Fully memristive spiking neural network for energy-efficient graph learning
Science Advances · 09.05.2025 · 11 (19)
DOI: 10.1126/sciadv.adv2312 ↗Kurz gefasst
Fachartikel in der Zeitschrift Science Advances, erschienen am 09.05.2025. Verfasst von Tuo Shi und 14 weiteren Autor:innen. Beteiligte Einrichtung: Zhejiang Laboratory, Hangzhou 311100, China. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 87 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar.
Abstract (Originalsprache)
Parallel and energy-efficient searching of the shortest paths on a large graph is challenging. Conventional methods commonly used are sequential and computing intensive, rendering them inadequate for addressing large-scale and real-time situations. Here, we propose a highly parallel, computation- and energy-efficient approach to shortest path–based graph learning based on an emerging memristor spiking neural network via algorithm-device codesign. The shortest path is obtained parallelly in nature using simultaneous spike traveling instead of arithmetic calculation, achieving extremely low time and space complexity. A nonlinear weight mapping approach is proposed to counterbalance the neuron intrinsic nonlinearity to guarantee accuracy to support large-scale graphs. The memristor hardware capability is experimentally demonstrated in unsupervised and supervised classification tasks. The estimated energy efficiency of 517.82 giga-traversal edges per second per watt outperforms field programmable gate arrays by three to four orders of magnitude, providing a pathway toward highly energy-efficient graph computing hardware.
Autor:innen und Institutionen
- Zhejiang Laboratory, Hangzhou 311100, China.
- State Key Laboratory of Integrated Chips and Systems, Frontier Institute of Chip and System, Fudan University, Shanghai 200433, China.
- Key Laboratory of Brain-like Neuromorphic Devices and Systems of Hebei Province, Hebei University, Baoding 071002, P. R. China.
ORCID-Profile: Tuo Shi, Yang Tian, Huiqin Ma, Zhanfeng Wang, Bo Lyu, Xumeng Zhang, Xiaobing Yan, Qi Liu
Zitieren
APA
Shi, T., Gao, L., Zhou, R., Tian, Y., Chen, P., Ding, Y., Tang, S., Ma, H., Lu, J., Zhang, H., Wang, Z., Lyu, B., Zhang, X., Yan, X., & Liu, Q. (2025). Fully memristive spiking neural network for energy-efficient graph learning. Science Advances, 11(19). https://doi.org/10.1126/sciadv.adv2312
Vancouver
Shi T, Gao L, Zhou R, Tian Y, Chen P, Ding Y, et al. Fully memristive spiking neural network for energy-efficient graph learning. Science Advances. 2025;11(19). doi:10.1126/sciadv.adv2312
BibTeX
@article{Shi2025,
author = {Shi, Tuo and Gao, Lili and Zhou, Ruixi and Tian, Yang and Chen, Pei and Ding, Yanting and Tang, Shuangzhu and Ma, Huiqin and Lu, Jian and Zhang, Hui and Wang, Zhanfeng and Lyu, Bo and Zhang, Xumeng and Yan, Xiaobing and Liu, Qi},
title = {Fully memristive spiking neural network for energy-efficient graph learning},
journal = {Science Advances},
year = {2025},
volume = {11},
number = {19},
doi = {10.1126/sciadv.adv2312}
}
EUVIMED