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 specialized learning machines.
I am also interested in graph problems in signal processing and theoretical computer science, as well as in the analysis of neural networks.
Selected recent papers
N. Karalias, A. Loukas. Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs. Oral at NeurIPS 2020. (preprint)
A. Loukas. How hard is to distinguish graphs with graph neural networks. NeurIPS 2020. (preprint)
C. Vignac, A. Loukas, P. Frossard. Building powerful and equivariant graph neural networks with structural message-passing. NeurIPS 2020 (preprint)
List of publications