From Isolation to Collaboration: Federated Class-Heterogeneous Learning for Chest X-Ray Classification

Pranav Kulkarni, Adway Kanhere, Paul H. Yi, Vishwa S. Parekh
Proceedings of the 4th Machine Learning for Health Symposium, PMLR 259:623-635, 2025.

Abstract

Federated learning (FL) is a promising paradigm to collaboratively train a global chest x-ray (CXR) classification model using distributed datasets while preserving patient privacy. A significant, yet relatively underexplored, challenge in FL is class-heterogeneity, where clients have different sets of classes. We propose surgical aggregation, a FL method that uses selective aggregation to collaboratively train a global model using distributed, class-heterogeneous datasets. Unlike other methods, our method does not rely on the assumption that clients share the same classes as other clients, know the classes of other clients, or have access to a fully annotated dataset. We evaluate surgical aggregation using class-heterogeneous CXR datasets across IID and non-IID settings. Our results show that our method outperforms current methods and has better generalizability.

Cite this Paper

BibTeX
@InProceedings{pmlr-v259-kulkarni25a, title = {From Isolation to Collaboration: Federated Class-Heterogeneous Learning for Chest X-Ray Classification}, author = {Kulkarni, Pranav and Kanhere, Adway and Yi, Paul H. and Parekh, Vishwa S.}, booktitle = {Proceedings of the 4th Machine Learning for Health Symposium}, pages = {623--635}, year = {2025}, editor = {Hegselmann, Stefan and Zhou, Helen and Healey, Elizabeth and Chang, Trenton and Ellington, Caleb and Mhasawade, Vishwali and Tonekaboni, Sana and Argaw, Peniel and Zhang, Haoran}, volume = {259}, series = {Proceedings of Machine Learning Research}, month = {15--16 Dec}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v259/main/assets/kulkarni25a/kulkarni25a.pdf}, url = {https://proceedings.mlr.press/v259/kulkarni25a.html}, abstract = {Federated learning (FL) is a promising paradigm to collaboratively train a global chest x-ray (CXR) classification model using distributed datasets while preserving patient privacy. A significant, yet relatively underexplored, challenge in FL is class-heterogeneity, where clients have different sets of classes. We propose surgical aggregation, a FL method that uses selective aggregation to collaboratively train a global model using distributed, class-heterogeneous datasets. Unlike other methods, our method does not rely on the assumption that clients share the same classes as other clients, know the classes of other clients, or have access to a fully annotated dataset. We evaluate surgical aggregation using class-heterogeneous CXR datasets across IID and non-IID settings. Our results show that our method outperforms current methods and has better generalizability.} }
Endnote
%0 Conference Paper %T From Isolation to Collaboration: Federated Class-Heterogeneous Learning for Chest X-Ray Classification %A Pranav Kulkarni %A Adway Kanhere %A Paul H. Yi %A Vishwa S. Parekh %B Proceedings of the 4th Machine Learning for Health Symposium %C Proceedings of Machine Learning Research %D 2025 %E Stefan Hegselmann %E Helen Zhou %E Elizabeth Healey %E Trenton Chang %E Caleb Ellington %E Vishwali Mhasawade %E Sana Tonekaboni %E Peniel Argaw %E Haoran Zhang %F pmlr-v259-kulkarni25a %I PMLR %P 623--635 %U https://proceedings.mlr.press/v259/kulkarni25a.html %V 259 %X Federated learning (FL) is a promising paradigm to collaboratively train a global chest x-ray (CXR) classification model using distributed datasets while preserving patient privacy. A significant, yet relatively underexplored, challenge in FL is class-heterogeneity, where clients have different sets of classes. We propose surgical aggregation, a FL method that uses selective aggregation to collaboratively train a global model using distributed, class-heterogeneous datasets. Unlike other methods, our method does not rely on the assumption that clients share the same classes as other clients, know the classes of other clients, or have access to a fully annotated dataset. We evaluate surgical aggregation using class-heterogeneous CXR datasets across IID and non-IID settings. Our results show that our method outperforms current methods and has better generalizability.
APA
Kulkarni, P., Kanhere, A., Yi, P.H. & Parekh, V.S.. (2025). From Isolation to Collaboration: Federated Class-Heterogeneous Learning for Chest X-Ray Classification. Proceedings of the 4th Machine Learning for Health Symposium, in Proceedings of Machine Learning Research 259:623-635 Available from https://proceedings.mlr.press/v259/kulkarni25a.html.

Related Material