Loading...
Weighted echo state graph neural networks based on robust and epitaxial film memristors
Guo, Zhenqiang Duan, Guojun Zhang, Yinxing Sun, Yong Zhang, Weifeng Li, Xiaohan Shi, Haowan Li, Pengfei Zhao, Zhen Xu, Jikang
Guo, Zhenqiang
Duan, Guojun
Zhang, Yinxing
Sun, Yong
Zhang, Weifeng
Li, Xiaohan
Shi, Haowan
Li, Pengfei
Zhao, Zhen
Xu, Jikang
Citations
Altmetric:
Advisors
Editors
Other Contributors
Affiliation
EPub Date
Publication Date
2025-01-04
Submitted Date
Collections
Files
Loading...
Article - VoR
Adobe PDF, 4.42 MB
Other Titles
Abstract
Hardware system customized toward the demands of graph neural network learning would promote efficiency and strong temporal processing for graph‐structured data. However, most amorphous/polycrystalline oxides‐based memristors commonly have unstable conductance regulation due to random growth of conductive filaments. And graph neural networks based on robust and epitaxial film memristors can especially improve energy efficiency due to their high endurance and ultra‐low power consumption. Here, robust and epitaxial Gd: HfO2‐based film memristors are reported and construct a weighted echo state graph neural network (WESGNN). Benefiting from the optimized epitaxial films, the high switching speed (20 ns), low energy consumption (2.07 fJ), multi‐value storage (4 bits), and high endurance (109) outperform most memristors. Notably, thanks to the appropriately dispersed conductance distribution (standard deviation = 7.68 nS), the WESGNN finely regulates the relative weights of input nodes and recursive matrix to realize state‐of‐the‐art performance using the MUTAG and COLLAB datasets for graph classification tasks. Overall, robust and epitaxial film memristors offer nanoscale scalability, high reliability, and low energy consumption, making them energy‐efficient hardware solutions for graph learning applications.
Citation
Guo, Z., Duan, G., Zhang, Y., Sun, Y., Zhang, W., Li, X., Shi, H., Li, P., Zhao, Z., Xu, J., Yang, B., Faraj, Y., & Yan, X. (2025). Weighted echo state graph neural networks based on robust and epitaxial film memristors. Advanced Science, 12(8), article-number 2411925. https://doi.org/10.1002/advs.202411925
Publisher
Wiley
Journal
Advanced Science
Research Unit
PubMed ID
PubMed Central ID
Type
Article
Language
Description
© 2025 The Author(s). Advanced Science published by Wiley-VCH GmbH
Series/Report no.
ISSN
EISSN
2198-3844
ISBN
ISMN
Gov't Doc
Test Link
Sponsors
National key R&D plan “nano frontier” key special project (grant no. 2021YFA1200502 and 2024YFA1208400), Disruptive Technology Innovation Project of the National Key R&D Program (grant no. DT01202402075), Interdisciplinary Research Program of Natural Science (grant no. DXK202101), Cultivation projects of national major R & D project (grant no. 92164109), National Natural Science Foundation of China (grant nos. 61674050 and 61874158), Special project of strategic leading science and technology of Chinese Academy of Sciences (grant no. XDB44000000-7), Hebei Basic Research Special Key Project (grant no. F2021201045), the Project of Distinguished Young of Hebei Province (grant no. A2018201231), the Support Program for the Top Young Talents of Hebei Province (grant no. 70280011807), the Hundred Persons Plan of Hebei Province (grant nos. E2018050004 and E2018050003), the Supporting Plan for 100 Excellent Innovative Talents in Colleges and Universities of Hebei Province (grant no. SLRC2019018), outstanding young scientific research and innovation team of Hebei University (grant no. 605020521001), Special support funds for national high level talents (grant no. 041500120001), High-level Talent Research Startup Project of Hebei University (grant no. 521000981426), Funded by Science and Technology Project of Hebei Education Department (grant nos. QN2020178, QN2021026), Baoding Science and Technology Plan Project (2172P011, 2272P014), Postgraduate's Innovation Fund Project of Hebei Province (CXZZBS2024004).