andreas loukas

I am a computer science researcher and graph enthusiast.

My work focuses on the foundations and applications of machine learning to structured problems. I aim to find ways to exploit (graph, constraint, group) information, with the ultimate goal of designing algorithms that can learn from fewer data. I am also fascinated by the theoretical analysis of neural networks and in using them to solve hard combinatorial and bio-engineering problems (especially protein design).

Selected recent works

A Loukas, M. Poiitis, S. Jegelka. What training reveals about neural network complexity. To appear at NeurIPS 2021. (pape r, bibtex, video)

G. Bouritsas, A Loukas, N. Karalias, M. Bronstein. Partition and code: learning how to compress graphs. To appear at NeurIPS 2021. (preprint, bibtex)

Y. Dong, J.B. Cordonnier, A. Loukas. Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depth. Oral at ICML 2021. (preprint, bibtex, blogpost)

N. Karalias, A. Loukas. Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs. Oral at NeurIPS 2020. (paper, bibtex, video starts at 36:54, blogpost, slides, talk at Yale)

A. Loukas. How hard is to distinguish graphs with graph neural networks. NeurIPS 2020. (paper, bibtex, video, blogpost)

C. Vignac, A. Loukas, P. Frossard. Building powerful and equivariant graph neural networks with structural message-passing. NeurIPS 2020 (paper, bibtex, video, blogpost)

A. Loukas. What graph neural networks cannot learn: depth vs width. ICLR 2020. (paper, bibtex, blogpost, 5min-presentation)

JB Cordonnier, A Loukas, M. Jaggi. On the relationship between self-attention and convolution. ICLR 2020. (paper, bibtex, blogpost, code, interactive website)