Link Prediction on Knowledge Graphs with Graph Neural Networks

Knowledge graphs store facts using relations between pairs of entities. In this work, we address the question of link prediction in knowledge graphs. Our general approach broadly follows neighborhood aggregation schemes such as that of Graph Convolutional Networks (GCN), which in turn was motivated by spectral graph convolutions. Our proposed model will aggregate information from neighbour entities and relations. Contrary to most existing knowledge graph completion methods, our model is expected to work in the inductive setting: Predicting relations for entities not seen during training.

Faculty Supervisor:

David Poole

Student:

Bahare Fatemi

Partner:

Element AI

Discipline:

Computer science

Sector:

Professional, scientific and technical services

University:

Program:

Accelerate

Current openings

Find the perfect opportunity to put your academic skills and knowledge into practice!

Government

International

Load More

International

Load More