no code implementations • 9 Feb 2024 • Dobrik Georgiev, Pietro Liò, Davide Buffelli
Recent work on neural algorithmic reasoning has demonstrated that graph neural networks (GNNs) could learn to execute classical algorithms.
no code implementations • 8 Jul 2023 • Valerie Engelmayer, Dobrik Georgiev, Petar Veličković
Neural algorithmic reasoners are parallel processors.
1 code implementation • 18 May 2023 • Dobrik Georgiev, Danilo Numeroso, Davide Bacciu, Pietro Liò
Solving NP-hard/complete combinatorial problems with neural networks is a challenging research area that aims to surpass classical approximate algorithms.
1 code implementation • 22 Aug 2022 • Han Xuanyuan, Pietro Barbiero, Dobrik Georgiev, Lucie Charlotte Magister, Pietro Lió
We propose a novel approach for producing global explanations for GNNs using neuron-level concepts to enable practitioners to have a high-level view of the model.
no code implementations • 28 Jan 2022 • Dobrik Georgiev, Marc Brockschmidt, Miltiadis Allamanis
Learning from structured data is a core machine learning task.
1 code implementation • 15 Jul 2021 • Dobrik Georgiev, Pietro Barbiero, Dmitry Kazhdan, Petar Veličković, Pietro Liò
Recent research on graph neural network (GNN) models successfully applied GNNs to classical graph algorithms and combinatorial optimisation problems.
1 code implementation • 25 May 2021 • Pietro Barbiero, Gabriele Ciravegna, Dobrik Georgiev, Franscesco Giannini
"PyTorch, Explain!"
no code implementations • 22 May 2020 • Dobrik Georgiev, Pietro Liò
Graph neural networks (GNNs) have found application for learning in the space of algorithms.