{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T01:18:16Z","timestamp":1776215896929,"version":"3.50.1"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T00:00:00Z","timestamp":1676246400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T00:00:00Z","timestamp":1676246400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Mach Intell"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>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\u2019s 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\u2013software 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\u00d7, 35.42\u00d7 and 40.37\u00d7 improvements in energy efficiency for a projected random resistive memory-based hybrid analogue\u2013digital 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.<\/jats:p>","DOI":"10.1038\/s42256-023-00609-5","type":"journal-article","created":{"date-parts":[[2023,2,13]],"date-time":"2023-02-13T17:03:35Z","timestamp":1676307815000},"page":"104-113","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":77,"title":["Echo state graph neural networks with analogue random resistive memory arrays"],"prefix":"10.1038","volume":"5","author":[{"given":"Shaocong","family":"Wang","sequence":"first","affiliation":[]},{"given":"Yi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Dingchen","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Woyu","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xi","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Danian","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Songqi","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3828-151X","authenticated-orcid":false,"given":"Xumeng","family":"Zhang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0679-8063","authenticated-orcid":false,"given":"Peng","family":"Lin","sequence":"additional","affiliation":[]},{"given":"Claudio","family":"Gallicchio","sequence":"additional","affiliation":[]},{"given":"Xiaoxin","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Qi","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Kwang-Ting","family":"Cheng","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2264-0677","authenticated-orcid":false,"given":"Zhongrui","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3573-8390","authenticated-orcid":false,"given":"Dashan","family":"Shang","sequence":"additional","affiliation":[]},{"given":"Ming","family":"Liu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,2,13]]},"reference":[{"key":"609_CR1","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1109\/TNN.2008.2005605","volume":"20","author":"F Scarselli","year":"2008","unstructured":"Scarselli, F., Gori, M., Tsoi, A. C., Hagenbuchner, M. & Monfardini, G. The graph neural network model. IEEE Trans. Neural Netw. 20, 61\u201380 (2008).","journal-title":"IEEE Trans. Neural Netw."},{"key":"609_CR2","doi-asserted-by":"publisher","first-page":"498","DOI":"10.1109\/TNN.2008.2010350","volume":"20","author":"A Micheli","year":"2009","unstructured":"Micheli, A. Neural network for graphs: a contextual constructive approach. IEEE Trans. Neural Netw. 20, 498\u2013511 (2009).","journal-title":"IEEE Trans. Neural Netw."},{"key":"609_CR3","unstructured":"Kipf, T. N. & Welling, M. Semi-supervised classification with graph convolutional networks.In Proc. 5th International Conference on Learning Representations (OpenReview.net, 2017)."},{"key":"609_CR4","unstructured":"Veli\u010dkovi\u0107, P. et al. Graph attention networks. In Proc. 6th International Conference on Learning Representations (OpenReview.net, 2018)."},{"key":"609_CR5","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1016\/j.neunet.2020.06.006","volume":"129","author":"D Bacciu","year":"2020","unstructured":"Bacciu, D., Errica, F., Micheli, A. & Podda, M. A gentle introduction to deep learning for graphs. Neural Netw. 129, 203\u2013221 (2020).","journal-title":"Neural Netw."},{"key":"609_CR6","doi-asserted-by":"publisher","first-page":"919","DOI":"10.1093\/bib\/bbz042","volume":"21","author":"M Sun","year":"2020","unstructured":"Sun, M. et al. Graph convolutional networks for computational drug development and discovery. Brief. Bioinform. 21, 919\u2013935 (2020).","journal-title":"Brief. Bioinform."},{"key":"609_CR7","doi-asserted-by":"crossref","unstructured":"Fan, W. et al. Graph neural networks for social recommendation. In The World Wide Web Conference (WWW) 417\u2013426 (ACM, 2019).","DOI":"10.1145\/3308558.3313488"},{"key":"609_CR8","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1038\/s41586-021-03544-w","volume":"594","author":"A Mirhoseini","year":"2021","unstructured":"Mirhoseini, A. et al. A graph placement methodology for fast chip design. Nature 594, 207\u2013212 (2021).","journal-title":"Nature"},{"key":"609_CR9","unstructured":"Lerer, A. et al. Pytorch-biggraph: a large-scale graph embedding system. In Proc. Machine Learning and Systems Vol. 1, 120\u2013131 (MLSys, 2019)."},{"key":"609_CR10","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1038\/s41928-018-0092-2","volume":"1","author":"D Ielmini","year":"2018","unstructured":"Ielmini, D. & Wong, H. S. P. In-memory computing with resistive switching devices. Nat. Electron. 1, 333\u2013343 (2018).","journal-title":"Nat. Electron."},{"key":"609_CR11","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1038\/s41928-020-0435-7","volume":"3","author":"W Zhang","year":"2020","unstructured":"Zhang, W. et al. Neuro-inspired computing chips. Nat. Electron. 3, 371\u2013382 (2020).","journal-title":"Nat. Electron."},{"key":"609_CR12","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1038\/s41928-017-0006-8","volume":"1","author":"MA Zidan","year":"2018","unstructured":"Zidan, M. A., Strachan, J. P. & Lu, W. D. The future of electronics based on memristive systems. Nat. Electron. 1, 22\u201329 (2018).","journal-title":"Nat. Electron."},{"key":"609_CR13","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1038\/s41565-020-0647-z","volume":"15","author":"VK Sangwan","year":"2020","unstructured":"Sangwan, V. K. & Hersam, M. C. Neuromorphic nanoelectronic materials. Nat. Nanotechnol. 15, 517\u2013528 (2020).","journal-title":"Nat. Nanotechnol."},{"key":"609_CR14","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1038\/s41565-020-0655-z","volume":"15","author":"A Sebastian","year":"2020","unstructured":"Sebastian, A., Le Gallo, M., Khaddam-Aljameh, R. & Eleftheriou, E. Memory devices and applications for in-memory computing. Nat. Nanotechnol. 15, 529\u2013544 (2020).","journal-title":"Nat. Nanotechnol."},{"key":"609_CR15","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/JPROC.2020.3004543","volume":"109","author":"Y Xi","year":"2021","unstructured":"Xi, Y. et al. In-memory learning with analog resistive switching memory: a review and perspective. Proc. IEEE 109, 14\u201342 (2021).","journal-title":"Proc. IEEE"},{"key":"609_CR16","doi-asserted-by":"publisher","first-page":"260","DOI":"10.1109\/JPROC.2018.2790840","volume":"106","author":"S Yu","year":"2018","unstructured":"Yu, S. Neuro-inspired computing with emerging nonvolatile memorys. Proc. IEEE 106, 260\u2013285 (2018).","journal-title":"Proc. IEEE"},{"key":"609_CR17","first-page":"89","volume":"2","author":"GW Burr","year":"2016","unstructured":"Burr, G. W. et al. Neuromorphic computing using non-volatile memory. Adv. Phys. X 2, 89\u2013124 (2016).","journal-title":"Adv. Phys. X"},{"key":"609_CR18","doi-asserted-by":"publisher","first-page":"1704729","DOI":"10.1002\/adma.201704729","volume":"30","author":"DS Jeong","year":"2018","unstructured":"Jeong, D. S. & Hwang, C. S. Nonvolatile memory materials for neuromorphic intelligent machines. Adv. Mater. 30, 1704729 (2018).","journal-title":"Adv. Mater."},{"key":"609_CR19","doi-asserted-by":"publisher","first-page":"499","DOI":"10.1038\/s42254-020-0208-2","volume":"2","author":"D Markovi\u0107","year":"2020","unstructured":"Markovi\u0107, D., Mizrahi, A., Querlioz, D. & Grollier, J. Physics for neuromorphic computing. Nat. Rev. Phys. 2, 499\u2013510 (2020).","journal-title":"Nat. Rev. Phys."},{"key":"609_CR20","doi-asserted-by":"crossref","unstructured":"Ying, R. et al. Graph convolutional neural networks for web-scale recommender systems. In Proc. 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining 974\u2013983 (ACM, 2018).","DOI":"10.1145\/3219819.3219890"},{"key":"609_CR21","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms3072","volume":"4","author":"F Alibart","year":"2013","unstructured":"Alibart, F., Zamanidoost, E. & Strukov, D. B. Pattern classification by memristive crossbar circuits using ex situ and in situ training. Nat. Commun. 4, 2072 (2013).","journal-title":"Nat. Commun."},{"key":"609_CR22","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1038\/nature14441","volume":"521","author":"M Prezioso","year":"2015","unstructured":"Prezioso, M. et al. Training and operation of an integrated neuromorphic network based on metal-oxide memristors. Nature 521, 61\u201364 (2015).","journal-title":"Nature"},{"key":"609_CR23","doi-asserted-by":"crossref","unstructured":"Yu, S. et al. Binary neural network with 16 Mb RRAM macro chip for classification and online training. In 2016 IEEE International Electron Devices Meeting 16.2.1\u201316.2.4 (IEEE, 2017).","DOI":"10.1109\/IEDM.2016.7838429"},{"key":"609_CR24","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms15199","volume":"8","author":"P Yao","year":"2017","unstructured":"Yao, P. et al. Face classification using electronic synapses. Nat. Commun. 8, 15199 (2017).","journal-title":"Nat. Commun."},{"key":"609_CR25","doi-asserted-by":"publisher","first-page":"784","DOI":"10.1038\/nnano.2017.83","volume":"12","author":"PM Sheridan","year":"2017","unstructured":"Sheridan, P. M. et al. Sparse coding with memristor networks. Nat. Nanotechnol. 12, 784\u2013789 (2017).","journal-title":"Nat. Nanotechnol."},{"key":"609_CR26","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-017-02337-y","volume":"8","author":"C Du","year":"2017","unstructured":"Du, C. et al. Reservoir computing using dynamic memristors for temporal information processing. Nat. Commun. 8, 2204 (2017).","journal-title":"Nat. Commun."},{"key":"609_CR27","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1038\/s41586-018-0180-5","volume":"558","author":"S Ambrogio","year":"2018","unstructured":"Ambrogio, S. et al. Equivalent-accuracy accelerated neural-network training using analogue memory. Nature 558, 60\u201367 (2018).","journal-title":"Nature"},{"key":"609_CR28","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-04482-4","volume":"9","author":"FM Bayat","year":"2018","unstructured":"Bayat, F. M. et al. Implementation of multilayer perceptron network with highly uniform passive memristive crossbar circuits. Nat. Commun. 9, 2331 (2018).","journal-title":"Nat. Commun."},{"key":"609_CR29","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-018-04933-y","volume":"9","author":"I Boybat","year":"2018","unstructured":"Boybat, I. et al. Neuromorphic computing with multi-memristive synapses. Nat. Commun. 9, 2514 (2018).","journal-title":"Nat. Commun."},{"key":"609_CR30","doi-asserted-by":"publisher","first-page":"1705914","DOI":"10.1002\/adma.201705914","volume":"30","author":"M Hu","year":"2018","unstructured":"Hu, M. et al. Memristor-based analog computation and neural network classification with a dot product engine. Adv. Mater. 30, 1705914 (2018).","journal-title":"Adv. Mater."},{"key":"609_CR31","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1038\/s41928-019-0313-3","volume":"2","author":"J Moon","year":"2019","unstructured":"Moon, J. et al. Temporal data classification and forecasting using a memristor-based reservoir computing system. Nat. Electron. 2, 480\u2013487 (2019).","journal-title":"Nat. Electron."},{"key":"609_CR32","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1038\/s41928-019-0270-x","volume":"2","author":"F Cai","year":"2019","unstructured":"Cai, F. et al. A fully integrated reprogrammable memristor\u2013CMOS system for efficient multiply\u2013accumulate operations. Nat. Electron. 2, 290\u2013299 (2019).","journal-title":"Nat. Electron."},{"key":"609_CR33","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-17215-3","volume":"11","author":"Q Duan","year":"2020","unstructured":"Duan, Q. et al. Spiking neurons with spatiotemporal dynamics and gain modulation for monolithically integrated memristive neural networks. Nat. Commun. 11, 3399 (2020).","journal-title":"Nat. Commun."},{"key":"609_CR34","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-16108-9","volume":"11","author":"V Joshi","year":"2020","unstructured":"Joshi, V. et al. Accurate deep neural network inference using computational phase-change memory. Nat. Commun. 11, 2473 (2020).","journal-title":"Nat. Commun."},{"key":"609_CR35","doi-asserted-by":"publisher","first-page":"641","DOI":"10.1038\/s41586-020-1942-4","volume":"577","author":"P Yao","year":"2020","unstructured":"Yao, P. et al. Fully hardware-implemented memristor convolutional neural network. Nature 577, 641\u2013646 (2020).","journal-title":"Nature"},{"key":"609_CR36","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1038\/s42256-020-0187-0","volume":"2","author":"S Wo\u017aniak","year":"2020","unstructured":"Wo\u017aniak, S., Pantazi, A., Bohnstingl, T. & Eleftheriou, E. Deep learning incorporating biologically inspired neural dynamics and in-memory computing. Nat. Mach. Intell. 2, 325\u2013336 (2020).","journal-title":"Nat. Mach. Intell."},{"key":"609_CR37","doi-asserted-by":"publisher","unstructured":"Xue, C.-X. et al. A CMOS-integrated compute-in-memory macro based on resistive random-access memory for AI edge devices. Nat. Electron. https:\/\/doi.org\/10.1038\/s41928-020-00505-5 (2020).","DOI":"10.1038\/s41928-020-00505-5"},{"key":"609_CR38","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1038\/s41928-020-0410-3","volume":"3","author":"G Karunaratne","year":"2020","unstructured":"Karunaratne, G. et al. In-memory hyperdimensional computing. Nat. Electron. 3, 327\u2013337 (2020).","journal-title":"Nat. Electron."},{"key":"609_CR39","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-18105-4","volume":"11","author":"Z Liu","year":"2020","unstructured":"Liu, Z. et al. Neural signal analysis with memristor arrays towards high-efficiency brain\u2013machine interfaces. Nat. Commun. 11, 4234 (2020).","journal-title":"Nat. Commun."},{"key":"609_CR40","doi-asserted-by":"publisher","first-page":"eaay2378","DOI":"10.1126\/sciadv.aay2378","volume":"6","author":"Z Sun","year":"2020","unstructured":"Sun, Z., Pedretti, G., Bricalli, A. & Ielmini, D. One-step regression and classification with cross-point resistive memory arrays. Sci. Adv. 6, eaay2378 (2020).","journal-title":"Sci. Adv."},{"key":"609_CR41","doi-asserted-by":"publisher","first-page":"eaba9901","DOI":"10.1126\/sciadv.aba9901","volume":"6","author":"K Yang","year":"2020","unstructured":"Yang, K. et al. Transiently chaotic simulated annealing based on intrinsic nonlinearity of memristors for efficient solution of optimization problems. Sci. Adv. 6, eaba9901 (2020).","journal-title":"Sci. Adv."},{"key":"609_CR42","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-021-22364-0","volume":"12","author":"G Karunaratne","year":"2021","unstructured":"Karunaratne, G. et al. Robust high-dimensional memory-augmented neural networks. Nat. Commun. 12, 2468 (2021).","journal-title":"Nat. Commun."},{"key":"609_CR43","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-020-20692-1","volume":"12","author":"Y Zhong","year":"2021","unstructured":"Zhong, Y. et al. Dynamic memristor-based reservoir computing for high-efficiency temporal signal processing. Nat. Commun. 12, 408 (2021).","journal-title":"Nat. Commun."},{"key":"609_CR44","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1038\/s41563-021-01099-9","volume":"21","author":"G Milano","year":"2022","unstructured":"Milano, G. et al. In materia reservoir computing with a fully memristive architecture based on self-organizing nanowire networks. Nat. Mater. 21, 195\u2013202 (2022).","journal-title":"Nat. Mater."},{"key":"609_CR45","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1038\/s41928-020-00523-3","volume":"4","author":"T Dalgaty","year":"2021","unstructured":"Dalgaty, T. et al. In situ learning using intrinsic memristor variability via Markov chain Monte Carlo sampling. Nat. Electron. 4, 151\u2013161 (2021).","journal-title":"Nat. Electron."},{"key":"609_CR46","doi-asserted-by":"crossref","unstructured":"Song, L., Zhuo, Y., Qian, X., Li, H. & Chen, Y. GraphR: Accelerating graph processing using ReRAM. In Proc. IEEE International Symposium on High Performance Computer Architecture 531\u2013543 (IEEE, 2018).","DOI":"10.1109\/HPCA.2018.00052"},{"key":"609_CR47","doi-asserted-by":"crossref","unstructured":"Dai, G., Huang, T., Wang, Y., Yang, H. & Wawrzynek, J. GraphSAR: A sparsity-aware processing-in-memory architecture for large-scale graph processing on ReRAMs. In Proc. 24th Asia and South Pacific Design Automation Conference (ASPDAC) 120\u2013126 (ACM, 2019).","DOI":"10.1145\/3287624.3287637"},{"key":"609_CR48","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1038\/nature03190","volume":"433","author":"K Terabe","year":"2005","unstructured":"Terabe, K., Hasegawa, T., Nakayama, T. & Aono, M. Quantized conductance atomic switch. Nature 433, 47\u201350 (2005).","journal-title":"Nature"},{"key":"609_CR49","doi-asserted-by":"publisher","first-page":"2632","DOI":"10.1002\/adma.200900375","volume":"21","author":"R Waser","year":"2009","unstructured":"Waser, R., Dittmann, R., Staikov, G. & Szot, K. Redox-based resistive switching memories \u2013 nanoionic mechanisms, prospects, and challenges. Adv. Mater. 21, 2632\u20132663 (2009).","journal-title":"Adv. Mater."},{"key":"609_CR50","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1038\/nmat3054","volume":"10","author":"T Ohno","year":"2011","unstructured":"Ohno, T. et al. Short-term plasticity and long-term potentiation mimicked in single inorganic synapses. Nat. Mater. 10, 591\u2013595 (2011).","journal-title":"Nat. Mater."},{"key":"609_CR51","doi-asserted-by":"publisher","first-page":"1951","DOI":"10.1109\/JPROC.2012.2190369","volume":"100","author":"HSP Wong","year":"2012","unstructured":"Wong, H. S. P. et al. Metal-oxide RRAM. Proc. IEEE 100, 1951\u20131970 (2012).","journal-title":"Proc. IEEE"},{"key":"609_CR52","doi-asserted-by":"publisher","first-page":"530","DOI":"10.1038\/nmat3307","volume":"11","author":"I Valov","year":"2012","unstructured":"Valov, I. et al. Atomically controlled electrochemical nucleation at superionic solid electrolyte surfaces. Nat. Mater. 11, 530\u2013535 (2012).","journal-title":"Nat. Mater."},{"key":"609_CR53","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms2784","volume":"4","author":"I Valov","year":"2013","unstructured":"Valov, I. et al. Nanobatteries in redox-based resistive switches require extension of memristor theory. Nat. Commun. 4, 1771 (2013).","journal-title":"Nat. Commun."},{"key":"609_CR54","doi-asserted-by":"publisher","first-page":"78","DOI":"10.1126\/science.1091277","volume":"304","author":"H Jaeger","year":"2004","unstructured":"Jaeger, H. & Haas, H. Harnessing nonlinearity: predicting chaotic systems and saving energy in wireless communication. Science 304, 78\u201380 (2004).","journal-title":"Science"},{"key":"609_CR55","doi-asserted-by":"crossref","unstructured":"Gallicchio, C. & Micheli, A. Fast and deep graph neural networks.In Proc. AAAI Conference on Artificial Intelligence 34, 3898\u20133905 (AAAI, 2020).","DOI":"10.1609\/aaai.v34i04.5803"},{"key":"609_CR56","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-017-00869-x","volume":"8","author":"H Jiang","year":"2017","unstructured":"Jiang, H. et al. A novel true random number generator based on a stochastic diffusive memristor. Nat. Commun. 8, 882 (2017).","journal-title":"Nat. Commun."},{"key":"609_CR57","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1038\/s41928-018-0039-7","volume":"1","author":"H Nili","year":"2018","unstructured":"Nili, H. et al. Hardware-intrinsic security primitives enabled by analogue state and nonlinear conductance variations in integrated memristors. Nat. Electron. 1, 197\u2013202 (2018).","journal-title":"Nat. Electron."},{"key":"609_CR58","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.cosrev.2009.03.005","volume":"3","author":"M Luko\u0161evi\u010dius","year":"2009","unstructured":"Luko\u0161evi\u010dius, M. & Jaeger, H. Reservoir computing approaches to recurrent neural network training. Comput. Sci. Rev. 3, 127\u2013149 (2009).","journal-title":"Comput. Sci. Rev."},{"key":"609_CR59","doi-asserted-by":"crossref","unstructured":"Gallicchio, C. & Micheli, A. Graph echo state networks. In The 2010 International Joint Conference on Neural Networks 1\u20138 (IEEE, 2010).","DOI":"10.1109\/IJCNN.2010.5596796"},{"key":"609_CR60","doi-asserted-by":"publisher","first-page":"786","DOI":"10.1021\/jm00106a046","volume":"34","author":"AK Debnath","year":"1991","unstructured":"Debnath, A. K., Lopez de Compadre, R. L., Debnath, G., Shusterman, A. J. & Hansch, C. Structure\u2013activity relationship of mutagenic aromatic and heteroaromatic nitro compounds. Correlation with molecular orbital energies and hydrophobicity. J. Med. Chem. 34, 786\u2013797 (1991).","journal-title":"J. Med. Chem."},{"key":"609_CR61","doi-asserted-by":"crossref","unstructured":"Li, Q., Han, Z. & Wu, X.-M. Deeper insights into graph convolutional networks for semi-supervised learning. In Proc. of the AAAI Conference on Artificial Intelligence 32 (AAAI, 2018).","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"609_CR62","doi-asserted-by":"crossref","unstructured":"Al-Rfou, R., Perozzi, B. & Zelle, D. Ddgk: Learning graph representations for deep divergence graph kernels. In World Wide Web Conference 37\u201348 (ACM, 2019).","DOI":"10.1145\/3308558.3313668"},{"key":"609_CR63","unstructured":"Niepert, M., Ahmed, M. & Kutzkov, K. Learning convolutional neural networks for graphs.In International Conference on Machine Learning 2014\u20132023 (PMLR, 2016)."},{"key":"609_CR64","doi-asserted-by":"crossref","unstructured":"Yanardag, P. & Vishwanathan, S. Deep graph kernels. In Proc. 21th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining 1365\u20131374 (ACM, 2015).","DOI":"10.1145\/2783258.2783417"},{"key":"609_CR65","unstructured":"Hamilton, W., Ying, Z. & Leskovec, J. Inductive representation learning on large graphs. In Advances in Neural Information Processing Systems (Curran Associates, Inc., 2017)."},{"key":"609_CR66","doi-asserted-by":"crossref","unstructured":"Zhang, M., Cui, Z., Neumann, M. & Chen, Y. An end-to-end deep learning architecture for graph classification. In AAAI Conference on Artificial Intelligence (AAAI, 2018).","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"609_CR67","first-page":"93","volume":"29","author":"P Sen","year":"2008","unstructured":"Sen, P. et al. Collective classification in network data. AI Mag. 29, 93\u201393 (2008).","journal-title":"AI Mag."},{"key":"609_CR68","doi-asserted-by":"publisher","unstructured":"Wang, S. et al. Code for \u2018Echo state graph neural networks with analogue random resistor arrays\u2019. HKU Library https:\/\/doi.org\/10.25442\/hku.21762944 (2022).","DOI":"10.25442\/hku.21762944"}],"container-title":["Nature Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00609-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00609-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00609-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,2,23]],"date-time":"2023-02-23T00:10:32Z","timestamp":1677111032000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s42256-023-00609-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,13]]},"references-count":68,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2023,2]]}},"alternative-id":["609"],"URL":"https:\/\/doi.org\/10.1038\/s42256-023-00609-5","relation":{},"ISSN":["2522-5839"],"issn-type":[{"value":"2522-5839","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,13]]},"assertion":[{"value":"5 September 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 February 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}