DDGD, discrete graph diffusion is a diffusion model that is able to generate graphs and uses a discrete categorical distribution instead of a gaussian to add noise to the graph. While this project was ...

The Temporal Discrete Graph Updater (TDGU) is a text-to-graph model that incrementally constructs temporal dynamic knowledge graphs from interactive text-based games. This project uses PyTorch ...

Abstract: While state-of-the-art kernels for graphs with discrete labels scale well to graphs with thousands of nodes, the few existing kernels for graphs with continuous attributes, unfortunately, do ...

Abstract: Deep learning models have shown great potential for fault location and classification tasks in distribution systems. Emerging multi-scale data sources such as waveform measurement units, ...

Graph curvature and Laplacian operators form a vibrant area of research at the intersection of differential geometry and graph theory. The concept of graph curvature, inspired by classical Ricci ...

This course is available on the MSc in Applicable Mathematics. This course is available as an outside option to students on other programmes where regulations permit. Students should be taking the ...