Binarized Simplicial Convolutional Neural Networks
Neural Networks · 2025-03 · 183 · 106928
DOI: 10.1016/j.neunet.2024.106928 ↗Kurz gefasst
Fachartikel in der Zeitschrift Neural Networks, 2025-03. Verfasst von Yi Yan und 1 weiteren Autor:innen. Beteiligte Einrichtung: Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China. Electronic address: yiyiyiyan@outlook.com. Hauptthemen laut MEDLINE: Neural Networks, Computer. Die Arbeit wurde bisher 28-mal zitiert (Crossref) und nennt 41 Literaturangaben. Gefördert von: Tsinghua Shenzhen International Graduate School, Science, Technology and Innovation Commission of Shenzhen Municipality.
Abstract (Originalsprache)
Graph Neural Networks have the limitation of processing features solely on graph nodes, neglecting data on high-dimensional structures such as edges and triangles. Simplicial Convolutional Neural Networks (SCNN) represent high-order structures using simplicial complexes to break this limitation but still lack time efficiency. In this paper, a novel neural network architecture named Binarized Simplicial Convolutional Neural Networks (Bi-SCNN) is proposed based on the combination of simplicial convolution with a weighted binary-sign forward propagation strategy. The utilization of the Hodge Laplacian on a weighted binary-sign forward propagation enables Bi-SCNN to efficiently and effectively represent simplicial features with higher-order structures, surpassing the capabilities of traditional graph node representations. The Bi-SCNN achieves reduced model complexity compared to previous SSCN variants through binarization and normalization, also serving as intrinsic nonlinearities of Bi-SCNN; this enables Bi-SCNN to shorten the execution time without compromising prediction performance and makes Bi-SCNN less prone to over-smoothing. Experimenting with real-world citation and ocean-drifter data confirmed that our proposed Bi-SCNN is efficient and accurate.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China. Electronic address: yiyiyiyan@outlook.com.
- Tsinghua Shenzhen International Graduate School, Tsinghua University, Shenzhen, China. Electronic address: kuruoglu@sz.tsinghua.edu.cn.
Förderung
- Tsinghua Shenzhen International Graduate School
- Science, Technology and Innovation Commission of Shenzhen Municipality
Zitieren
APA
Yan, Y., & Kuruoglu, E. E. (2025). Binarized Simplicial Convolutional Neural Networks. Neural Networks, 183, 106928. https://doi.org/10.1016/j.neunet.2024.106928
Vancouver
Yan Y, Kuruoglu EE. Binarized Simplicial Convolutional Neural Networks. Neural Networks. 2025;183:106928. doi:10.1016/j.neunet.2024.106928
BibTeX
@article{Yan2025,
author = {Yan, Yi and Kuruoglu, Ercan Engin},
title = {Binarized Simplicial Convolutional Neural Networks},
journal = {Neural Networks},
year = {2025},
volume = {183},
pages = {106928},
doi = {10.1016/j.neunet.2024.106928}
}
EUVIMED