Trustworthy Multi-source Learning (2025 entry onward)
Primary supervisor
Additional supervisors
- Samuel Kaski
Additional information
Contact admissions office
Other projects with the same supervisor
- Ontology Informed Machine Learning for Computer Vision
- Controlled Synthesis of Virtual Patient Populations with Multimodal Representation Learning
- Representation Learning and Its Applications
- Machine Learning for Vision and Language Understanding
- Learning of user models in human-in-the-loop machine learning (2025 entry onward)
- Probabilistic modelling and Bayesian machine learning (2025 entry onward)
- Collaborative Probabilistic Machine Learning (2025 entry onward)
- Automatic Experimental Design with Human in the Loop (2025 entry onward)
Funding
- Competition Funded Project (Students Worldwide)
This research project is one of a number of projects at this institution. It is in competition for funding with one or more of these projects. Usually the project which receives the best applicant will be awarded the funding. Applications for this project are welcome from suitably qualified candidates worldwide. Funding may only be available to a limited set of nationalities and you should read the full department and project details for further information.
Project description
Morden machine learning tasks such as multi-modal learning, multi-view learning, domain adaptation/transfer learning, zero/few-shot learning, human-in-the-loop modelling, etc. share similar modelling strategies and frameworks. They could be unified as a process of learning from multiple information sources aiming at predictions based on input obtained from different but relevant data sources. On the other hand, there are high noise, missing entries, heterogeneousness, and misalignment (or called gap, shift) between the learned representations/distributions across data sources etc. in these learning tasks. Therefore, how to systematically integrate these uncertainties and heterogeneity while discovering their similarities across tasks become crucial in feature learning.
This project aims at (1) developing a unified theory and algorithms for trustworthy learning from multi-source data, to address common modelling and data challenges raised in the aforementioned learning tasks, and (2) further applying the developed techniques to real-world applications. The aimed theories and frameworks for algorithm development will optimise data usage in hidden representation spaces and improve learning efficiency.
Person specification
For information
- Candidates must hold a minimum of an upper Second Class UK Honours degree or international equivalent in a relevant science or engineering discipline.
- Candidates must meet the School's minimum English Language requirement.
- Candidates will be expected to comply with the University's policies and practices of equality, diversity and inclusion.
Essential
Applicants will be required to evidence the following skills and qualifications.
- This project requires mathematical engagement and ability substantially greater than for a typical Computer Science PhD. Give evidence for appropriate competence, as relevant to the project description.
- You must be capable of performing at a very high level.
- You must have a self-driven interest in uncovering and solving unknown problems and be able to work hard and creatively without constant supervision.
Desirable
Applicants will be required to evidence the following skills and qualifications.
- You will have good time management.
- You will possess determination (which is often more important than qualifications) although you'll need a good amount of both.
General
Applicants will be required to address the following.
- Comment on your transcript/predicted degree marks, outlining both strong and weak points.
- Discuss your final year Undergraduate project work - and if appropriate your MSc project work.
- How well does your previous study prepare you for undertaking Postgraduate Research?
- Why do you believe you are suitable for doing Postgraduate Research?