Graph Machine Learning with Neo4j

Supervisor

Suitable for

Abstract

Co-supervisor Neo4J (industrial partner)

We have discussed a set of projects concerning data science on graphs with Brian Shi (an Oxford alumni) of the Neo4j data science team, including (but not limited to): -- understanding and evaluating different initialization regimes in node embeddings, -- explainability and interpretability for graph ML, design of online grap ML algorithms/models where nodes and edges are addfed/modified in near real-timel A student would be working with Michael Benedikt and the Neo4j team: the project will be research-focused and any software produced would be in the public domain.  The balance of experiment and theory could be tuned to the student's interests. The main prerequisite would be a very good knowledge of graph ML, at the level of Oxford's GRL course.