{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,24]],"date-time":"2025-08-24T01:38:56Z","timestamp":1755999536907,"version":"3.37.3"},"reference-count":42,"publisher":"IOP Publishing","issue":"1","license":[{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2020,12,1]],"date-time":"2020-12-01T00:00:00Z","timestamp":1606780800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"National Science Founation","award":["1633631"],"award-info":[{"award-number":["1633631"]}]},{"name":"National Institute of Aging","award":["AG059602"],"award-info":[{"award-number":["AG059602"]}]},{"name":"Human Frontiers Science Program","award":["HFSP - RGP0023\/2018"],"award-info":[{"award-number":["HFSP - RGP0023\/2018"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2021,3,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>We define a novel type of ensemble graph convolutional network (GCN) model. Using optimized linear projection operators to map between spatial scales of graph, this ensemble model learns to aggregate information from each scale for its final prediction. We calculate these linear projection operators as the infima of an objective function relating the structure matrices used for each GCN. Equipped with these projections, our model (a Graph Prolongation-Convolutional Network) outperforms other GCN ensemble models at predicting the potential energy of monomer subunits in a coarse-grained mechanochemical simulation of microtubule bending. We demonstrate these performance gains by measuring an estimate of the Floating Point OPerations spent to train each model, as well as wall-clock time. Because our model learns at multiple scales, it is possible to train at each scale according to a predetermined schedule of coarse vs. fine training. We examine several such schedules adapted from the algebraic multigrid literature, and quantify the computational benefit of each. We also compare this model to another model which features an optimized coarsening of the input graph. Finally, we derive backpropagation rules for the input of our network model with respect to its output, and discuss how our method may be extended to very large graphs.<\/jats:p>","DOI":"10.1088\/2632-2153\/abb6d2","type":"journal-article","created":{"date-parts":[[2020,9,9]],"date-time":"2020-09-09T22:33:59Z","timestamp":1599690839000},"page":"015009","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Graph prolongation convolutional networks: explicitly multiscale machine learning on graphs with applications to modeling of cytoskeleton"],"prefix":"10.1088","volume":"2","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5561-2368","authenticated-orcid":false,"given":"Cory B","family":"Scott","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9085-9171","authenticated-orcid":false,"given":"Eric","family":"Mjolsness","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2020,12,1]]},"reference":[{"key":"mlstabb6d2bib1","doi-asserted-by":"publisher","first-page":"265","DOI":"10.5555\/3026877.3026899","article-title":"Tensorflow: A system for large-scale machine learning","author":"Abadi","year":"2016"},{"article-title":"N-GCN: multi-scale graph convolution for semi-supervised node classification","year":"2018","author":"Abu-El-Haija","key":"mlstabb6d2bib2"},{"article-title":"A gentle introduction to deep learning for graphs","year":"2019","author":"Bacciu","key":"mlstabb6d2bib3"},{"key":"mlstabb6d2bib4","doi-asserted-by":"publisher","first-page":"443","DOI":"10.1007\/s10479-010-0757-3","article-title":"Solving the rectangular assignment problem and applications","volume":"181","author":"Bijsterbosch","year":"2010","journal-title":"Ann. Oper. Res."},{"key":"mlstabb6d2bib5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1005959","article-title":"A computational framework for cortical microtubule dynamics in realistically shaped plant cells","volume":"14","author":"Chakrabortty","year":"2018","journal-title":"PLoS Comput. Biol."},{"key":"mlstabb6d2bib6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IJCNN.2015.7280542","article-title":"Coarse-to-fine trained multi-scale convolutional neural networks for image classification","author":"Dou","year":"2015"},{"key":"mlstabb6d2bib7","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.ceb.2007.12.003","article-title":"Microtubule assembly dynamics: new insights at the nanoscale","volume":"20","author":"Gardner","year":"2008","journal-title":"Curr. Opin. Cell Biol."},{"key":"mlstabb6d2bib8","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.ceb.2012.09.006","article-title":"Microtubule catastrophe and rescue","volume":"25","author":"Gardner","year":"2013","journal-title":"Curr. Opin. Cell Biol."},{"key":"mlstabb6d2bib9","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.11680","article-title":"Learning across scales - multiscale methods for convolution neural networks","author":"Haber","year":"2018"},{"article-title":"Lapsolver: fast linear assignment problem (LAP) solvers for python based on c-extensions","year":"2018","author":"Heindl","key":"mlstabb6d2bib10"},{"key":"mlstabb6d2bib11","doi-asserted-by":"publisher","first-page":"169a","DOI":"10.1016\/j.bpj.2012.11.953","article-title":"Moltemplate: A coarse-grained model assembly tool","volume":"104","author":"Jewett","year":"2013","journal-title":"Biophys. J."},{"key":"mlstabb6d2bib12","doi-asserted-by":"publisher","first-page":"6665","DOI":"10.1109\/CVPR.2017.433","article-title":"Multigrid neural architectures","author":"Ke","year":"2017"},{"key":"mlstabb6d2bib13","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.1529\/biophysj.104.055483","article-title":"Flexural rigidity of individual microtubules measured by a buckling force with optical traps","volume":"90","author":"Kikumoto","year":"2006","journal-title":"Biophys. J."},{"article-title":"Semi-supervised classification with graph convolutional networks","year":"2016","author":"Kipf","key":"mlstabb6d2bib14"},{"key":"mlstabb6d2bib15","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevLett.89.248101","article-title":"Nanomechanics of microtubules","volume":"89","author":"Kis","year":"2002","journal-title":"Phys. Rev. Lett."},{"key":"mlstabb6d2bib16","article-title":"LanczosNet: multi-scale deep graph convolutional networks","author":"Liao","year":"2019","journal-title":"arXiv:1901.01484"},{"volume":"vol 60","year":"2012","author":"Lov\u00e1sz","key":"mlstabb6d2bib17"},{"key":"mlstabb6d2bib18","doi-asserted-by":"publisher","first-page":"642","DOI":"10.1091\/mbc.e11-08-0688","article-title":"The mechanisms of microtubule catastrophe and rescue: implications from analysis of a dimer-scale computational model","volume":"23","author":"Margolin","year":"2012","journal-title":"Mol. Biol. Cell"},{"key":"mlstabb6d2bib19","doi-asserted-by":"publisher","first-page":"3167","DOI":"10.1529\/biophysj.104.051789","article-title":"A molecular-mechanical model of the microtubule","volume":"88","author":"Molodtsov","year":"2005","journal-title":"Biophys. J."},{"key":"mlstabb6d2bib20","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1016\/j.tibtech.2008.03.002","article-title":"Microtubule architecture: inspiration for novel carbon nanotube-based biomimetic materials","volume":"26","author":"Pampaloni","year":"2008","journal-title":"Trends Biotechnol."},{"key":"mlstabb6d2bib21","article-title":"Fast parallel algorithms for short-range molecular dynamics","author":"Plimpton","year":"1993","journal-title":"Technical Report"},{"key":"mlstabb6d2bib22","first-page":"p 297","article-title":"Robustness of coupled algebraic multigrid for the Navier-Stokes equations","author":"Raw","year":"1996"},{"key":"mlstabb6d2bib23","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","article-title":"U-net: convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"mlstabb6d2bib24","doi-asserted-by":"publisher","first-page":"1302","DOI":"10.1103\/PhysRevB.17.1302","article-title":"Molecular-dynamics study of a three-dimensional one-component model for distortive phase transitions","volume":"17","author":"Schneider","year":"1978","journal-title":"Phys. Rev. B"},{"article-title":"Novel diffusion-derived distance measures for graphs","year":"2019b","author":"Scott","key":"mlstabb6d2bib25"},{"key":"mlstabb6d2bib26","doi-asserted-by":"publisher","first-page":"S297\u2013S320","DOI":"10.1137\/18M1191506","article-title":"Multilevel artificial neural network training for spatially correlated learning","volume":"41","author":"Scott","year":"2019a","journal-title":"SIAM J. Sci. Comput."},{"key":"mlstabb6d2bib27","doi-asserted-by":"publisher","first-page":"1715","DOI":"10.1126\/science.1083529","article-title":"Sustained microtubule treadmilling in arabidopsis cortical arrays","volume":"300","author":"Shaw","year":"2003","journal-title":"Science"},{"key":"mlstabb6d2bib28","doi-asserted-by":"publisher","DOI":"10.1101\/291682","article-title":"A structural mechano-chemical model for dynamic instability of microtubule","author":"Stewman","year":"2018","journal-title":"BioRxiv"},{"key":"mlstabb6d2bib29","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1016\/S0377-0427(00)00516-1","article-title":"A review of algebraic multigrid","author":"St\u00fcben","year":"2001"},{"key":"mlstabb6d2bib30","doi-asserted-by":"publisher","DOI":"10.1088\/0965-0393\/18\/1\/015012","article-title":"Visualization and analysis of atomistic simulation data with OVITO \u2013 the open visualization tool","volume":"18","author":"Stukowski","year":"2010","journal-title":"Model. Simul. Mater. Sci. Eng."},{"key":"mlstabb6d2bib31","doi-asserted-by":"crossref","first-page":"3015","DOI":"10.1143\/JJAP.41.3015","article-title":"Flexural rigidity of a single microtubule","volume":"41","author":"Takasone","year":"2002","journal-title":"Japan. J. Appl. Phys."},{"key":"mlstabb6d2bib32","first-page":"42","article-title":"GNU parallel - the command-line power tool","volume":"36","author":"Tange","year":"2011","journal-title":";login: The USENIX Magazine"},{"key":"mlstabb6d2bib33","doi-asserted-by":"publisher","first-page":"19","DOI":"10.3389\/fphy.2014.00019","article-title":"Efficient event-driven simulations shed new light on microtubule organization in the plant cortical array","volume":"2","author":"Tindemans","year":"2014","journal-title":"Front. Phys."},{"key":"mlstabb6d2bib34","first-page":"4755","article-title":"Pymanopt: A python toolbox for optimization on manifolds using automatic differentiation","volume":"17","author":"Townsend","year":"2016"},{"key":"mlstabb6d2bib35","doi-asserted-by":"publisher","first-page":"2911","DOI":"10.1529\/biophysj.105.060913","article-title":"Mechanochemical model of microtubule structure and self-assembly kinetics","volume":"89","author":"VanBuren","year":"2005","journal-title":"Biophys. J."},{"key":"mlstabb6d2bib36","doi-asserted-by":"publisher","first-page":"179","DOI":"10.1007\/BF02238511","article-title":"Algebraic multigrid by smoothed aggregation for second and fourth order elliptic problems","volume":"56","author":"Van\u011bk","year":"1996","journal-title":"Computing"},{"key":"mlstabb6d2bib37","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1103\/PhysRev.159.98","article-title":"Computer \u2018experiments\u2019 on classical fluids. i. thermodynamical properties of Lennard-Jones molecules","volume":"159","author":"Verlet","year":"1967","journal-title":"Phys. Rev."},{"key":"mlstabb6d2bib38","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1038\/nature03606","article-title":"Nucleotide-dependent bending flexibility of tubulin regulates microtubule assembly","volume":"435","author":"Wang","year":"2005","journal-title":"Nature"},{"key":"mlstabb6d2bib39","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/S0377-0427(00)00517-3","article-title":"Geometric multigrid with applications to computational fluid dynamics","volume":"128","author":"Wesseling","year":"2001","journal-title":"J. Comput. Appl. Math."},{"key":"mlstabb6d2bib40","doi-asserted-by":"publisher","first-page":"4800","DOI":"10.5555\/3327345.3327389","article-title":"Hierarchical graph representation learning with differentiable pooling","author":"Ying","year":"2018","journal-title":"Adv. Neural Information Process. Systems"},{"year":"2018","author":"Zhang","key":"mlstabb6d2bib41"},{"key":"mlstabb6d2bib42","first-page":"51","article-title":"PGU-net+: progressive growing of U-net+ for automated cervical nuclei segmentation","author":"Zhao","year":"2019","journal-title":"Lecture Notes Computer Sci."}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d2","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d2\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d2\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d2\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d2","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d2\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d2\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d2\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d2\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d2\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d2","content-type":"text\/html","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,17]],"date-time":"2022-11-17T14:28:10Z","timestamp":1668695290000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/abb6d2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,1]]},"references-count":42,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2020,12,1]]},"published-print":{"date-parts":[[2021,3,1]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/abb6d2","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2020,12,1]]},"assertion":[{"value":"Graph prolongation convolutional networks: explicitly multiscale machine learning on graphs with applications to modeling of cytoskeleton","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2020 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2020-03-20","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-09-09","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2020-12-01","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}