EUVIMEDEUVIMED entdecken
Crossref

Neuro-Symbolic Federated Learning over Heterogeneous Data-Views: A Structured Approach to Distributive EHR Modelling

Soheila Molaei, Bahareh Fatemi, Anshul Thakur, Andrew Soltan, Fazle Rabbi, Andreas L. Opdahl, Kim Branson, Patrick Schwab, Danielle Belgrave, David A. Clifton

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (29) · 24422-24430

DOI: 10.1609/aaai.v40i29.39624 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Soheila Molaei und 9 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Federated learning (FL) enables privacy-preserving model training across distributed Electronic Health Records (EHRs), but its deployment remains limited by data-view heterogeneity, where institutions maintain incompatible local schemas. Most existing methods address this by enforcing flat, aligned data views, which require extensive cross-site preprocessing and manual harmonisation that often discards client-specific features, or by projecting inputs into a shared latent space, which sacrifices interpretability. We propose a modelling shift from conventional FL with vectorised inputs to a symbolic, relation-centric framework, where each client organises its EHR data as a structured, type-aware relational graph. This enables client-specific inference without requiring schema alignment and supports FL across heterogeneous data views. To model over these symbolic structures, we introduce an architecture that combines relation-aware message passing with a learnable feature relevance mechanism, jointly enabling accurate local predictions and client-specific interpretability while supporting parameter sharing across clients. Beyond strong performance on three real-world EHR datasets exhibiting data-view heterogeneity, we further show that our framework supports multimodal FL under modality-level heterogeneity. Using MC-MED, a publicly available multimodal emergency department dataset, we demonstrate that our method accommodates clients with partially missing modalities, highlighting its robustness and scalability in real-world clinical settings.

Zitieren

APA

Molaei, S., Fatemi, B., Thakur, A., Soltan, A., Rabbi, F., Opdahl, A. L., Branson, K., Schwab, P., Belgrave, D., & Clifton, D. A. (2026). Neuro-Symbolic Federated Learning over Heterogeneous Data-Views: A Structured Approach to Distributive EHR Modelling. Proceedings of the AAAI Conference on Artificial Intelligence, 40(29), 24422-24430. https://doi.org/10.1609/aaai.v40i29.39624

Vancouver

Molaei S, Fatemi B, Thakur A, Soltan A, Rabbi F, Opdahl AL, et al. Neuro-Symbolic Federated Learning over Heterogeneous Data-Views: A Structured Approach to Distributive EHR Modelling. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(29):24422-24430. doi:10.1609/aaai.v40i29.39624

BibTeX
@article{Molaei2026,
  author = {Molaei, Soheila and Fatemi, Bahareh and Thakur, Anshul and Soltan, Andrew and Rabbi, Fazle and Opdahl, Andreas L. and Branson, Kim and Schwab, Patrick and Belgrave, Danielle and Clifton, David A.},
  title = {Neuro-Symbolic Federated Learning over Heterogeneous Data-Views: A Structured Approach to Distributive EHR Modelling},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {29},
  pages = {24422--24430},
  doi = {10.1609/aaai.v40i29.39624}
}
Kostenlos starten →