Yau M., Lu E., Karalias N., Xu J., Jegelka S. (2023). Are Graph Neural Networks Optimal Approximation Algorithms? NeurIPS Workshop on the Mathematics of Modern Machine Learning (M3L) 2023. (arxiv)

Karalias N., Robinson J., Loukas A., Jegelka S. (2022). Neural Set Function Extensions: Learning with Discrete Functions in High Dimensions. NeurIPS 2022. (arxiv, proceedings, blogpost, video presentation)

Karalias N., & Loukas A. (2020). Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs. In NeurIPS (arxiv, code, blogpost, short presentation, podcast, bibtex)

Bouritsas G., Loukas A., Karalias N., Bronstein M. (2021). Partition and Code: learning how to compress graphs. Advances in Neural Information Processing Systems, 34. (arxiv, code, slides, bibtex)