Ian Gallagher

Ian Gallagher

Heilbronn Research Fellow

University of Bristol


I am a Data Science Research Fellow at the Heilbronn Institute for Mathematical Research. I completed my PhD at the School of Mathematics, University of Bristol supervised by Prof. Patrick Rubin-Delanchy.

My research interests include using graph embeddings to find interesting structure in real-world networks.

  • Graph embedding for clustering, anomaly detection and link prediction
  • Applications in cyber-security, social science and biology
  • PhD in Statistics, 2022

    University of Bristol

  • Certificate in Advanced Study of Mathematics (Part III), Distinction, 2005

    University of Cambridge, Trinity College

  • BA Hons. Mathematics, First, 2004

    University of Cambridge, Trinity College


(2023). A simple and powerful framework for stable dynamic network embedding. arXiv preprint.


(2023). Spectral embedding of weighted graphs. Accepted for Journal of the American Statistical Association.


(2022). Spectral embedding and the latent geometry of multipartite networks. arXiv preprint.


(2019). Persistent homology of graph embeddings.


Recent & Upcoming Talks

Neural Information Processing Systems (NeurIPS 2023), New Orleans, USA, December 2023. Intensity profile projection: a framework for continuous-time representation learning for dynamic networks.

NUMBATs Seminar, Monash University, Australia, September 2023. Adjacency spectral embedding beyond unweighted, undirected networks.

Mathematical and Statistical Aspects of Security and Cybersecurity, Bristol, UK, May 2023. Spectral graph embedding for computer networks.

International Conference on Computational Statistics (COMPSTAT 2022), Bologna, Italy, August 2022. Spectral embedding of weighted graphs.

Neural Information Processing Systems (NeurIPS 2021), Virtual, December 2021. Spectral embedding for dynamic networks with stability guarantees.


I have written a Python package for graph spectral embedding available at the GitHub repository, Spectral-Embedding.

The package includes a variety of tools for spectral embedding of graphs, using the theory of the generalised random dot product graph and its many extensions to analyse networks.


Statistical Machine Learning, University of Bristol, 2022/23.