Supervisors: Prof. Jesus Cerquides, Associate Prof. Jeffrey Chan and Dr. Azadeh Alavi.
Project 1: Graph Neural Networks for language
The overall aim of the research is to analyze the potential contributions of the network structure in the construction of language models. The project will investigate AI techniques to take advantage of the links between documents (for example reference between scientific articles, responses or citations between tweets) as an opportunity to build better text representations.
Project 2: Graph Neural Networks for material sciences
The overall aim of the research is to contribute to current research in applications of Graph Neural Networks in material sciences research. GNNs are expected to enable an accurate and interpretable prediction of the properties of materials. The idea of the work is to expand the research ideas in [Dai2021].
Dai, M., Demirel, M.F., Liang, Y. et al. Graph neural networks for an accurate and interpretable prediction of the properties of polycrystalline materials. npj Comput Mater 7, 103 (2021). https://doi.org/10.1038/s41524-021-00574-w
Project 3: Graph Neural Networks for biomedical image segmentation
The overall aim of the research is to contribute to biomedical image segmentation tasks through the use of Graph Neural Networks. The idea of the work is to apply the research ideas developed in [Alon2022] for another biomedical image segmentation tasks. Specifical examples will be oocytes and embryos from mammals.
Alon, Yoav & Zhou, Huiyu. (2022). Neuroplastic graph attention networks for nuclei segmentation in histopathology images.
