The goal of his PhD project is to develop a way to best provide personalised models in the common setting where nodes aim to jointly solve a common problem.
- Qualification Type: PhD
- Closes: 11th March 2022.
Overview
The School of Science & Technology at City, University of London is offering a three-year doctoral studentship for 2021/22 entry.
The scholarship is one of two co-funded by Equideum Health, a company working at the interface between blockchain, machine learning and privacy enhancing technologies to develop new healthcare solutions.
The successful candidate will be supported by the Department of Computer Science and its academic staff (with extensive expertise in machine learning in healthcare) as well as deal with real-world challenges relative to industrial deployment.
Applications are invited from exceptional UK, European and International graduates wishing to pursue cutting-edge research in AI and healthcare, one of the School's key research areas.
The School is investing in academic excellence following its success in the last REF, which highlighted the world class quality of its research.
Project outline
Federated machine learning is a technique to incrementally train a model using different datasets, owned by different entities. This is the technique used by Apple/Google on our smartphones to improve their models' accuracy and "improve your user experience".
We envision Federated Learning will dramatically change the way we collaborate in healthcare settings. In particular, the ability for multiple entities to share their knowledge within a federated learning network could open collaboration opportunities between more and more institutions across the world.
The challenge lies in the discrepancy between datasets at each node in the network (each entity). If different nodes have different data distributions, the learned global model will provide sub-optimal local accuracy.
The goal of his PhD project is to develop a way to best provide personalised models in the common setting where nodes aim to jointly solve a common problem.
In another form of collaborative learning, each entity within the network might want to benefit from the backbone features learnt by the network but apply this knowledge to its custom task, in a Federated Multi-Task Learning fashion.
The project will involve publicly available medical datasets (e.g., UK Biobank), mostly consisting (but not limited to) medical scans acquired at different institutions.
Common tasks such as classification, segmentation and object detection will be used as test scenario for the solutions developed.
Funding
A doctoral studentship will provide:
- An annual bursary (£16,000) with a substantial top-up salary offered by the company to outstanding candidates, for a total amount aligned to typical RA salaries in the UK.
- Full tuition fee for Home students. Applications from international applicants are welcome but the applicant must make appropriate arrangements to cover the difference between the international and home tuition fee.
- A budget for travel expenses and consumables (£4,000 in total).
Eligibility
The studentships will be awarded on the basis of outstanding academic achievement and the potential to produce cutting edge-research. Prospective applicants must:
- Hold a good honours degree (normally no less than a second class honours degree or an equivalent qualification) in an appropriate subject. Exceptionally, if the first degree is in a different subject area, we can consider applications from those with a good Master’s Degree in a relevant subject or extensive professional experience in the area of their proposed research;
- Be able to demonstrate proficiency in the use of oral and written English;
- Applicants whose mother tongue is not English must meet any one or a combination of the following:
- A minimum IELTS average score of 6.5; with a minimum of 6.0 in each of the four components
- The award of a Masters’ degree, the teaching of which was in English from an English Speaking country.
How to Apply
Initial informal enquiries should be addressed to Dr Giacomo Tarroni.
Visit our Computer science research degrees web page for further information on making a formal application. When submitting your proposal, enter the title “Multi-task Federated Learning for Medical Imaging” and you will automatically be considered for this studentship.
The online application can be found in the ‘How to apply section’ in the web link above and should include the following supporting documents:
- Copies of Degree Certificates and Transcripts in official English translation - original will be requested before an offer is made.
- Official work e-mail addresses (not private ones) for two referees (one of which must be an academic).
- Proof of English Language proficiency (minimum average score of 6.5 IELTS, with a minimum of 6.0 in each of the four components) if English is not your first language.
- Passport.
For queries regarding the application process, please email the School.
Equality, diversity and inclusion
City, University of London is committed to promoting equality, diversity and inclusion in all its activities, processes, and culture, for our whole community, including staff, students and visitors.
We welcome applications regardless of gender, sexual orientation, disability, marital status, race, nationality, ethnic origin, religion or social class. For more information on our approaches to encouraging an inclusive environment, please see our Equality, Diversity and Inclusion pages.