Multimodal Federated Learning in Healthcare

About the Project

These projects are open to students worldwide, but have no funding attached. Therefore, the successful applicant will be expected to fund tuition fees at the relevant level (home or international) and any applicable additional research costs. Please consider this before applying.

Multimodal AI has demonstrated remarkable success by integrating diverse data sources to achieve more comprehensive and accurate analysis than unimodal approaches. However, its translation to healthcare remains constrained by limited public datasets and strict privacy regulations surrounding patient data. Federated learning (FL) offers a promising solution by enabling collaborative model training across hospitals and medical centers without sharing sensitive data, thereby ensuring both privacy and security.

Our lab has pioneered several key advances in this field — including the development of feature imputation networks [2] for handling missing modalities, cross-modal data augmentation by retrieval [1] using small-scale public datasets, and federated foundation models [3] that enable scalable, privacy-preserving multimodal learning across distributed institutions.

Building on these foundations, this PhD project will explore the next frontier of multimodal federated learning [4] — extending beyond conventional text and imaging modalities to incorporate additional data types such as electronic health records (EHRs), genomic data, sensor data, and physiological signals. This research will address critical challenges in aligning, integrating, and learning from highly heterogeneous modalities in a distributed and privacy-sensitive environment.

The project will aim to:

• Develop robust frameworks for cross-modal alignment and representation learning across diverse healthcare modalities.
• Investigate privacy-preserving federated strategies to ensure secure, fair, and generalizable learning across multiple institutions.
• Evaluate the resulting models on real-world clinical datasets and benchmark them against existing multimodal and unimodal baselines.

The successful candidate will collaborate closely with a Professor of Health Data Science at the Institute of Medical Sciences (IMS)—one of the UK’s leading institutions in medical research. This partnership will offer opportunities to gain clinical domain insights, co-design practical solutions tailored to healthcare needs, and validate the developed methods on real-world data through the Aberdeen Data Safe Haven, a secure and trusted research environment hosting sensitive health data.

Furthermore, there will be opportunities to collaborate with international faculty members from partner institutions in the USA, with the potential for short-term research visits to strengthen global collaboration and exposure.

This interdisciplinary project will advance the development of trustworthy, data-efficient, and generalizable multimodal AI systems for healthcare, setting the stage for the next generation of federated learning research across diverse biomedical data modalities.

Informal enquiries can be made by contacting Dr B Bhattarai (binod.bhattarai@abdn.ac.uk).

Decisions will be based on academic merit. The successful applicant should have, or expect to obtain, a UK Honours Degree at 2.1 (or equivalent) in Computer Science, Artificial Intelligence, Data Science, or a related discipline.

Essential skills and background:

• Strong foundation in linear algebra, probability, and statistics
• Proficiency in programming with Python and experience with deep learning frameworks such as PyTorch or TensorFlow
• Familiarity with machine learning and deep neural networks

Desirable (but not essential):

• Background in medical imaging, healthcare data, or biomedical signal analysis
• Experience with federated learning, multimodal learning, or trustworthy AI

We encourage applications from all backgrounds and communities, and are committed to having a diverse, inclusive team.

Application Procedure:

Formal applications can be completed online: https://www.abdn.ac.uk/pgap/login.php.

You should apply for Degree of Doctor of Philosophy in Computing Science to ensure your application is passed to the correct team for processing.

Please clearly note the name of the lead supervisor and project titleon the application form. If you do not include these details, it may not be considered for the project.

Your application must include: A personal statement, an up-to-date copy of your academic CV, and clear copies of your educational certificates and transcripts.

Please note: you do not need to provide a research proposal with this application.

If you require any additional assistance in submitting your application or have any queries about the application process, please don't hesitate to contact us at researchadmissions@abdn.ac.uk

Funding Notes

This is a self-funding project open to students worldwide. Our typical start dates for this programme are February or October.

Fees for this programme can be found here Finance and Funding | Study Here | The University of Aberdeen.