We aim to advance multimodal learning within a federated learning framework, where diverse data modalities remain distributed across sites due to privacy constraints
Job Summary
We aim to advance multimodal learning within a federated learning framework, where diverse data modalities remain distributed across sites due to privacy constraints.
Our focus is on developing methods that can effectively learn from multi-modality data in a privacy-preserving and efficient manner.
The project will incorporate a broad spectrum of biomedical data types—including histology, DNA sequencing, bulk/single-cell/spatial RNA sequencing, and clinical EHR data—with plans to expand to epigenetic data such as DNA methylation.
Matching Summary
We aim to advance multimodal learning within a federated learning framework, where diverse data modalities remain distributed across sites due to privacy constraints.
Skills & Requirements
Must-have
multimodal learning
federated learning framework
privacy-preserving methods
biomedical data types
data fusion strategies
Nice-to-have
collaborative scientific discovery
fosters collaborative innovation
safe and welcoming workplace
Key Requirements
Guest Faculty
Visiting Faculty Appointment
Faculty
Foreign Government Sponsored or Affiliated Activities restrictions