Skip to main content

Graph Neural Networks for Knowledge Graphs


Egor V. Kostylev

Suitable for

MSc in Computer Science
Mathematics and Computer Science, Part C
Computer Science and Philosophy, Part C
Computer Science, Part C


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).