Binarized Simplicial Convolutional Neural Networks

arXiv:2405.04098v1 Announce Type: new
Abstract: Graph Neural Networks have a limitation of solely processing features on graph nodes, neglecting data on high-dimensional structures such as edges and triangles. Simplicial Convolutional Neural Networks (SCNN) represent higher-order structures using simplicial complexes to break this limitation albeit still lacking time efficiency. In this paper, we propose a novel neural network architecture on simplicial complexes named Binarized Simplicial Convolutional Neural Networks (Bi-SCNN) based on the combination of simplicial convolution with a binary-sign forward propagation …

abstract arxiv convolutional convolutional neural networks cs.lg data eess.sp efficiency features graph graph neural networks networks neural networks nodes novel paper processing type