{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:39:14Z","timestamp":1779381554222,"version":"3.53.1"},"reference-count":83,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,2,1]],"date-time":"2023-02-01T00:00:00Z","timestamp":1675209600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"TUM-ICL incentive funding"},{"name":"Freunde und Förderer der Augenklinik, München, Germany"},{"name":"ERC","award":["724228"],"award-info":[{"award-number":["724228"]}]},{"name":"German Federal Ministry of Education and Health"},{"DOI":"10.13039\/501100019776","name":"Deutschen Schwindel- und Gleichgewichtszentrum","doi-asserted-by":"publisher","award":["01 EO0901"],"award-info":[{"award-number":["01 EO0901"]}],"id":[{"id":"10.13039\/501100019776","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,2,1]]},"DOI":"10.1109\/tpami.2022.3170249","type":"journal-article","created":{"date-parts":[[2022,4,26]],"date-time":"2022-04-26T19:37:49Z","timestamp":1651001869000},"page":"1606-1617","source":"Crossref","is-referenced-by-count":88,"title":["Differentiable Graph Module (DGM) for Graph Convolutional Networks"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4528-1670","authenticated-orcid":false,"given":"Anees","family":"Kazi","sequence":"first","affiliation":[{"name":"Department of Computer Aided Medical Procedures and Augmented Reality, Technical University of Munich, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7729-4666","authenticated-orcid":false,"given":"Luca","family":"Cosmo","sequence":"additional","affiliation":[{"name":"Ca’ Foscari University of Venice, Venezia, VE, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7082-0739","authenticated-orcid":false,"given":"Seyed-Ahmad","family":"Ahmadi","sequence":"additional","affiliation":[{"name":"NVIDIA, Munich, W\u00fcrselen, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6032-5611","authenticated-orcid":false,"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[{"name":"Department of Computer Aided Medical Procedures and Augmented Reality, Technical University of Munich, München, Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Michael M.","family":"Bronstein","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Oxford, Oxford, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.06.001"},{"key":"ref57","first-page":"1972","article-title":"Learning discrete structures for graph neural networks","author":"franceschi","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","article-title":"Learning deep generative models of graphs","author":"li","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01157"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2019.8759193"},{"key":"ref59","first-page":"4805","article-title":"Hierarchical graph representation learning with differentiable pooling","author":"ying","year":"2018","journal-title":"Proc Adv Neural Informat Process Syst"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66179-7_21"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00344"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2815012"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/SSCI.2018.8628758"},{"key":"ref11","first-page":"1263","article-title":"Neural message passing for quantum chemistry","author":"gilmer","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref55","first-page":"4558","article-title":"Adaptive sampling towards fast graph representation learning","author":"huang","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref10","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","author":"duvenaud","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11691"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/bty294"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20351-1_6"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1038\/s41592-019-0666-6"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2018.09.012"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014424"},{"key":"ref50","article-title":"Watch your step: Learning node embeddings via graph attention","author":"abu-el-haija","year":"2017"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2887284"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-59713-9_62"},{"key":"ref48","article-title":"Gaan: Gated attention networks for learning on large and spatiotemporal graphs","author":"zhang","year":"2018"},{"key":"ref47","article-title":"Neural relational inference for interacting systems","author":"kipf","year":"2018"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2012.2197809"},{"key":"ref41","article-title":"What graph neural networks cannot learn: Depth versus width","author":"loukas","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2890143"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2018.2887284"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219980"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.576"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICMLA.2018.00064"},{"key":"ref4","first-page":"5171","article-title":"Link prediction based on graph neural networks","author":"zhang","year":"2018","journal-title":"Proc 32nd Int Conf Neural Inf Process Syst"},{"key":"ref3","article-title":"Relational inductive biases, deep learning, and graph networks","author":"battaglia","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.556"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_25"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00717"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref40","first-page":"7090","article-title":"Universal invariant and equivariant graph neural networks","author":"keriven","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref83","article-title":"Brain signal classification via learning connectivity structure","author":"jang","year":"2019","journal-title":"CoRR"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref35","article-title":"PairNorm: Tackling oversmoothing in GNNs","author":"zhao","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref34","article-title":"DropEdge: Towards deep graph convolutional networks on node classification","author":"rong","year":"2019"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01175"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01143"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00936"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32251-9_14"},{"key":"ref30","first-page":"1025","article-title":"Inductive representation learning on large graphs","author":"hamilton","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2019.8759274"},{"key":"ref33","article-title":"GraphSAINT: Graph sampling based inductive learning method","author":"zeng","year":"2019"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2857768"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"key":"ref2","article-title":"Representation learning on graphs: Methods and applications","author":"hamilton","year":"2017"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"ref39","article-title":"Invariant and equivariant graph networks","author":"maron","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref38","article-title":"How powerful are graph neural networks?","author":"xu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.24899"},{"key":"ref70","article-title":"Kernel operations on the gpu, with autodiff, without memory overflows","author":"charlier","year":"2020"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4393"},{"key":"ref72","article-title":"Tadpole challenge: Prediction of longitudinal evolution in alzheimer's disease","author":"marinescu","year":"2018"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2879624"},{"key":"ref68","article-title":"Hyperbolic graph convolutional neural networks","volume":"32","author":"chami","year":"2019","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref23","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2016"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1214\/19-STS702"},{"key":"ref26","article-title":"Graph attention networks","author":"veli?kovi?","year":"2017"},{"key":"ref25","article-title":"Graph neural networks with convolutional ARMA filters","author":"bianchi","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/BF02419615"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.2008.2005605"},{"key":"ref64","first-page":"6338","article-title":"Poincaré embeddings for learning hierarchical representations","author":"nickel","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.82.036106"},{"key":"ref22","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","author":"defferrard","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1609\/aimag.v29i3.2157"},{"key":"ref21","article-title":"Spectral networks and locally connected networks on graphs","author":"bruna","year":"2013"},{"key":"ref65","article-title":"Stochastic beams and where to find them: The gumbel-top-k trick for sampling sequences without replacement","author":"kool","year":"2019","journal-title":"CoRR"},{"key":"ref28","article-title":"Community detection with graph neural networks","volume":"1050","author":"bruna","year":"2017","journal-title":"Statistics"},{"key":"ref27","article-title":"N-body networks: A covariant hierarchical neural network architecture for learning atomic potentials","author":"kondor","year":"2018"},{"key":"ref29","article-title":"Dual-primal graph convolutional networks","author":"monti","year":"2018"},{"key":"ref60","article-title":"Learning conditioned graph structures for interpretable visual question answering","author":"chen","year":"2018"},{"key":"ref62","article-title":"Graph kernel neural networks","author":"cosmo","year":"2021"},{"key":"ref61","first-page":"19 314","article-title":"Iterative deep graph learning for graph neural networks:better and robust node embeddings","author":"chen","year":"2020","journal-title":"Proc 34th Int Conf Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10008914\/09763421.pdf?arnumber=9763421","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,30]],"date-time":"2023-01-30T19:43:44Z","timestamp":1675107824000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9763421\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,1]]},"references-count":83,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3170249","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,1]]}}}