Federated Learning Scholarship Position : Advancements in data-driven machine learning (ML) techniques have presented significant potential in healthcare. However, challenges in training and deploying ML models persist due to data heterogeneity and privacy concerns. Federated learning (FL) emerges as a solution, allowing decentralized model training while maintaining data privacy. This scholarship focuses on developing generalizable models in a distributed FL framework, addressing challenges in performance, generalization, class imbalance, and biases in medical data.
Summary Table:
| Area | Details |
|---|---|
| Title | Federated Learning Scholarship |
| Duration | 3 Years |
| Application Deadline | 1st February 2024 |
Study Area: Medical Data Research
Scholarship Description: The scholarship aims to explore novel approaches to boost model performance, improve generalizability, tackle class imbalance, and address biases in medical data within a distributed federated learning framework. The candidate will work with multimodal datasets, including PolypGen and VPH-DARE@IT, to enhance FL performance and develop techniques for local performance improvement.
Eligibility: Applicants must have outstanding academic merit, a first-class or upper second-class Honours Degree (or international equivalent), or an MSc/MRes with distinction. Background in Computer Science, Engineering, Physics, or Mathematics is preferred. Strong knowledge and experience in imaging, medical imaging, computer vision, and machine learning/deep learning are advantageous.
Country eligibility- International (open to all nationalities, including the UK)
Required Documents:
- CV
- Academic Transcripts
- Degree Certificates
- Research Proposal (if applicable)
- Reference Letters (if applicable)
How to Apply: Interested candidates should submit their application online, including the required documents, by clicking on the Apply button on the scholarship portal.
- Application Process: Formal applications for research degree study should be made online through the University’s website, specifying the EPSRC DTP Engineering & Physical Sciences program and the research degree in Federated Learning for Healthcare with Dr. Sharib Ali as the proposed supervisor.
- Requirements:Â Applicants need a first or upper second-class honors degree, or an MSc/MRes with distinction. Proficiency in programming and relevant skills is encouraged.
- For further information about this project, please contact Dr Sharib Ali by email to S.S.Ali@leeds.ac.uk
- For further information about your application, please contact Doctoral College Admissions by email to phd@engineering.leeds.ac.uk
Last Date for Apply: 19 February 2024
Note: The scholarship offers a unique opportunity to work on curated multimodal datasets and advance research in federated learning for medical data. Programming skills in Python, C/C++, and familiarity with deep learning libraries are desirable. For more information, contact [Dr. Ali] at [contact email/phone number].
