{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T22:01:09Z","timestamp":1776290469153,"version":"3.50.1"},"reference-count":174,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Government through the Australian Research Council","doi-asserted-by":"publisher","award":["LP160100630"],"award-info":[{"award-number":["LP160100630"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000923","name":"Australian Government through the Australian Research Council","doi-asserted-by":"publisher","award":["LP180100654"],"award-info":[{"award-number":["LP180100654"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["III-1526499"],"award-info":[{"award-number":["III-1526499"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["III-1763325"],"award-info":[{"award-number":["III-1763325"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["III-1909323"],"award-info":[{"award-number":["III-1909323"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"NSF","doi-asserted-by":"publisher","award":["CNS-1930941"],"award-info":[{"award-number":["CNS-1930941"]}],"id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Neural Netw. Learning Syst."],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1109\/tnnls.2020.2978386","type":"journal-article","created":{"date-parts":[[2020,3,24]],"date-time":"2020-03-24T22:03:24Z","timestamp":1585087404000},"page":"4-24","source":"Crossref","is-referenced-by-count":8576,"title":["A Comprehensive Survey on Graph Neural Networks"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4450-7738","authenticated-orcid":false,"given":"Zonghan","family":"Wu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0794-527X","authenticated-orcid":false,"given":"Shirui","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Fengwen","family":"Chen","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3740-9515","authenticated-orcid":false,"given":"Guodong","family":"Long","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5715-7154","authenticated-orcid":false,"given":"Chengqi","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Philip S.","family":"Yu","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref170","first-page":"4548","article-title":"Mime: Multilevel medical embedding of electronic health records for predictive healthcare","author":"choi","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref172","first-page":"5900","article-title":"Graph convolutional networks with argument-aware pooling for event detection","author":"nguyen","year":"2018","journal-title":"Proc AAAI"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2016.09.046"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref173","first-page":"536","article-title":"Combinatorial optimization with graph convolutional networks and guided tree search","author":"li","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/872"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098126"},{"key":"ref39","article-title":"A survey on graph kernels","author":"kriege","year":"2019","journal-title":"arXiv 1903 11835"},{"key":"ref38","first-page":"1","article-title":"Approximated neighbours MinHash graph node kernel","author":"navarin","year":"2017","journal-title":"Proc ESANN"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/493"},{"key":"ref32","first-page":"1895","article-title":"Tri-party deep network representation","author":"pan","year":"2016","journal-title":"Proc IJCAI"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.03.022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2807452"},{"key":"ref37","first-page":"2539","article-title":"Weisfeiler–Lehman graph kernels","volume":"12","author":"shervashidze","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref36","first-page":"1201","article-title":"Graph kernels","volume":"11","author":"vishwanathan","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.8626170"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2849727"},{"key":"ref27","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"gilmer","year":"2017","journal-title":"Proc ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2018.2850013"},{"key":"ref20","article-title":"Deep convolutional networks on graph-structured data","author":"henaff","year":"2015","journal-title":"arXiv 1506 05163"},{"key":"ref22","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc ICLR"},{"key":"ref21","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","author":"defferrard","year":"2016","journal-title":"Proc NIPS"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2010350"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2879624"},{"key":"ref101","first-page":"1","article-title":"Order matters: Sequence to sequence for sets","author":"vinyals","year":"2016","journal-title":"Proc ICLR"},{"key":"ref26","first-page":"2014","article-title":"Learning convolutional neural networks for graphs","author":"niepert","year":"2016","journal-title":"Proc ICML"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1115"},{"key":"ref25","first-page":"1993","article-title":"Diffusion-convolutional neural networks","author":"atwood","year":"2016","journal-title":"Proc NIPS"},{"key":"ref50","first-page":"941","article-title":"Stochastic training of graph convolutional networks with variance reduction","author":"chen","year":"2018","journal-title":"Proc ICML"},{"key":"ref51","first-page":"4563","article-title":"Adaptive sampling towards fast graph representation learning","author":"huang","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2078"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1209"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1026"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1150"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00756"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1159"},{"key":"ref151","first-page":"2655","article-title":"Out of the box: Reasoning with graph convolution nets for factual visual question answering","author":"narasimhan","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref146","first-page":"673","article-title":"Neural graph matching networks for fewshot 3D action recognition","author":"guo","year":"2018","journal-title":"Proc ECCV"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/418"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.556"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.697"},{"key":"ref59","first-page":"1145","article-title":"Deep neural networks for learning graph representations","author":"cao","year":"2016","journal-title":"Proc AAAI"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"ref57","first-page":"1","article-title":"How powerful are graph neural networks","author":"xu","year":"2019","journal-title":"Proc ICLR"},{"key":"ref56","first-page":"1","article-title":"Deep graph infomax","author":"veli?kovi?","year":"2019","journal-title":"Proc ICLR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014424"},{"key":"ref54","first-page":"4801","article-title":"Hierarchical graph representation learning with differentiable pooling","author":"ying","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref53","first-page":"1","article-title":"Deeper insights into graph convolutional networks for semi-supervised learning","author":"li","year":"2018","journal-title":"Proc AAAI"},{"key":"ref52","first-page":"1","article-title":"An end-to-end deep learning architecture for graph classification","author":"zhang","year":"2018","journal-title":"Proc AAAI"},{"key":"ref40","first-page":"3546","article-title":"Adaptive graph convolutional neural networks","author":"li","year":"2018","journal-title":"Proc AAAI"},{"key":"ref167","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220077"},{"key":"ref166","first-page":"1","article-title":"Learning to represent programs with graphs","author":"allamanis","year":"2017","journal-title":"Proc ICLR"},{"key":"ref165","first-page":"6410","article-title":"Graph convolutional policy network for goal-directed molecular graph generation","author":"you","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref164","first-page":"6530","article-title":"Protein interface prediction using graph convolutional networks","author":"fout","year":"2017","journal-title":"Proc NIPS"},{"key":"ref163","first-page":"3697","article-title":"Geometric matrix completion with recurrent multi-graph neural networks","author":"monti","year":"2017","journal-title":"Proc NIPS"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref161","article-title":"Graph convolutional matrix completion","author":"van den berg","year":"2017","journal-title":"arXiv 1706 02263"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741093"},{"key":"ref4","article-title":"Google’s neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016","journal-title":"arXiv 1609 08144"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref6","article-title":"Convolutional networks for images, speech, and time series","volume":"3361","author":"lecun","year":"1995","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref8","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref159","first-page":"2588","article-title":"Deep multi-view spatial-temporal network for taxi demand prediction","author":"yao","year":"2018","journal-title":"Proc AAAI"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref49","first-page":"1","article-title":"FastGCN: Fast learning with graph convolutional networks via importance sampling","author":"chen","year":"2018","journal-title":"Proc ICLR"},{"key":"ref157","first-page":"1","article-title":"Learning graphical state transitions","author":"johnson","year":"2016","journal-title":"Proc ICLR"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1071"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2018.8628758"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219947"},{"key":"ref48","first-page":"1","article-title":"GaAN: Gated attention networks for learning on large and spatiotemporal graphs","author":"zhang","year":"2018","journal-title":"Proc UAI"},{"key":"ref47","first-page":"1","article-title":"Contextual graph Markov model: A deep and generative approach to graph processing","author":"bacciu","year":"2018","journal-title":"Proc ICML"},{"key":"ref42","first-page":"1024","article-title":"Inductive representation learning on large graphs","author":"hamilton","year":"2017","journal-title":"Proc NIPS"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186116"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.576"},{"key":"ref43","first-page":"1","article-title":"Graph attention networks","author":"velickovic","year":"2017","journal-title":"Proc ICLR"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1145\/1557019.1557109"},{"key":"ref126","article-title":"Alchemy: A quantum chemistry dataset for benchmarking AI models","author":"chen","year":"2019","journal-title":"arXiv 1906 09427"},{"key":"ref125","article-title":"Quantum chemistry structures and properties of 134 kilo molecules","volume":"1","author":"ramakrishnan","year":"2014","journal-title":"Data Science Journal"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btg130"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.573"},{"key":"ref72","first-page":"1","article-title":"Diffusion convolutional recurrent neural network: Data-driven traffic forecasting","author":"li","year":"2018","journal-title":"Proc ICLR"},{"key":"ref71","first-page":"362","article-title":"Structured sequence modeling with graph convolutional recurrent networks","author":"seo","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1145\/2611567"},{"key":"ref70","first-page":"1","article-title":"NetGAN: Generating graphs via random walks","author":"bojchevski","year":"2018","journal-title":"Proc ICML"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/264"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301922"},{"key":"ref130","doi-asserted-by":"crossref","first-page":"1306","DOI":"10.1609\/aaai.v24i1.7519","article-title":"Toward an architecture for never-ending language learning","author":"carlson","year":"2010","journal-title":"Proc AAAI"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/505"},{"key":"ref75","first-page":"1","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","author":"yan","year":"2018","journal-title":"Proc AAAI"},{"key":"ref133","first-page":"1","article-title":"Deep graph library: Towards efficient and scalable deep learning on graphs","author":"wang","year":"2019","journal-title":"Proc ICLR Workshop Represent Learn Graphs Manifolds"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1145\/3132847.3132967"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2015.2492567"},{"key":"ref131","first-page":"1","article-title":"Pitfalls of graph neural network evaluation","author":"shchur","year":"2018","journal-title":"Proc NeurIPS Workshop"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2526058"},{"key":"ref132","first-page":"1","article-title":"A fair comparison of graph neural networks for graph classification","author":"errica","year":"2020","journal-title":"Proc ICLR"},{"key":"ref136","first-page":"4362","article-title":"Mean-field theory of graph neural networks in graph partitioning","author":"kawamoto","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref135","first-page":"5165","article-title":"Link prediction based on graph neural networks","author":"zhang","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref138","first-page":"690","article-title":"Graph R-CNN for scene graph generation","author":"yang","year":"2018","journal-title":"Proc ECCV"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939753"},{"key":"ref139","first-page":"346","article-title":"Factorizable net: An efficient subgraph-based framework for scene graph generation","author":"li","year":"2018","journal-title":"Proc ECCV"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/362"},{"key":"ref61","first-page":"1","article-title":"Variational graph auto-encoders","author":"kipf","year":"2016","journal-title":"Proc NIPS Workshop Bayesian Deep Learn"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220068"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220000"},{"key":"ref65","first-page":"1","article-title":"Learning deep generative models of graphs","author":"li","year":"2018","journal-title":"Proc ICML"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00133"},{"key":"ref66","first-page":"1","article-title":"GraphRNN: A deep generative model for graphs","author":"you","year":"2018","journal-title":"Proc ICML"},{"key":"ref141","first-page":"1","article-title":"Dynamic graph CNN for learning on point clouds","volume":"38","author":"wang","year":"2019","journal-title":"ACM Trans Graph"},{"key":"ref67","first-page":"412","article-title":"Graphvae: Towards generation of small graphs using variational autoencoders","author":"simonovsky","year":"2018","journal-title":"Proc ICANN"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00479"},{"key":"ref68","first-page":"7110","article-title":"Constrained generation of semantically valid graphs via regularizing variational autoencoders","author":"ma","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240621"},{"key":"ref2","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","author":"ren","year":"2015","journal-title":"Proc NIPS"},{"key":"ref69","first-page":"1","article-title":"MolGAN: An implicit generative model for small molecular graphs","author":"de cao","year":"2018","journal-title":"ICML Workshop Theor Found Appl Deep Generative Models"},{"key":"ref144","first-page":"401","article-title":"Learning human-object interactions by graph parsing neural networks","author":"qi","year":"2018","journal-title":"Proc ECCV"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.91"},{"key":"ref145","first-page":"1","article-title":"Few-shot learning with graph neural networks","author":"satorras","year":"2018","journal-title":"Proc ICLR"},{"key":"ref109","article-title":"Learning graph embedding with adversarial training methods","author":"pan","year":"2019","journal-title":"IEEE Trans Cybern"},{"key":"ref95","first-page":"2485","article-title":"Column networks for collective classification","author":"pham","year":"2017","journal-title":"Proc AAAI"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref94","article-title":"The Weisfeiler–Lehman method and graph isomorphism testing","author":"douglas","year":"2011","journal-title":"arXiv 1101 5211"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005141"},{"key":"ref93","first-page":"12","article-title":"A reduction of a graph to a canonical form and an algebra arising during this reduction","volume":"2","author":"weisfeiler","year":"1968","journal-title":"Nauchno- Technicheskaya Informatsia"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1162\/0899766053491878"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00097"},{"key":"ref91","first-page":"3189","article-title":"Learning shape correspondence with anisotropic convolutional neural networks","author":"boscaini","year":"2016","journal-title":"Proc NIPS"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/0893-6080(89)90020-8"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.112"},{"key":"ref104","first-page":"1","article-title":"Invariant and equivariant graph networks","author":"maron","year":"2019","journal-title":"ICLRE"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.08.010"},{"key":"ref102","first-page":"3734","article-title":"Self-attention graph pooling","author":"lee","year":"2019","journal-title":"Proc ICML"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1021\/acscentsci.7b00572"},{"key":"ref112","first-page":"1945","article-title":"Grammar variational autoencoder","author":"kusner","year":"2017","journal-title":"Proc ICML"},{"key":"ref110","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc NIPS"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2017.2726981"},{"key":"ref99","doi-asserted-by":"crossref","first-page":"2022","DOI":"10.1145\/3308558.3313562","article-title":"Heterogeneous graph attention network","author":"wang","year":"2019","journal-title":"Proc World Wide Web Conf (WWW)"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.11"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00113"},{"key":"ref10","first-page":"1024","article-title":"Representation learning on graphs: Methods and applications","author":"hamilton","year":"2017","journal-title":"Proc NIPS"},{"key":"ref11","article-title":"Relational inductive biases, deep learning, and graph networks","author":"battaglia","year":"2018","journal-title":"arXiv 1806 01261"},{"key":"ref12","article-title":"Attention models in graphs: A survey","author":"boaz lee","year":"2018","journal-title":"arXiv 1807 07984"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/72.572108"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1402008"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2010.5596796"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2235192"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"ref17","first-page":"1","article-title":"Gated graph sequence neural networks","author":"li","year":"2015","journal-title":"Proc ICLR"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref18","first-page":"1114","article-title":"Learning steady-states of iterative algorithms over graphs","author":"dai","year":"2018","journal-title":"Proc ICML"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2469645"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btx252"},{"key":"ref19","first-page":"1","article-title":"Spectral networks and locally connected networks on graphs","author":"bruna","year":"2014","journal-title":"Proc ICLR"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2238935"},{"key":"ref114","first-page":"593","article-title":"Modeling relational data with graph convolutional networks","author":"schlichtkrull","year":"2018","journal-title":"ESWC"},{"key":"ref113","first-page":"1","article-title":"Syntax-directed variational autoencoder for structured data","author":"dai","year":"2018","journal-title":"Proc ICLR"},{"key":"ref116","article-title":"Wasserstein GAN","author":"arjovsky","year":"2017","journal-title":"arXiv 1701 07875"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2004.837783"},{"key":"ref115","first-page":"5767","article-title":"Improved training of Wasserstein GANs","author":"gulrajani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1007\/s10115-007-0103-5"},{"key":"ref89","first-page":"9197","article-title":"Watch your step: Learning node embeddings via graph attention","author":"abu-el-haija","year":"2018","journal-title":"Proc NeurIPS"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1021\/jm00106a046"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1016\/S0022-2836(03)00628-4"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bti1007"},{"key":"ref85","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","author":"duvenaud","year":"2015","journal-title":"Proc NIPS"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-016-9938-8"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1038\/ncomms13890"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219980"}],"container-title":["IEEE Transactions on Neural Networks and Learning Systems"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/5962385\/9312808\/9046288-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5962385\/9312808\/09046288.pdf?arnumber=9046288","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,19]],"date-time":"2022-10-19T17:48:14Z","timestamp":1666201694000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9046288\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":174,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tnnls.2020.2978386","relation":{},"ISSN":["2162-237X","2162-2388"],"issn-type":[{"value":"2162-237X","type":"print"},{"value":"2162-2388","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1]]}}}