About me...

I am a post doc in Machine Learning at the AI Centre, ETH Zurich. I completed my PhD in 2022 at the University of Edinburgh as a member of the Centre for Doctoral Training in Data Science, supervised by Profs Tim Hospedales and Iain Murray. My PhD focused on developing a theoretical understanding of how words are represented: as word embeddings learned from huge text corpora (e.g. by word2vec or GloVe); or as entity embeddings learned from the facts of a knowledge graph. During my PhD I spent 6 months on internship at Samsung AI Centre, Cambridge looking into the interestection of representation learning and logical reasoning.

PhD thesis: “Towards a Theoretical Understanding of Word and Relation Representation

Main Research Interest: developing a theoretical/mathematical understanding of how successful machine learning methods work. The goal being to: (i) deepen our general understanding of the underlying latent structure of the data – i.e. of language, images, speech, DNA, etc – and of the often implicit mechanisms by which it can be learned; and from that (ii) develop improved, interpretable and controllable machine leraning algorithms. Where my PhD focused on representing discrete objects (word embeddings, knowledge graph representation methods and network/graph embeddings), my current work abstracts this to consider more general latent variable/representation models.

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.


Interpreting Knowledge Graph Relation Representation from Word Embeddings [arXiv]
C Allen*, I Balažević*, T Hospedales; ICLR, 2021

Multi-scale Attributed Embedding of Networks [arXiv] [github]
B Rozemberczki, C Allen, R Sarkar; Journal of Complex Networks , 2021

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

Multi-relational Poincaré Graph Embeddings [arXiv] [github]
I Balažević, C Allen, T Hospedales; NeurIPS, 2019

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

TuckER: Tensor Factorization for Knowledge Graph Completion [arXiv] [github]
I Balažević, C Allen, T Hospedales; EMNLP, 2019 (oral)

Hypernetwork Knowledge Graph Embeddings [arXiv] [github]
I Balažević, C Allen, T Hospedales; ICANN, 2019 (oral)


subscribe via RSS