Graph Neural Networks for Knowledge Graphs
Supervisors
Suitable for
Abstract
Description: Graph Neural Networks (GNNs) are a class of neural network architectures that has recently become popular for
a wide range of applications dealing with graph-structured data. GNNs can be seen as a generalisation of both Convolutional
Neural Networks and Recurrent Neural Networks. This project will explore GNN-based techniques for solving various tasks relevant
to Knowledge Graphs (datastores where factual information is stored as a graph with nodes representing objects and edges representing
relationships between such objects). Examples of relevant tasks include (a.k.a. link prediction) and entity resolution (determining
whether two nodes in the graph represent the same entity).