My research focuses on the foundations and applications of graph methods in machine learning and data science. I aim to find elegant explanations for phenomena associated with learning and to exploit them in order to design principled solutions. I am also interested in the analysis of neural networks and in using deep learning techniques to solve bio-engineering problems (especially protein design).
Selected recent works
N. Karalias, A. Loukas. Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs. Oral at NeurIPS 2020. (preprint, bibtex, blogpost)
A. Loukas. How hard is to distinguish graphs with graph neural networks. NeurIPS 2020. (preprint, bibtex, blogpost)
C. Vignac, A. Loukas, P. Frossard. Building powerful and equivariant graph neural networks with structural message-passing. NeurIPS 2020 (preprint, bibtex)