{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T06:33:30Z","timestamp":1782887610554,"version":"3.54.5"},"reference-count":106,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100014462","name":"Mitsubishi Electric Research Laboratories","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100014462","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","award":["CCF-2006738"],"award-info":[{"award-number":["CCF-2006738"]}],"id":[{"id":"10.13039\/501100008982","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":[[2023,6,1]]},"DOI":"10.1109\/tpami.2021.3083614","type":"journal-article","created":{"date-parts":[[2021,5,25]],"date-time":"2021-05-25T20:04:47Z","timestamp":1621973087000},"page":"6909-6922","source":"Crossref","is-referenced-by-count":7,"title":["Revisiting 2D Convolutional Neural Networks for Graph-Based Applications"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3077-8214","authenticated-orcid":false,"given":"Yecheng","family":"Lyu","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0584-3448","authenticated-orcid":false,"given":"Xinming","family":"Huang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, Worcester Polytechnic Institute, Worcester, MA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref57","article-title":"Learning deep generative models of graphs","author":"li","year":"2018"},{"key":"ref56","first-page":"2434","article-title":"Graphite: Iterative generative modeling of graphs","volume":"97","author":"grover","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33011110"},{"key":"ref58","first-page":"5708","article-title":"GraphRNN: Generating realistic graphs with deep auto-regressive models","author":"you","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1201\/b15385"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/FOCS.2007.56"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-24651-0_12"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2319"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.camwa.2004.08.015"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-44969-8_6"},{"key":"ref46","first-page":"52","article-title":"Representation learning on graphs: Methods and applications","volume":"40","author":"hamilton","year":"2017","journal-title":"IEEE Data Eng Bull"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2007.70580"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2807452"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2018.2849727"},{"key":"ref42","first-page":"138","article-title":"Embedding planar graphs on the grid","author":"schnyder","year":"1990","journal-title":"Proc 1st Annu ACM-SIAM Symp Discrete Algorithms"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(95)00020-D"},{"key":"ref44","article-title":"Force-directed drawing algorithms","author":"kobourov","year":"2013","journal-title":"Handbook of Graph Drawing and Visualization"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/0020-0190(89)90102-6"},{"key":"ref49","first-page":"92","article-title":"Circular layout in the graph layout toolkit","author":"do?rus\u00f6z","year":"1996","journal-title":"Proc Int Symp Graph Drawing"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2978386"},{"key":"ref7","first-page":"6861","article-title":"Simplifying graph convolutional networks","author":"wu","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014602"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2017.2693418"},{"key":"ref3","first-page":"1024","article-title":"Inductive representation learning on large graphs","author":"hamilton","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref6","first-page":"2083","article-title":"Graph U-nets","author":"gao","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref5","first-page":"1","article-title":"FastGCN: Fast learning with graph convolutional networks via importance sampling","author":"chen","year":"2018","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref100","author":"kingma","year":"2015"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","first-page":"2990","article-title":"The multiscale laplacian graph kernel","author":"kondor","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313461"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2999032"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412808"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57321-8_26"},{"key":"ref30","article-title":"SPI-GCN: A simple permutation-invariant graph convolutional network","author":"atamna","year":"2019"},{"key":"ref33","article-title":"Wasserstein weisfeiler-lehman graph kernels","author":"togninalli","year":"2019","journal-title":"Proc 33rd Conf Neural Inf Process Syst"},{"key":"ref32","article-title":"Graph capsule convolutional neural networks","author":"verma","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i03.5673"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330982"},{"key":"ref23","article-title":"Learning metrics for persistence-based summaries and applications for graph classification","author":"zhao","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref26","article-title":"Graph kernels based on linear patterns: Theoretical and experimental comparisons","author":"jia","year":"2019"},{"key":"ref25","article-title":"Spectral multigraph networks for discovering and fusing relationships in molecules","author":"knyazev","year":"2018","journal-title":"Proc 32nd Conf Neural Inf Process Syst Workshops"},{"key":"ref20","first-page":"1","article-title":"Capsule graph neural network","author":"xinyi","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICBK.2018.00033"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2018.11.002"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-015-5517-9"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783417"},{"key":"ref29","first-page":"1623","article-title":"On valid optimal assignment kernels and applications to graph classification","author":"kriege","year":"2016","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref13","first-page":"2014","article-title":"Learning convolutional neural networks for graphs","author":"niepert","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2957755"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330897"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3308558.3313668"},{"key":"ref97","year":"2014"},{"key":"ref96","author":"bradley","year":"1977","journal-title":"Applied Mathematical Programming"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33014007"},{"key":"ref99","first-page":"1319","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref10","article-title":"When work matters: Transforming classical network structures to graph CNN","author":"zhao","year":"2018"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1145\/345513.345353"},{"key":"ref17","first-page":"2186","article-title":"Anonymous walk embeddings","author":"ivanov","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","article-title":"How powerful are graph neural networks?","author":"xu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30493-5_54"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2019.8851698"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref92","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref95","author":"wolsey","year":"2014","journal-title":"Integer and Combinatorial Optimization"},{"key":"ref94","author":"zisserman","year":"2018","journal-title":"Self-Supervised Learning"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01227"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00166"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00054"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00275"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.99"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1145\/3326362"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00478"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00169"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00760"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00268"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00534"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00986"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00985"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00910"},{"key":"ref106","article-title":"Segmentation models","author":"yakubovskiy","year":"2019"},{"key":"ref75","first-page":"820","article-title":"PointCNN: Convolution on x-transformed points","author":"li","year":"2018","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref104","first-page":"1","article-title":"Sur la sphere vide","volume":"7","author":"delaunay","year":"1934","journal-title":"Izvestia Akademii Nauk SSSR Otdelenie Matematicheskikh i Estestvennykh Nauk"},{"key":"ref74","first-page":"5099","article-title":"PointNet++: Deep hierarchical feature learning on point sets in a metric space","author":"qi","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref105","first-page":"1106","article-title":"Complexity of delaunay triangulation for points on lower-dimensional˜polyhedra","author":"amenta","year":"2007","journal-title":"Proc 18th ACM-SIAM Symp Discrete Algorithms"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00979"},{"key":"ref102","article-title":"A hierarchical singular value decomposition algorithm for low rank matrices","author":"vasudevan","year":"2017","journal-title":"CoRR"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_6"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2980238"},{"key":"ref2","article-title":"Semi-supervised classification with graph convolutional networks","author":"kipf","year":"2017","journal-title":"Proc 5th Int Conf Learn Representations"},{"key":"ref1","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":"ref71","article-title":"Linked dynamic graph CNN: Learning on point cloud via linking hierarchical features","author":"zhang","year":"2019"},{"key":"ref70","first-page":"1","article-title":"Efficient graph classification via graph encoding networks","author":"ho","year":"2020","journal-title":"Proc RIVF Int Conf Comput Commun Technol"},{"key":"ref73","first-page":"652","article-title":"PointNet: Deep learning on point sets for 3D classification and segmentation","author":"qi","year":"2017","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240621"},{"key":"ref68","article-title":"Deep learning on graphs: A survey","author":"zhang","year":"2020","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.697"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00039"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.112"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11725"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2018.2879624"},{"key":"ref65","first-page":"3189","article-title":"Learning shape correspondence with anisotropic convolutional neural networks","author":"boscaini","year":"2016","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2934396"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.576"},{"key":"ref61","first-page":"1972","article-title":"Learning discrete structures for graph neural networks","author":"franceschi","year":"2019","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/10120646\/9440667-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09440667.pdf?arnumber=9440667","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,29]],"date-time":"2023-05-29T17:36:11Z","timestamp":1685381771000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9440667\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":106,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3083614","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":[[2023,6,1]]}}}