Bio. I hold a D.Phil in Computer Science from the University of Oxford, supervised by Dr. İsmail İlkan Ceylan and Prof. Thomas Lukasiewicz. My main research area is graph representation learning (GRL). More specifically, I am interested in identifying the strengths and limitations of GRL models, namely shallow embedding models and graph neural networks (GNNs), and proposing machine learning approaches with improved inductive capacity, interpretability, and representation power over relational data.
Current Work. I am working on large language models (LLMs) and natural language processing with the Learning Agency Lab and supporting the Learning Engineering program at Schmidt Futures. I am also a visiting scientist at the Francis Crick Institute.
Contact. Please get in touch at ralph {at} ralphabb.ai. You can also find my old departmental webpage here.