MULTIPLi - MULTIcentric and Privacy-preserving Learning in Healthcare

The increasing availability of heterogeneous healthcare data across institutions creates unprecedented opportunities for data-driven medicine, while simultaneously raising critical challenges related to privacy, governance, and data sharing. As a result, many high-value healthcare datasets remain isolated across institutions, limiting the development, validation, and generalizability of Artificial Intelligence (AI) models for clinical and biomedical applications, despite multicentric studies being widely regarded as the gold standard for robust and generalizable medical evidence. Multicentric and privacy-preserving learning paradigms, such as Federated and Distributed Learning, offer a promising path forward by enabling collaborative model training and analysis without requiring the exchange of raw and possibly sensitive patient data.

The MULTIPLi Health workshop addresses the methodological, technical, and practical challenges associated with building trustworthy AI systems under these constraints. It focuses on learning from multicentric and heterogeneous healthcare data while ensuring compliance with privacy regulations. The workshop aims to examine recent advances as well as unresolved issues related to scalability, robustness, evaluation, and deployment in real-world clinical environments.

By aligning with AIME’s focus on medical decision support and clinically meaningful evaluation, MULTIPLi Health provides a forum for advancing privacy-aware AI methodologies that are essential for the next generation of collaborative healthcare research.

Workshop schedule (Conference room TODO)

Opening remarks [##:##-##:##]

Name Surname (Uni)

Keynote [##:##-##:##]

Name Surname (Uni), Title

Coffee break [##:##-##:##]

Technical presentations [##:##-##:##] 

• Name Surname. Title

• Name Surname. Title

• Name Surname. Title

• ...

Spotlight presentations [##:##-##:##] 

• • Name Surname. Title

  • Name Surname. Title

  • Name Surname. Title

Lunch [##:##-##:##] 

Keynote [##:##-##:##] 

Name Surname (Uni), Title

Technical presentations [##:##-##:##] 

• Name Surname. Title

• Name Surname. Title

• Name Surname. Title

• ...

Closing Remarks [##:##-##:##] 

Coffee break [##:##-##:##] 

Poster session [##:##-##:##] 

Topics and themes

Topics of interest include, but are not limited to:

• Federated learning methods and architectures for healthcare applications

• Federated analytics and distributed statistical analysis across hospitals and cohorts

• Distributed and collaborative learning under data heterogeneity and imbalance

• Privacy-preserving machine learning (e.g., differential privacy, secure aggregation, secure multi-party computation)

• Learning from multicentric, multi-modal, and longitudinal healthcare datasets 

• Evaluation, benchmarking, and reproducibility in federated and multicentric settings

• System infrastructures, platforms, and frameworks for distributed healthcare AI

• Clinical use cases and real-world deployments of federated and privacy-preserving learning

• Trust, robustness, and fairness in privacy-aware collaborative models

• Explainable AI in federated and distributed learning

Call for papers

Important Dates

• Submission Due Date: Day, Month xth, 2026, AoE

• Notification of Acceptance: Day, Month xth, 2026, AoE

• Early Registration Rate Ends: Day, Month xth, 2026

• Camera-ready Papers Due: Day, Month xth, 2026

• Workshop Date: Friday, July 10th, 2026, Ottawa, Canada

Submission Instructions

We invite submissions of original research on the previously mentioned aspects of TODO (see the complete list of topics above). Submissions should be best-effort anonymized and follow the AIME'26 template. The review process will be double-blind. We accept both short papers (4 pages + references + optional appendix) and long papers (8 pages + references + optional appendix). Submissions exceeding the long papers format will be desk-rejected.

Submissions are processed in TODO: LINK

...

Presentation Instructions

All accepted papers are expected to be presented in person. The workshop will not provide support for virtual talks.

Accepted papers will be presented either as talks or posters. There is no difference in scientific quality between talks and posters. The reviewing and selection processes are identical. The selection of papers will differentiate between oral and poster presentations according to the topics, and not to the level of quality.

Oral presentations: we allocated 15' for each paper presentation (12' + 3' of Q&A)

Poster presentations: we allocated 1'/2' for a spotlight oral presentation (just a couple of slides to raise your work's visibility). Poster guidelines can be found here: https://aaai.org/conference/aaai/aaai-26/poster-guidelines/