English

Binarized Simplicial Convolutional Neural Networks

Machine Learning 2024-10-24 v2 Signal Processing

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 strategy. The usage of the Hodge Laplacian on a binary-sign forward propagation enables Bi-SCNN to efficiently and effectively represent simplicial features that have higher-order structures than traditional graph node representations. Compared to the previous Simplicial Convolutional Neural Networks, the reduced model complexity of Bi-SCNN shortens the execution time without sacrificing the prediction performance and is less prone to the over-smoothing effect. Experimenting with real-world citation and ocean-drifter data confirmed that our proposed Bi-SCNN is efficient and accurate.

Keywords

Cite

@article{arxiv.2405.04098,
  title  = {Binarized Simplicial Convolutional Neural Networks},
  author = {Yi Yan and Ercan E. Kuruoglu},
  journal= {arXiv preprint arXiv:2405.04098},
  year   = {2024}
}
R2 v1 2026-06-28T16:19:08.142Z