Simplicial Attention Neural Networks

1 code implementation • 14 Mar 2022 • L. Giusti, C. Battiloro, P. Di Lorenzo, S. Sardellitti, S. Barbarossa

The aim of this work is to introduce simplicial attention networks (SANs), i. e., novel neural architectures that operate on data defined on simplicial complexes leveraging masked self-attentional layers.

Imputation Trajectory Prediction