Carl Allen


I am in my third (final) year of a PhD in Machine Learning at the University of Edinburgh, supervised by Tim Hospedales and Iain Murray. I am a member of the Centre for Doctoral Training in Data Science. My main interest is in theoretically understanding how machine learning methods work, with a current focus on the representation of discrete objects, eg. word embeddings, knowledge graph representation methods and network/graph embeddings more generally.

Background

I moved into Artificial Intelligence/Machine Learning research after some time working in Project Finance. I hold a BSc in Mathematics and Chemistry from the University of Southampton, an MSc Mathematics and the Foundations of Computer Science (MFoCS) from the University of Oxford and MScs in Artificial Intelligence and Data Science from the University of Edinburgh.

Publications

On Understanding Knowledge Graph Representation [arXiv]
C Allen*, I Balažević*, T Hospedales

Multi-scale Attributed Embedding of Networks [arXiv] [github]
B Rozemberczki, C Allen, R Sarkar

What the Vec? Towards Probabilistically Grounded Embeddings [arXiv]
C Allen, I Balažević, T Hospedales; Neural Information Processing Systems, 2019

Multi-relational Poincaré Graph Embeddings [arXiv] [github]
I Balažević, C Allen, T Hospedales; Neural Information Processing Systems, 2019

Analogies Explained: Towards Understanding Word Embeddings [arXiv] [blog post] [slides]
C Allen, T Hospedales; International Conference on Machine Learning, 2019 (honorable mention)

TuckER: Tensor Factorization for Knowledge Graph Completion [arXiv] [github]
I Balažević, C Allen, T Hospedales; Empirical Methods in Natural Language Processing, 2019 (oral)

Hypernetwork Knowledge Graph Embeddings [arXiv] [github]
I Balažević, C Allen, T Hospedales; International Conference on Artificial Neural Networks, 2019 (oral)

carl.allen@ed.ac.uk  |  Blog  |  Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB