Latent Space Representations of Neural Algorithmic Reasoners

arXiv:2307.08874v2 Announce Type: replace
Abstract: Neural Algorithmic Reasoning (NAR) is a research area focused on designing neural architectures that can reliably capture classical computation, usually by learning to execute algorithms. A typical approach is to rely on Graph Neural Network (GNN) architectures, which encode inputs in high-dimensional latent spaces that are repeatedly transformed during the execution of the algorithm. In this work we perform a detailed analysis of the structure of the latent space induced by the GNN when executing …

arxiv cs.lg space stat.ml type