← Search

Antonis Vasileiou

2 accepted papers

2026

Which Algorithms Can Graph Neural Networks Learn?

ICML 2026oral

In recent years, there has been growing interest in understanding neural architectures' ability to learn to execute discrete algorithms, a line of work often referred to as neural algorithmic reasoning. The goal is to integrate algorithmic reasoning capabilities into larger neural pipelines. Many su…

Cited by 0SourceScholar
2025

Covered Forest: Fine-grained generalization analysis of graph neural networks

ICML 2025spotlight

The expressive power of message-passing graph neural networks (MPNNs) is reasonably well understood, primarily through combinatorial techniques from graph isomorphism testing. However, MPNNs' generalization abilities---making meaningful predictions beyond the training set---remain less explored. Cur…