Wang, J;
Jin, Y;
Stoyanov, D;
Wang, L;
(2023)
FedDP: Dual Personalization in Federated Medical Image Segmentation.
IEEE Transactions on Medical Imaging
10.1109/TMI.2023.3299206.
(In press).
Preview |
Text
FedDP_Dual_Personalization_in_Federated_Medical_Image_Segmentation.pdf - Accepted Version Download (7MB) | Preview |
Abstract
Personalized federated learning (PFL) addresses the data heterogeneity challenge faced by general federated learning (GFL). Rather than learning a single global model, with PFL a collection of models are adapted to the unique feature distribution of each site. However, current PFL methods rarely consider self-attention networks which can handle data heterogeneity by long-range dependency modeling and they do not utilize prediction inconsistencies in local models as an indicator of site uniqueness. In this paper, we propose <italic>FedDP</italic>, a novel federated learning scheme with dual personalization, which improves model personalization from both feature and prediction aspects to boost image segmentation results. We leverage long-range dependencies by designing a <italic>local query</italic> (LQ) that decouples the query embedding layer out of each local model, whose parameters are trained privately to better adapt to the respective feature distribution of the site. We then propose <italic>inconsistency-guided calibration</italic> (IGC), which exploits the inter-site prediction inconsistencies to accommodate the model learning concentration. By encouraging a model to penalize pixels with larger inconsistencies, we better tailor prediction-level patterns to each local site. Experimentally, we compare FedDP with the state-of-the-art PFL methods on two popular medical image segmentation tasks with different modalities, where our results consistently outperform others on both tasks. Our code and models will be available at https://github.com/jcwang123/PFL-Seg-Trans.
| Type: | Article |
|---|---|
| Title: | FedDP: Dual Personalization in Federated Medical Image Segmentation |
| Location: | United States |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1109/TMI.2023.3299206 |
| Publisher version: | https://doi.org/10.1109/TMI.2023.3299206 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. - This work is supported by the Ministry of Science and Technology of the People’s Republic of China under grant No. 2021ZD0201900 and 2021ZD0201904, and supported by WEISS [203145/Z/16/Z]; and Horizon 2020 FET (863146). For the purpose of open access, the author has applied a CC BY public copyright licence to any author accepted manuscript version arising from this submission. |
| Keywords: | Personalized federated learning, Medical image segmentation, Self-attention mechanism |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10175394 |
Archive Staff Only
 |
View Item |
