AISTATS 2024poster9 citations

Federated Learning For Heterogeneous Electronic Health Records Utilising Augmented Temporal Graph Attention Networks

Soheila Molaei, Anshul Thakur, Ghazaleh Niknam, Andrew Soltan, Hadi Zare, David A Clifton

Abstract

The proliferation of decentralised electronic healthcare records (EHRs) across medical institutions requires innovative federated learning strategies for collaborative data analysis and global model training, prioritising data privacy. A prevalent issue during decentralised model training is the data-view discrepancies across medical institutions that arises from differences or availability of healthcare services, such as blood test panels. The prevailing way to handle this issue is to select a common subset of features across institutions to make data-views consistent. This approach, however, constrains some institutions to shed some critical features that may play a significant role in improving the model performance. This paper introduces a federated learning framework that relies on augmented graph attention networks to address data-view heterogeneity. The proposed framework utilises an alignment augmentation layer over self-attention mechanisms to weigh the importance of neighbouring nodes when updating a node’s embedding irrespective of the data-views. Furthermore, our framework adeptly addresses both the temporal nuances and structural intricacies of EHR datasets. This dual capability not only offers deeper insights but also effectively encapsulates EHR graphs’ time-evolving nature. Using diverse real-world datasets, we show that the proposed framework significantly outperforms conventional FL methodology for dealing with heterogeneous data-views.

BibTeX
@InProceedings{pmlr-v238-molaei24a,
  title = 	 {Federated Learning For Heterogeneous Electronic Health Records Utilising Augmented Temporal Graph Attention Networks},
  author =       {Molaei, Soheila and Thakur, Anshul and Niknam, Ghazaleh and Soltan, Andrew and Zare, Hadi and A Clifton, David},
  booktitle = 	 {Proceedings of The 27th International Conference on Artificial Intelligence and Statistics},
  pages = 	 {1342--1350},
  year = 	 {2024},
  editor = 	 {Dasgupta, Sanjoy and Mandt, Stephan and Li, Yingzhen},
  volume = 	 {238},
  series = 	 {Proceedings of Machine Learning Research},
  month = 	 {02--04 May},
  publisher =    {PMLR},
  pdf = 	 {https://proceedings.mlr.press/v238/molaei24a/molaei24a.pdf},
  url = 	 {https://proceedings.mlr.press/v238/molaei24a.html},
  abstract = 	 {The proliferation of decentralised electronic healthcare records (EHRs) across medical institutions requires innovative federated learning strategies for collaborative data analysis and global model training, prioritising data privacy. A prevalent issue during decentralised model training is the data-view discrepancies across medical institutions that arises from differences or availability of healthcare services, such as blood test panels. The prevailing way to handle this issue is to select a common subset of features across institutions to make data-views consistent. This approach, however, constrains some institutions to shed some critical features that may play a significant role in improving the model performance. This paper introduces a federated learning framework that relies on augmented graph attention networks to address data-view heterogeneity. The proposed framework utilises an alignment augmentation layer over self-attention mechanisms to weigh the importance of neighbouring nodes when updating a node’s embedding irrespective of the data-views. Furthermore, our framework adeptly addresses both the temporal nuances and structural intricacies of EHR datasets. This dual capability not only offers deeper insights but also effectively encapsulates EHR graphs’ time-evolving nature. Using diverse real-world datasets, we show that the proposed framework significantly outperforms conventional FL methodology for dealing with heterogeneous data-views.}
}