{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T08:28:15Z","timestamp":1785572895057,"version":"3.56.0"},"reference-count":170,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Program on Key Basic Research Project","award":["2015CB352300"],"award-info":[{"award-number":["2015CB352300"]}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018AAA0102004"],"award-info":[{"award-number":["2018AAA0102004"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1936219"],"award-info":[{"award-number":["U1936219"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1611461"],"award-info":[{"award-number":["U1611461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61772304"],"award-info":[{"award-number":["61772304"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Academy of Artificial Intelligence"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2022,1,1]]},"DOI":"10.1109\/tkde.2020.2981333","type":"journal-article","created":{"date-parts":[[2020,3,17]],"date-time":"2020-03-17T21:31:12Z","timestamp":1584480672000},"page":"249-270","source":"Crossref","is-referenced-by-count":1111,"title":["Deep Learning on Graphs: A Survey"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2451-843X","authenticated-orcid":false,"given":"Ziwei","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2957-8511","authenticated-orcid":false,"given":"Peng","family":"Cui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2236-9290","authenticated-orcid":false,"given":"Wenwu","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/Nature14539"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"ref3","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Advances Neural Inf. Processi. Syst.","author":"Krizhevsky"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref5","volume-title":"Network Science","author":"Barabasi","year":"2016"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2235192"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939825"},{"key":"ref9","article-title":"Relational inductive biases, deep learning, and graph networks","author":"Battaglia","year":"2018"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3363574"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1186\/s40649-019-0069-y"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3201243"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2021.01.001"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.250598"},{"key":"ref16","article-title":"Representation learning on graphs: Methods and applications","author":"Hamilton","year":"2017"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2849727"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"ref19","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref20","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Machi. Learn. Res."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10488"},{"key":"ref22","first-page":"539","article-title":"Learning to discover social circles in ego networks","volume-title":"Proc. 25th Int. Conf. Neural Inf. Process. Syst.","author":"Leskovec"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref24","article-title":"Gated graph sequence neural networks","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Li"},{"key":"ref25","first-page":"1106","article-title":"Learning steady-states of iterative algorithms over graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dai"},{"key":"ref26","first-page":"5694","article-title":"Graphrnn: Generating realistic graphs with deep auto-regressive models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"You"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401092"},{"key":"ref28","first-page":"3700","article-title":"Geometric matrix completion with recurrent multi-graph neural networks","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Monti"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107000"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1179"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2005.1555942"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/72.712151"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1093\/comjnl\/7.2.155"},{"key":"ref35","first-page":"102","article-title":"A learning rule for asynchronous perceptrons with feedback in a combinatorial environment","volume-title":"Proc. 1st Int. Conf. Neural Netw.","author":"Almeida"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.59.2229"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1002\/9781118033074"},{"key":"ref38","article-title":"Learning to decipher the heap for program verification","volume-title":"Proc. Workshop Constructive Mach. Learn. Int. Conf. Mach. Learn.","author":"Brockschmidt"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3097997"},{"key":"ref40","article-title":"Spectral networks and locally connected networks on graphs","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Bruna"},{"key":"ref41","article-title":"Deep convolutional networks on graph-structured data","author":"Henaff","year":"2015"},{"key":"ref42","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Defferrard"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18178\/wcse.2019.06.016"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2879624"},{"key":"ref45","article-title":"Graph wavelet neural network","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref46","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Duvenaud"},{"key":"ref47","first-page":"2014","article-title":"Learning convolutional neural networks for graphs","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Niepert"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219947"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"ref50","first-page":"2001","article-title":"Diffusion-convolutional neural networks","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Atwood"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3178876.3186116"},{"key":"ref52","first-page":"1263","article-title":"Neural message passing for quantum chemistry","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Gilmer"},{"key":"ref53","first-page":"1025","article-title":"Inductive representation learning on large graphs","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Hamilton"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.576"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s10822-016-9938-8"},{"key":"ref56","first-page":"4805","article-title":"Hierarchical graph representation learning with differentiable pooling","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref57","article-title":"Graph attention networks","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Velickovic"},{"key":"ref58","article-title":"Gaan: Gated attention networks for learning on large and spatiotemporal graphs","volume-title":"Proc. 34th Conf. Uncertainty Artif. Intell.","author":"Zhang"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313562"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10851"},{"key":"ref61","article-title":"Predict then propagate: Graph neural networks meet personalized pagerank","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Klicpera"},{"key":"ref62","first-page":"5453","article-title":"Representation learning on graphs with jumping knowledge networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.11"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref65","article-title":"Supervised community detection with line graph neural networks","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref67","first-page":"942","article-title":"Stochastic training of graph convolutional networks with variance reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref68","article-title":"FastGCN: Fast learning with graph convolutional networks via importance sampling","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref69","first-page":"4563","article-title":"Adaptive sampling towards fast graph representation learning","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"ref71","first-page":"6861","article-title":"Simplifying graph convolutional networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wu"},{"key":"ref72","article-title":"Revisiting graph neural networks: All we have is low-pass filters","author":"Maehara","year":"2019"},{"key":"ref73","article-title":"How powerful are graph neural networks?","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Xu"},{"key":"ref74","article-title":"Deep graph infomax","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Veli\u010dkovi\u0107"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1120.003.0080"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1016\/j.acha.2010.04.005"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219969"},{"key":"ref78","first-page":"539","article-title":"Weisfeiler-lehman graph kernels","volume":"12","author":"Shervashidze","year":"2011","journal-title":"J. Mach. Learn. Res."},{"key":"ref79","first-page":"2177","article-title":"Neural word embedding as implicit matrix factorization","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Levy"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/2897518.2897542"},{"key":"ref81","volume-title":"Fuzzy sets and fuzzy logic","author":"Klir","year":"1995"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220062"},{"key":"ref83","first-page":"1309","article-title":"The elements of statistical learning: Data mining, inference, and prediction","volume":"66","author":"Ruppert","year":"2010","journal-title":"J. Royal Statist. Soc."},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/s11222-007-9033-z"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1115"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2015.2512529"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1016\/j.jsc.2013.09.003"},{"key":"ref88","article-title":"Order matters: Sequence to sequence for sets","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Vinyals"},{"key":"ref89","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Vaswani"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1126\/science.286.5439.509"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11271"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2018.08.010"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330956"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v28i1.8916"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939753"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v30i1.10179"},{"key":"ref99","article-title":"Graph convolutional matrix completion","volume-title":"Proc. Int. Conf. Knowl. Discovery Data Mining","author":"Berg"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220068"},{"key":"ref101","article-title":"Deep gaussian embedding of graphs: Unsupervised inductive learning via ranking","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Bojchevski"},{"key":"ref102","article-title":"Variational graph auto-encoders","volume-title":"Proc. NIPS Workshop Bayesian Deep Learn.","author":"Kipf"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220052"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/362"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220000"},{"key":"ref106","first-page":"281","article-title":"Some methods for classification and analysis of multivariate observations","volume-title":"Proc. 5th Berkeley Symp. Math. Statist. Probability","author":"MacQueen"},{"key":"ref107","article-title":"A note on spectral clustering and SVD of graph data","author":"Zhang","year":"2018"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741093"},{"key":"ref109","first-page":"1","article-title":"Random walks on graphs: A survey","volume":"2","author":"Lov\u00e1sz","year":"1993","journal-title":"Combinatorics"},{"key":"ref110","article-title":"The pagerank citation ranking: Bringing order to the Web","author":"Page","year":"1999"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref112","article-title":"A tutorial on energy-based learning","author":"LeCun","year":"2006","journal-title":"Predicting Structured Data"},{"key":"ref113","article-title":"Auto-encoding variational bayes","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1137\/1118101"},{"key":"ref115","first-page":"2672","article-title":"Generative adversarial nets","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Goodfellow"},{"key":"ref116","first-page":"6412","article-title":"Graph convolutional policy network for goal-directed molecular graph generation","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"You"},{"key":"ref117","article-title":"MolGAN: An implicit generative model for small molecular graphs","volume-title":"Proc. Workshop Theor. Foundations Appl. Deep Generative Models","author":"De Cao and"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330958"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219980"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1060"},{"key":"ref121","article-title":"Go for a walk and arrive at the answer: Reasoning over paths in knowledge bases using reinforcement learning","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Das"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1038\/nature24270"},{"key":"ref123","first-page":"1057","article-title":"Policy gradient methods for reinforcement learning with function approximation","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Sutton"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11872"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11865"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1145\/3269206.3271768"},{"key":"ref127","first-page":"610","article-title":"Netgan: Generating graphs via random walks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bojchevski"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220078"},{"key":"ref129","first-page":"1115","article-title":"Adversarial attack on graph structured data","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Dai"},{"key":"ref130","article-title":"Adversarial attacks on graph neural networks via meta learning","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"Z\u00fcgner"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/2623330.2623732"},{"key":"ref132","first-page":"2702","article-title":"Discriminative embeddings of latent variable models for structured data","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Dai"},{"key":"ref133","first-page":"2110","article-title":"DeepInf: Modeling influence locality in large social networks","volume-title":"Proc. 24th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining","author":"Qiu"},{"key":"ref134","first-page":"5711","article-title":"Learning disentangled representations for recommendation","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Ma"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1021\/acs.jcim.6b00601"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.120.145301"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66182-7_54"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty294"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66179-7_21"},{"key":"ref140","article-title":"Towards gene expression convolutions using gene interaction graphs","volume-title":"Proc. Int. Conf. Mach. Learn. Workshop Comput. Biol.","author":"Dutil"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1209"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1159"},{"key":"ref143","article-title":"Few-shot learning with graph neural networks","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Garcia"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.573"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.556"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.10"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/505"},{"key":"ref149","article-title":"Diffusion convolutional recurrent neural network: Data-driven traffic forecasting","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Li"},{"key":"ref150","article-title":"Learning to represent programs with graphs","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Allamanis"},{"key":"ref151","first-page":"537","article-title":"Combinatorial optimization with graph convolutional networks and guided tree search","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014731"},{"key":"ref153","first-page":"2252","article-title":"Learning multiagent communication with backpropagation","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Sukhbaatar"},{"key":"ref154","first-page":"4509","article-title":"Interaction networks for learning about objects, relations and physics","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Battaglia"},{"key":"ref155","first-page":"2698","article-title":"Vain: Attentional multi-agent predictive modeling","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Hoshen"},{"key":"ref156","first-page":"4974","article-title":"A simple neural network module for relational reasoning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Santoro"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783296"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00113"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11266"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330848"},{"key":"ref161","first-page":"9244","article-title":"GNN explainer: A tool for post-hoc explanation of graph neural networks","volume-title":"Proc. Advances Neural Inf. Process. Syst.","author":"Ying"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330851"},{"key":"ref163","article-title":"Power up! robust graph convolutional network against evasion attacks based on graph powering","author":"Jin","year":"2019"},{"key":"ref164","article-title":"Fast graph representation learning with PyTorch Geometric","volume-title":"Proc. ICLR Workshop Representation Learn. Graphs Manifolds","author":"Fey"},{"key":"ref165","article-title":"Deep graph library: Towards efficient and scalable deep learning on graphs","volume-title":"Proc. ICLR Workshop Representation Learn. Graphs Manifolds","author":"Wang"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.14778\/3352063.3352127"},{"key":"ref167","article-title":"Pitfalls of graph neural network evaluation","volume-title":"Proc. Relational Representation Learn. Workshop","author":"Shchur"},{"key":"ref168","article-title":"Learning deep generative models of graphs","author":"Li","year":"2018"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2018.2820126"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/9639435\/09039675.pdf?arnumber=9039675","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,9]],"date-time":"2024-01-09T22:25:54Z","timestamp":1704839154000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9039675\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,1]]},"references-count":170,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2020.2981333","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,1,1]]}}}