Ivana Balažević


I am a 3rd (and final) year PhD student in Machine Learning at the School of Informatics, University of Edinburgh, supervised by Tim Hospedales and Ivan Titov. I am a member of the Centre for Doctoral Training in Data Science. Majority of my PhD research is centered around representation learning for knowledge graphs. More broadly, I am interested in 1) understanding how semantics is encoded in the geometry of representations; and 2) learning to better represent objects in the real world, ranging from words to objects in images.


From November 2019 to June 2020, I interned at the Samsung AI Center in Cambridge.

From June 2020 to February 2021, I was a Research Scientist Intern at Facebook AI Research (FAIR) with Sebastian Riedel.


Background

Before starting my PhD, I received a BSc in Computer Science at the Faculty of Electrical Engineering and Computing, University of Zagreb, an MSc in Computer Science at the Technische Universität Berlin and an MSc in Data Science at the University of Edinburgh.

Publications

Interpreting Knowledge Graph Relation Representation from Word Embeddings
Carl Allen*, Ivana Balažević*, Timothy Hospedales, ICLR, 2021
[paper]

Multi-relational Poincaré Graph Embeddings
Ivana Balažević, Carl Allen, Timothy Hospedales, NeurIPS, 2019
[paper] [code]

What the Vec? Towards Probabilistically Grounded Embeddings
Carl Allen, Ivana Balažević, Timothy Hospedales, NeurIPS, 2019
[paper]

TuckER: Tensor Factorization for Knowledge Graph Completion
Ivana Balažević, Carl Allen, Timothy Hospedales, EMNLP, 2019 (oral)
[paper] [code] [slides][video]

Hypernetwork Knowledge Graph Embeddings
Ivana Balažević, Carl Allen, Timothy Hospedales, ICANN, 2019 (oral)
[paper] [code] [slides]

Preprints

Learning the Prediction Distribution for Semi-Supervised Learning with Normalising Flows
Ivana Balažević*, Carl Allen*, Timothy Hospedales, arXiv:2007.02745, 2020
[paper] [code]

A Probabilistic Framework for Discriminative and Neuro-Symbolic Semi-Supervised Learning
Carl Allen, Ivana Balažević, Timothy Hospedales, arXiv:2006.05896, 2020
[paper]

Workshops

Benchmark and Best Practices for Biomedical Knowledge Graph Embeddings
David Chang, Ivana Balažević, Carl Allen, Daniel Chawla, Cynthia Brandt, Andrew Taylor
ACL BioNLP Workshop
, 2020
[paper]

TuckER: Tensor Factorization for Knowledge Graph Completion
Ivana Balažević, Carl Allen, Timothy Hospedales, ICML AMTL Workshop, 2019
[paper]

ibalazevic
ibalazevic

Contact

Email: ivana.balazevic@ed.ac.uk
Office: Room 3.50, Informatics Forum, 10 Crichton Street, Edinburgh, EH8 9AB