Echo state graph neural networks with analogue random resistive memory arrays
Open accessThe DOI matches its Crossref record; 65 of the 65 references it cites were found in a registry or an index.
Abstract
Recent years have witnessed a surge of interest in learning representations of graph-structured data, with applications from social networks to drug discovery. However, graph neural networks, the machine learning models for handling graph-structured data, face significant challenges when running on conventional digital hardware, including the slowdown of Moore’s law due to transistor scaling limits and the von Neumann bottleneck incurred by physically separated memory and processing units, as well as a high training cost. Here we present a hardware–software co-design to address these challenges, by designing an echo state graph neural network based on random resistive memory arrays, which are built from low-cost, nanoscale and stackable resistors for efficient in-memory computing. This approach leverages the intrinsic stochasticity of dielectric breakdown in resistive switching to implement random projections in hardware for an echo state network that effectively minimizes the training complexity thanks to its fixed and random weights. The system demonstrates state-of-the-art performance on both graph classification using the MUTAG and COLLAB datasets and node classification using the CORA dataset, achieving 2.16×, 35.42× and 40.37× improvements in energy efficiency for a projected random resistive memory-based hybrid analogue–digital system over a state-of-the-art graphics processing unit and 99.35%, 99.99% and 91.40% reductions of backward pass complexity compared with conventional graph learning. The results point to a promising direction for next-generation artificial intelligence systems for graph learning.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“the memristive dot product engine (MDPE), which performs large-scale vector-matrix multiplication (VMM) operations using a memristive crossbar array6–13”
From Flexible self-rectifying synapse array for energy-efficient edge multiplication in electrocardiogram diagnosis (2025) · cites this paper as [12]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
The graph neural network model
Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M., & Monfardini, G. (2009) · IEEE Transactions on Neural Networks · doi:10.1109/tnn.2008.2005605 · Cited by 9,582 · cited 2×
“s() j = as (t) j + (1 − a)σ [uj + ∑ k∈N(j) WRs k ] G (1)”
MethodRedox‐Based Resistive Switching Memories – Nanoionic Mechanisms, Prospects, and Challenges
Waser, R., Dittmann, R., Staikov, G., & Szot, K. (2009) · Advanced Materials · doi:10.1002/adma.200900375 · Cited by 5,080
Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication
Jaeger, H., & Haas, H. (2004) · Science · doi:10.1126/science.1091277 · Cited by 3,811
Graph Convolutional Neural Networks for Web-Scale Recommender Systems
Ying, R., He, R., Chen, K., Eksombatchai, P., Hamilton, W. L., & Leskovec, J. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3219890 · Cited by 3,733 · cited 1×
“For example, the training of PinSage took 78 hours on 32 central processing unit (CPU) cores and 16 Tesla K80 graphics processing units (GPUs) 20 .”
MethodCollective Classification in Network Data
Sen, P., Namata, G., Bilgic, M., Getoor, L., Gallagher, B., & Eliassi‐Rad, T. (2008) · AI Magazine · doi:10.1609/aimag.v29i3.2157 · Cited by 3,293
Training and operation of an integrated neuromorphic network based on metal-oxide memristors
Prezioso, M., Merrikh-Bayat, F., Hoskins, B. D., Adam, G. C., Likharev, K. K., & Strukov, D. B. (2015) · Nature · doi:10.1038/nature14441 · Cited by 3,001
Reservoir computing approaches to recurrent neural network training
Lukoševičius, M., & Jaeger, H. (2009) · Computer Science Review · doi:10.1016/j.cosrev.2009.03.005 · Cited by 2,956 · cited 1×
“Software-wise, the echo state network (ESN) is a type of reservoir computer 26,31,43,58 comprising a large number of neurons with random and recurrent interconnections, where the states of all the neurons are accessible by a simple software readout layer 55,59 (see Supplementary Figs.”
BackgroundDeeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning
Li, Q., Han, Z., & Wu, X.-M. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.11604 · Cited by 2,872
Wong, H.-S. P., Lee, H.-Y., Yu, S., Chen, Y.-S., Wu, Y., Chen, P.-S., Lee, B., Chen, F. T., & Tsai, M.-J. (2012) · Proceedings of the IEEE · doi:10.1109/jproc.2012.2190369 · Cited by 2,757
In-memory computing with resistive switching devices
Ielmini, D., & Wong, H.-S. P. (2018) · Nature Electronics · doi:10.1038/s41928-018-0092-2 · Cited by 2,298 · cited 1×
“Such digital hardware suffers from frequent and massive data shuttling between off-chip memory and processing units during graph learning, the so-called von Neumann bottleneck 10–19 .”
Background
Research works printed but not linked: 4
- Kipf, T. N. & Welling, M. Semi-supervised classification with graph convolutional networks.In Proc. 5th International Conference on Learning Representations (OpenReview.net, 2017).
- Veličković, P. et al. Graph attention networks. In Proc. 6th International Conference on Learning Representations (OpenReview.net, 2018).
- Niepert, M., Ahmed, M. & Kutzkov, K. Learning convolutional neural networks for graphs.In International Conference on Machine Learning 2014–2023 (PMLR, 2016).
- Hamilton, W., Ying, Z. & Leskovec, J. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems (Curran Associates, Inc., 2017).
Cited by
Recent Advances and Future Prospects for Memristive Materials, Devices, and Systems
Song, M.-K., Kang, J.-H., Zhang, X., Ji, W., Ascoli, A., Messaris, I., Demirkol, A. S., Dong, B., Aggarwal, S., Wan, W., et al. (2023) · ACS Nano · doi:10.1021/acsnano.3c03505 · Cited by 300
Self-citationPhysical reservoir computing with emerging electronics
Liang, X., Tang, J., Zhong, Y., Gao, B., Qian, H., & Wu, H. (2024) · Nature Electronics · doi:10.1038/s41928-024-01133-z · Cited by 226
“Novel RC algorithms—such as the recently proposed hierarchical RC 144 , deep RC 145,146 , echo state graph neural networks 147 and next-generation RC 148 —could inspire innovation in eRC architectures and physical nodes.”
Roadmap to neuromorphic computing with emerging technologies
Mehonić, A., Ielmini, D., Roy, K., Mutlu, O., Kvatinsky, S., Serrano‐Gotarredona, T., Linares-Barranco, B., Spiga, S., Savel'ev, S. E., Balanov, A. G., et al. (2024) · APL Materials · doi:10.1063/5.0179424 · Cited by 199
Self-citationMemristor-Based Artificial Chips
Sun, B. T., Chen, Y., Zhou, G., Cao, Z., Yang, C. S., Du, J., Chen, X., & Shao, J. (2023) · ACS Nano · doi:10.1021/acsnano.3c07384 · Cited by 123
Self-citationNanoscale memristor devices: materials, fabrication, and artificial intelligence
Yu, Y., Xiao, M., Fieser, D., Zhou, W., & Hu, A. (2024) · Journal of Materials Chemistry C · doi:10.1039/d3tc04510b · Cited by 78
Metadata
- Authors
- Wang, S., Li, Y., Wang, D., Zhang, W., Chen, X., Dong, D., Wang, S., Zhang, X., Lin, P., Gallicchio, C., Xu, X., Liu, Q., Cheng, K.-T., Wang, Z., Shang, D., & Liu, M.
- Affiliations
- Chinese Academy of Sciences (CN)
- University of Hong Kong (HK)
- Fudan University (CN)
- Zhejiang University (CN)
- University of Pisa (IT)
- Hong Kong University of Science and Technology (HK)
- Corresponding author
- Wang, Zhongrui
- Shang, Dashan
- ORCID
- Venue
- Nature Machine Intelligence
- Published
- 2023-02-13
- Volume
- 5
- Issue
- 2
- Pages
- 104-113
- ISSN
- 2522-5839 (ISSN-L)
- OpenAlex
- W4320486502
- Cited by
- 84
- References
- 65
- Citations by year
- 2026: 15 · 2025: 26 · 2024: 25 · 2023: 18
- FWCI
- 6.24
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- creativecommons.org/licenses/by/4.0 (tdm)
- creativecommons.org/licenses/by/4.0 (vor)
- Locations
- Nature Machine Intelligence (publishedVersion, cc-by)
- Rare & Special e-Zone (The Hong Kong University of Science and Technology) (submittedVersion)
- CINECA IRIS Institutial research information system (University of Pisa) (submittedVersion, cc-by)
- Funders
- National Natural Science Foundation of China (61888102, 61874138, 62122004, XDB44000000, 2018YFA0701500, Z210006, 61821091)
- Chinese Academy of Sciences (XDB44000000, 61888102)
- Innovation and Technology Commission (MHP/066/20)
- Innovation and Technology Fund
- Topics
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Memory and Neural Computing
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Reservoir Computing
- Physical Sciences › Computer Science › Artificial Intelligence › Neural Networks and Applications
- Keywords
- echo state networks, graph neural networks, in-memory computing, hardware-software co-design, dielectric breakdown, energy efficiency, node classification, graph classification, von Neumann bottleneck
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Echo state graph neural networks with analogue random resistive memory arrays. https://app.cochat.ai/papers/10.1038/s42256-023-00609-5
- The paper
- Wang, S., Li, Y., Wang, D., Zhang, W., Chen, X., Dong, D., Wang, S., Zhang, X., Lin, P., Gallicchio, C., Xu, X., Liu, Q., Cheng, K.-T., Wang, Z., Shang, D., & Liu, M. (2023). Echo state graph neural networks with analogue random resistive memory arrays. Nature Machine Intelligence. https://doi.org/10.1038/s42256-023-00609-5
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.