while preserving data privacy. While it proves effective for single tasks, its application to multiple tasks remains challenging. This study proposes Adaptive Tuning of Layer Sharing (ATLAS), a method that dynamically selects shared layers and optimizes task weighting based on task similarity. ATLAS improves the efficiency and accuracy of multi-task FL while reducing communication costs.
Authors
- Takao Marukame (ORCID: https://orcid.org/0000-0001-5954-828X)
- Kota Ando (ORCID: https://orcid.org/0000-0001-8648-3768)
- F. Arai (ORCID: https://orcid.org/0009-0009-5890-7303)
- Shusuke Kawai (ORCID: https://orcid.org/0000-0003-1070-7213)
- Tetsuya Asai (ORCID: https://orcid.org/0000-0003-1158-9810)
- Itsuki Akeno (ORCID: https://orcid.org/0009-0005-3172-7522)
Institutions
- Hokkaido University (JP)
Publication Details
- Journal
- Journal of Signal Processing
- Published
- 2025-06-30
- DOI
- https://doi.org/10.2299/jsp.29.87
- Primary Topic
- Privacy-Preserving Technologies in Data
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Japan Society for the Promotion of Science
- Precursory Research for Embryonic Science and Technology