Multiresolution equivariant graph variational autoencoder
In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each resolution level, MGVAE employs higher order message passing to encode the graph whi...
Uloženo v:
| Vydáno v: | Machine learning: science and technology Ročník 4; číslo 1; s. 15031 - 15054 |
|---|---|
| Hlavní autoři: | , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Bristol
IOP Publishing
01.03.2023
|
| Témata: | |
| ISSN: | 2632-2153, 2632-2153 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | In this paper, we propose
Multiresolution Equivariant Graph Variational Autoencoders
(MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each resolution level, MGVAE employs higher order message passing to encode the graph while learning to partition it into mutually exclusive clusters and coarsening into a lower resolution that eventually creates a hierarchy of latent distributions. MGVAE then constructs a hierarchical generative model to variationally decode into a hierarchy of coarsened graphs. Importantly, our proposed framework is end-to-end permutation equivariant with respect to node ordering. MGVAE achieves competitive results with several generative tasks including general graph generation, molecular generation, unsupervised molecular representation learning to predict molecular properties, link prediction on citation graphs, and graph-based image generation. Our implementation is available at
https://github.com/HyTruongSon/MGVAE
. |
|---|---|
| AbstractList | In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each resolution level, MGVAE employs higher order message passing to encode the graph while learning to partition it into mutually exclusive clusters and coarsening into a lower resolution that eventually creates a hierarchy of latent distributions. MGVAE then constructs a hierarchical generative model to variationally decode into a hierarchy of coarsened graphs. Importantly, our proposed framework is end-to-end permutation equivariant with respect to node ordering. MGVAE achieves competitive results with several generative tasks including general graph generation, molecular generation, unsupervised molecular representation learning to predict molecular properties, link prediction on citation graphs, and graph-based image generation. Our implementation is available at https://github.com/HyTruongSon/MGVAE . In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate graphs in a multiresolution and equivariant manner. At each resolution level, MGVAE employs higher order message passing to encode the graph while learning to partition it into mutually exclusive clusters and coarsening into a lower resolution that eventually creates a hierarchy of latent distributions. MGVAE then constructs a hierarchical generative model to variationally decode into a hierarchy of coarsened graphs. Importantly, our proposed framework is end-to-end permutation equivariant with respect to node ordering. MGVAE achieves competitive results with several generative tasks including general graph generation, molecular generation, unsupervised molecular representation learning to predict molecular properties, link prediction on citation graphs, and graph-based image generation. Our implementation is available at https://github.com/HyTruongSon/MGVAE . |
| Author | Kondor, Risi Hy, Truong Son |
| Author_xml | – sequence: 1 givenname: Truong Son orcidid: 0000-0002-5092-3757 surname: Hy fullname: Hy, Truong Son organization: University of Chicago Department of Computer Science, Chicago, IL 60637, United States of America – sequence: 2 givenname: Risi surname: Kondor fullname: Kondor, Risi |
| BookMark | eNp9kElPwzAUhC1UJErpnWMkroQ-L3GSI6rYpCIucLa8pbgKces4SPx7koZNSHCy_Twzmvcdo0njG4vQKYYLDEWxIJySlOCMLqTWYIoDNP0aTX7cj9C8bTcAQDJMMwJTVN53dXTBtr7uovNNYnede5XBySYm6yC3z8n-NfzJOpFd9LbR3thwgg4rWbd2_nHO0NP11ePyNl093NwtL1epZpjHVCmQoLSyOWUq4xnVBCyrCpUzVpWlZdqUrK_GsaI8M2VBgShcKSBAbW4rOkN3Y67xciO2wb3I8Ca8dGI_8GEtZIhO11ZYLIFSSyXjmpmKK0XyPs1UlBnFAfqsszFrG_yus20UG9-FfrFWkLwoSZ5zTnoVH1U6-LYNthLaxT2BGKSrBQYxUBcDVjFgFSP13gi_jJ91_7Gcjxbnt99l_pS_A4yflKw |
| CODEN | MLSTCK |
| CitedBy_id | crossref_primary_10_1088_2632_2153_ad5bbf crossref_primary_10_1007_s00466_025_02633_1 crossref_primary_10_1088_2632_2153_ad3ee4 crossref_primary_10_1137_24M166053X crossref_primary_10_3390_ijms25116186 |
| Cites_doi | 10.1109/TPAMI.2007.1115 10.1145/321694.321699 10.1007/978-3-030-01418-6_41 10.1038/sdata.2014.22 10.1103/PhysRev.136.B864 10.1021/ci300415d 10.1007/s10618-010-0210-x 10.1063/1.5024797 10.1021/acs.jcim.5b00559 10.3389/fdata.2019.00003 10.1609/aimag.v29i3.2157 10.1109_TNN.2008.2005605 10.5555/944919.944937 10.1021/acscentsci.7b00572 10.1007/s10822-016-9938-8 10.1016/j.acha.2010.04.005 10.1016/j.acha.2006.04.004 |
| ContentType | Journal Article |
| Copyright | 2023 The Author(s). Published by IOP Publishing Ltd 2023 The Author(s). Published by IOP Publishing Ltd. This work is published under http://creativecommons.org/licenses/by/4.0 (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| Copyright_xml | – notice: 2023 The Author(s). Published by IOP Publishing Ltd – notice: 2023 The Author(s). Published by IOP Publishing Ltd. This work is published under http://creativecommons.org/licenses/by/4.0 (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License. |
| DBID | O3W TSCCA AAYXX CITATION 3V. 7XB 88I 8FE 8FG 8FK ABUWG AFKRA ARAPS AZQEC BENPR BGLVJ CCPQU DWQXO GNUQQ HCIFZ JQ2 K7- M2P P62 PHGZM PHGZT PIMPY PKEHL PQEST PQGLB PQQKQ PQUKI PRINS Q9U DOA |
| DOI | 10.1088/2632-2153/acc0d8 |
| DatabaseName | Institute of Physics Open Access Journals (Activated by CARLI) IOPscience (Open Access) CrossRef ProQuest Central (Corporate) ProQuest Central (purchase pre-March 2016) Science Database (Alumni Edition) ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) (purchase pre-March 2016) ProQuest Central (Alumni) ProQuest Central UK/Ireland Advanced Technologies & Computer Science Collection ProQuest Central Essentials ProQuest Central ProQuest Technology Collection ProQuest One Community College ProQuest Central Korea ProQuest Central Student SciTech Collection (ProQuest) ProQuest Computer Science Collection Computer Science Database Science Database (ProQuest) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Premium ProQuest One Academic (New) ProQuest Publicly Available Content Database ProQuest One Academic Middle East (New) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ProQuest Central China ProQuest Central Basic DOAJ Directory of Open Access Journals |
| DatabaseTitle | CrossRef Publicly Available Content Database Computer Science Database ProQuest Central Student Technology Collection ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ProQuest Central China ProQuest Central ProQuest One Applied & Life Sciences ProQuest Central Korea ProQuest Central (New) Advanced Technologies & Aerospace Collection ProQuest Science Journals (Alumni Edition) ProQuest Central Basic ProQuest Science Journals ProQuest One Academic Eastern Edition ProQuest Technology Collection ProQuest SciTech Collection ProQuest One Academic UKI Edition ProQuest One Academic ProQuest One Academic (New) ProQuest Central (Alumni) |
| DatabaseTitleList | CrossRef Publicly Available Content Database |
| Database_xml | – sequence: 1 dbid: DOA name: DOAJ Directory of Open Access Journals url: https://www.doaj.org/ sourceTypes: Open Website – sequence: 2 dbid: O3W name: Institute of Physics Open Access Journals (Activated by CARLI) url: http://iopscience.iop.org/ sourceTypes: Publisher – sequence: 3 dbid: PIMPY name: ProQuest Publicly Available Content Database url: http://search.proquest.com/publiccontent sourceTypes: Aggregation Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 2632-2153 |
| ExternalDocumentID | oai_doaj_org_article_e1a033e3a46c4df6bb2702bdf34db600 10_1088_2632_2153_acc0d8 mlstacc0d8 |
| GroupedDBID | 88I ABHWH ABUWG ACHIP AFKRA AKPSB ALMA_UNASSIGNED_HOLDINGS ARAPS AZQEC BENPR BGLVJ CCPQU CJUJL DWQXO EBS GNUQQ GROUPED_DOAJ HCIFZ IOP K7- M2P M~E N5L O3W OK1 PIMPY TSCCA AAYXX AEINN AFFHD CITATION PHGZM PHGZT PQGLB 3V. 7XB 8FE 8FG 8FK JQ2 P62 PKEHL PQEST PQQKQ PQUKI PRINS Q9U |
| ID | FETCH-LOGICAL-c416t-bb0a0bcbe734b5653c20e4f8b744f99e4cd9415361b365d98302b1fb0203e7ef3 |
| IEDL.DBID | DOA |
| ISICitedReferencesCount | 8 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000957021100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 2632-2153 |
| IngestDate | Tue Oct 14 19:06:00 EDT 2025 Fri Jul 25 03:53:00 EDT 2025 Sat Nov 29 02:22:47 EST 2025 Tue Nov 18 22:22:10 EST 2025 Sun Aug 18 14:40:27 EDT 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 1 |
| Language | English |
| License | Original content from this work may be used under the terms of the Creative Commons Attribution 4.0 license. Any further distribution of this work must maintain attribution to the author(s) and the title of the work, journal citation and DOI. |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c416t-bb0a0bcbe734b5653c20e4f8b744f99e4cd9415361b365d98302b1fb0203e7ef3 |
| Notes | MLST-100828.R1 ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| ORCID | 0000-0002-5092-3757 |
| OpenAccessLink | https://doaj.org/article/e1a033e3a46c4df6bb2702bdf34db600 |
| PQID | 2789277662 |
| PQPubID | 4916454 |
| PageCount | 24 |
| ParticipantIDs | crossref_citationtrail_10_1088_2632_2153_acc0d8 proquest_journals_2789277662 crossref_primary_10_1088_2632_2153_acc0d8 iop_journals_10_1088_2632_2153_acc0d8 doaj_primary_oai_doaj_org_article_e1a033e3a46c4df6bb2702bdf34db600 |
| PublicationCentury | 2000 |
| PublicationDate | 2023-03-01 |
| PublicationDateYYYYMMDD | 2023-03-01 |
| PublicationDate_xml | – month: 03 year: 2023 text: 2023-03-01 day: 01 |
| PublicationDecade | 2020 |
| PublicationPlace | Bristol |
| PublicationPlace_xml | – name: Bristol |
| PublicationTitle | Machine learning: science and technology |
| PublicationTitleAbbrev | MLST |
| PublicationTitleAlternate | Mach. Learn.: Sci. Technol |
| PublicationYear | 2023 |
| Publisher | IOP Publishing |
| Publisher_xml | – name: IOP Publishing |
| References | Fout (mlstacc0d8bib9) 2017 You (mlstacc0d8bib16) 2018 Kipf (mlstacc0d8bib59) 2016 Liu (mlstacc0d8bib19) 2019; vol 32 Maron (mlstacc0d8bib15) 2019 Xu (mlstacc0d8bib53) 2022 LeCun (mlstacc0d8bib76) 1999 Xu (mlstacc0d8bib13) 2019 Ingraham (mlstacc0d8bib45) 2017 Vahdat (mlstacc0d8bib48) 2020; vol 33 Niepert (mlstacc0d8bib2) 2016 Gómez-Bombarelli (mlstacc0d8bib21) 2018; 4 Sterling (mlstacc0d8bib66) 2015; 55 Liu (mlstacc0d8bib67) 2018; vol 31 Glorot (mlstacc0d8bib74) Ranganath (mlstacc0d8bib44) 2016 Cohen (mlstacc0d8bib26) 2016; vol 48 Cheng (mlstacc0d8bib12) 2015 Liao (mlstacc0d8bib18) 2019; vol 32 Dhillon (mlstacc0d8bib37) 2007; 29 Edmonds (mlstacc0d8bib63) 1972; 19 Rue (mlstacc0d8bib62) 2005; vol 104 Chen (mlstacc0d8bib11) 2014 Xie (mlstacc0d8bib52) 2022 Paszke (mlstacc0d8bib90) 2019; vol 32 Dieng (mlstacc0d8bib81) 2019 Kondor (mlstacc0d8bib28) 2018 Cohen (mlstacc0d8bib27) 2017 Koller (mlstacc0d8bib61) 2009 Hy (mlstacc0d8bib8) 2018; 148 Kriege (mlstacc0d8bib84) 2016; vol 16 Maron (mlstacc0d8bib32) 2019 Rustamov (mlstacc0d8bib10) 2013; vol 26 Dai (mlstacc0d8bib20) 2020 Blei (mlstacc0d8bib43) 2003; 3 Si (mlstacc0d8bib39) 2014; vol 27 Scarselli (mlstacc0d8bib1) 2009; 20 Prakash Dwivedi (mlstacc0d8bib85) 2020 Klushyn (mlstacc0d8bib46) 2019; vol 32 Maddison (mlstacc0d8bib56) 2014; vol 27 Lin (mlstacc0d8bib80) 2018; vol 31 Zhou (mlstacc0d8bib41) 2019; 2 Serviansky (mlstacc0d8bib30) 2020; vol 33 Veličković (mlstacc0d8bib87) 2018 Jin (mlstacc0d8bib24) 2018 Shin (mlstacc0d8bib40) 2012 Ruddigkeit (mlstacc0d8bib64) 2012; 52 Bengio (mlstacc0d8bib50) 2021; vol 34 Kingma (mlstacc0d8bib68) 2015 Sen (mlstacc0d8bib69) 2008; 29 Dhillon (mlstacc0d8bib36) 2005 Battaglia (mlstacc0d8bib4) 2016; vol 29 Kearnes (mlstacc0d8bib6) 2016; 30 Wainwright (mlstacc0d8bib58) 2005 Shervashidze (mlstacc0d8bib83) 2011; 12 Monti (mlstacc0d8bib88) 2017 Li (mlstacc0d8bib17) 2018 Henning Thiede (mlstacc0d8bib25) 2020 Ma (mlstacc0d8bib89) 2019 Perozzi (mlstacc0d8bib73) 2014 Zaheer (mlstacc0d8bib29) 2017; vol 30 Goodfellow (mlstacc0d8bib42) 2014; vol 27 Tang (mlstacc0d8bib72) 2011; 23 Coifman (mlstacc0d8bib34) 2006; 21 Kingma (mlstacc0d8bib54) 2014 Maron (mlstacc0d8bib31) 2020 Jain (mlstacc0d8bib51) 2022 Bengio (mlstacc0d8bib49) 2021 Seitzer (mlstacc0d8bib78) 2020 De Cao (mlstacc0d8bib23) 2018 Maron (mlstacc0d8bib33) 2019; vol 32 Radford (mlstacc0d8bib75) 2016 Gumbel (mlstacc0d8bib55) 1954; 33 Wu (mlstacc0d8bib47) 2020; vol 33 Jang (mlstacc0d8bib57) 2017 Gilmer (mlstacc0d8bib7) 2017 Yang (mlstacc0d8bib86) 2020; vol 33 Srivastava (mlstacc0d8bib79) 2017; vol 30 Duvenaud (mlstacc0d8bib5) 2015; 28 Chiang (mlstacc0d8bib38) 2012 Li (mlstacc0d8bib3) 2016 You (mlstacc0d8bib70) 2018 Hohenberg (mlstacc0d8bib82) 1964; 136 Ying (mlstacc0d8bib14) 2018; vol 31 Simonovsky (mlstacc0d8bib22) 2018 Hammond (mlstacc0d8bib35) 2011; 30 Shi (mlstacc0d8bib71) 2020 Heusel (mlstacc0d8bib77) 2017; vol 30 Murphy (mlstacc0d8bib60) 2012 Ramakrishnan (mlstacc0d8bib65) 2014; 1 |
| References_xml | – volume: 29 start-page: 1944 year: 2007 ident: mlstacc0d8bib37 article-title: Weighted graph cuts without eigenvectors a multilevel approach publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2007.1115 – start-page: pp 4212 year: 2019 ident: mlstacc0d8bib89 article-title: Disentangled graph convolutional networks – volume: vol 31 year: 2018 ident: mlstacc0d8bib67 article-title: Constrained graph variational autoencoders for molecule design – volume: 19 start-page: 248 year: 1972 ident: mlstacc0d8bib63 article-title: Theoretical improvements in algorithmic efficiency for network flow problems publication-title: J. ACM doi: 10.1145/321694.321699 – volume: vol 48 start-page: pp 2990 year: 2016 ident: mlstacc0d8bib26 article-title: Group equivariant convolutional networks – year: 2018 ident: mlstacc0d8bib87 article-title: Graph attention networks – volume: vol 32 year: 2019 ident: mlstacc0d8bib19 article-title: Graph normalizing flows – year: 2018 ident: mlstacc0d8bib70 article-title: Code for GraphRNN: generating realistic graphs with deep auto-regressive model – year: 2022 ident: mlstacc0d8bib52 article-title: Crystal diffusion variational autoencoder for periodic material generation – volume: vol 31 year: 2018 ident: mlstacc0d8bib14 article-title: Hierarchical graph representation learning with differentiable pooling – start-page: pp 249 ident: mlstacc0d8bib74 article-title: Understanding the difficulty of training deep feedforward neural networks – start-page: p 5 year: 2017 ident: mlstacc0d8bib27 article-title: Steerable CNNs – volume: vol 27 year: 2014 ident: mlstacc0d8bib56 article-title: A* sampling – start-page: pp 215 year: 2012 ident: mlstacc0d8bib40 article-title: Multi-scale link prediction – year: 2018 ident: mlstacc0d8bib22 article-title: GraphVAE: towards generation of small graphs using variational autoencoders doi: 10.1007/978-3-030-01418-6_41 – volume: 33 year: 1954 ident: mlstacc0d8bib55 article-title: Statistical theory of extreme values and some practical applications: a series of lectures – volume: vol 29 year: 2016 ident: mlstacc0d8bib4 article-title: Interaction networks for learning about objects, relations and physics – year: 2016 ident: mlstacc0d8bib59 article-title: Variational graph auto-encoders – start-page: pp 1263 year: 2017 ident: mlstacc0d8bib7 article-title: Neural message passing for quantum chemistry – volume: vol 32 year: 2019 ident: mlstacc0d8bib46 article-title: Learning hierarchical priors in VAEs – year: 2005 ident: mlstacc0d8bib58 article-title: A variational principle for graphical models – year: 2009 ident: mlstacc0d8bib61 – volume: 1 year: 2014 ident: mlstacc0d8bib65 article-title: Quantum chemistry structures and properties of 134 kilo molecules publication-title: Sci. Data doi: 10.1038/sdata.2014.22 – volume: vol 33 start-page: pp 5933 year: 2020 ident: mlstacc0d8bib47 article-title: Stochastic normalizing flows – volume: vol 26 year: 2013 ident: mlstacc0d8bib10 article-title: Wavelets on graphs via deep learning – volume: vol 30 year: 2017 ident: mlstacc0d8bib29 article-title: Deep sets – year: 2020 ident: mlstacc0d8bib25 article-title: The general theory of permutation equivariant neural networks and higher order graph variational encoders – volume: vol 104 year: 2005 ident: mlstacc0d8bib62 article-title: Gaussian Markov random fields: theory and applications – volume: vol 34 start-page: pp 27381 year: 2021 ident: mlstacc0d8bib50 article-title: Flow network based generative models for non-iterative diverse candidate generation – year: 2015 ident: mlstacc0d8bib68 article-title: Adam: a method for stochastic optimization – start-page: pp 629 year: 2005 ident: mlstacc0d8bib36 article-title: A fast kernel-based multilevel algorithm for graph clustering – volume: vol 31 year: 2018 ident: mlstacc0d8bib80 article-title: PacGAN: the power of two samples in generative adversarial networks – volume: 136 start-page: 864 year: 1964 ident: mlstacc0d8bib82 article-title: Inhomogeneous electron gas publication-title: Phys. Rev. doi: 10.1103/PhysRev.136.B864 – volume: 52 start-page: 2864 year: 2012 ident: mlstacc0d8bib64 article-title: Enumeration of 166 billion organic small molecules in the chemical universe database GDB-17 publication-title: J. Chem. Inf. Modeling doi: 10.1021/ci300415d – volume: 23 start-page: 447 year: 2011 ident: mlstacc0d8bib72 article-title: Leveraging social media networks for classification publication-title: Data Min. Knowl. Discov. doi: 10.1007/s10618-010-0210-x – year: 2018 ident: mlstacc0d8bib17 article-title: Learning deep generative models of graphs – year: 1999 ident: mlstacc0d8bib76 article-title: The MNIST database of handwritten digits – start-page: pp 5425 year: 2017 ident: mlstacc0d8bib88 article-title: Geometric deep learning on graphs and manifolds using mixture model CNNs – volume: 148 year: 2018 ident: mlstacc0d8bib8 article-title: Predicting molecular properties with covariant compositional networks publication-title: J. Chem. Phys. doi: 10.1063/1.5024797 – volume: 55 start-page: 2324 year: 2015 ident: mlstacc0d8bib66 article-title: Zinc 15—ligand discovery for everyone publication-title: J. Chem. Inf. Modeling doi: 10.1021/acs.jcim.5b00559 – volume: 2 start-page: 3 year: 2019 ident: mlstacc0d8bib41 article-title: Misc-GAN: a multi-scale generative model for graphs publication-title: Front. Big Data doi: 10.3389/fdata.2019.00003 – volume: 29 start-page: 93 year: 2008 ident: mlstacc0d8bib69 article-title: Collective classification in network data publication-title: AI Mag. doi: 10.1609/aimag.v29i3.2157 – volume: 20 start-page: 61 year: 2009 ident: mlstacc0d8bib1 article-title: The graph neural network model publication-title: IEEE Trans. Neural Netw. doi: 10.1109_TNN.2008.2005605 – year: 2020 ident: mlstacc0d8bib71 article-title: GraphAF: a flow-based autoregressive model for molecular graph generation – volume: 3 start-page: 993 year: 2003 ident: mlstacc0d8bib43 article-title: Latent Dirichlet allocation publication-title: J. Mach. Learn. Res. doi: 10.5555/944919.944937 – year: 2022 ident: mlstacc0d8bib53 article-title: GeoDiff: a geometric diffusion model for molecular conformation generation – volume: vol 33 start-page: pp 22080 year: 2020 ident: mlstacc0d8bib30 article-title: Set2Graph: learning graphs from sets – volume: vol 30 year: 2017 ident: mlstacc0d8bib79 article-title: VEEGAN: reducing mode collapse in GANs using implicit variational learning – volume: 4 start-page: 268 year: 2018 ident: mlstacc0d8bib21 article-title: Automatic chemical design using a data-driven continuous representation of molecules publication-title: ACS Cent. Sci. doi: 10.1021/acscentsci.7b00572 – start-page: pp 2323 year: 2018 ident: mlstacc0d8bib24 article-title: Junction tree variational autoencoder for molecular graph generation – year: 2019 ident: mlstacc0d8bib15 article-title: Invariant and equivariant graph networks – year: 2021 ident: mlstacc0d8bib49 article-title: GFlowNet foundations – year: 2017 ident: mlstacc0d8bib57 article-title: Categorical reparameterization with Gumbel-Softmax – start-page: pp 2014 year: 2016 ident: mlstacc0d8bib2 article-title: Learning convolutional neural networks for graphs – volume: 30 start-page: 595 year: 2016 ident: mlstacc0d8bib6 article-title: Molecular graph convolutions: moving beyond fingerprints publication-title: J. Comput.-Aided Mol. Des. doi: 10.1007/s10822-016-9938-8 – year: 2015 ident: mlstacc0d8bib12 article-title: Deep Haar scattering networks – year: 2018 ident: mlstacc0d8bib28 article-title: Covariant compositional networks for learning graphs – year: 2014 ident: mlstacc0d8bib54 article-title: Auto-encoding variational Bayes – volume: vol 27 year: 2014 ident: mlstacc0d8bib42 article-title: Generative adversarial nets – volume: vol 32 year: 2019 ident: mlstacc0d8bib33 article-title: Provably powerful graph networks – start-page: pp 663 year: 2012 ident: mlstacc0d8bib60 article-title: Chapter 19: Undirected graphical models (Markov random fields) – volume: vol 32 year: 2019 ident: mlstacc0d8bib90 article-title: PyTorch: an imperative style, high-performance deep learning library – start-page: pp 701 year: 2014 ident: mlstacc0d8bib73 article-title: DeepWalk: online learning of social representations – year: 2019 ident: mlstacc0d8bib81 article-title: Prescribed generative adversarial networks – volume: vol 33 start-page: pp 20286 year: 2020 ident: mlstacc0d8bib86 article-title: Factorizable graph convolutional networks – year: 2016 ident: mlstacc0d8bib3 article-title: Gated graph sequence neural networks – start-page: pp 4363 year: 2019 ident: mlstacc0d8bib32 article-title: On the universality of invariant networks – year: 2018 ident: mlstacc0d8bib23 article-title: MolGAN: an implicit generative model for small molecular graphs – volume: vol 27 year: 2014 ident: mlstacc0d8bib39 article-title: Multi-scale spectral decomposition of massive graphs – year: 2016 ident: mlstacc0d8bib75 article-title: Unsupervised representation learning with deep convolutional generative adversarial networks – start-page: pp 324 year: 2016 ident: mlstacc0d8bib44 article-title: Hierarchical variational models – start-page: pp 5708 year: 2018 ident: mlstacc0d8bib16 article-title: GraphRNN: generating realistic graphs with deep auto-regressive models – volume: vol 16 start-page: pp 1623 year: 2016 ident: mlstacc0d8bib84 article-title: On valid optimal assignment kernels and applications to graph classification – start-page: pp 6533 year: 2017 ident: mlstacc0d8bib9 article-title: Protein interface prediction using graph convolutional networks – start-page: pp 2302 year: 2020 ident: mlstacc0d8bib20 article-title: Scalable deep generative modeling for sparse graphs – volume: 30 start-page: 129 year: 2011 ident: mlstacc0d8bib35 article-title: Wavelets on graphs via spectral graph theory publication-title: Appl. Comput. Harmon. Anal. doi: 10.1016/j.acha.2010.04.005 – start-page: pp 9786 year: 2022 ident: mlstacc0d8bib51 article-title: Biological sequence design with GFlowNets – start-page: pp 1607 year: 2017 ident: mlstacc0d8bib45 article-title: Variational inference for sparse and undirected models – start-page: pp 6734 year: 2020 ident: mlstacc0d8bib31 article-title: On learning sets of symmetric elements – volume: 12 start-page: 2539 year: 2011 ident: mlstacc0d8bib83 article-title: Weisfeiler-Lehman graph kernels publication-title: J. Mach. Learn. Res. – year: 2020 ident: mlstacc0d8bib85 article-title: Benchmarking graph neural networks – volume: vol 32 year: 2019 ident: mlstacc0d8bib18 article-title: Efficient graph generation with graph recurrent attention networks – volume: vol 33 start-page: pp 19667 year: 2020 ident: mlstacc0d8bib48 article-title: NVAE: a deep hierarchical variational autoencoder – year: 2014 ident: mlstacc0d8bib11 article-title: Unsupervised deep Haar scattering on graphs – year: 2019 ident: mlstacc0d8bib13 article-title: Graph wavelet neural network – start-page: pp 615 year: 2012 ident: mlstacc0d8bib38 article-title: Scalable clustering of signed networks using balance normalized cut – year: 2020 ident: mlstacc0d8bib78 article-title: PyTorch-FID: FID Score for PyTorch (Version 0.1.1) – volume: 28 start-page: 2224 year: 2015 ident: mlstacc0d8bib5 article-title: Convolutional networks on graphs for learning molecular fingerprints – volume: vol 30 year: 2017 ident: mlstacc0d8bib77 article-title: GANs trained by a two time-scale update rule converge to a local Nash equilibrium – volume: 21 start-page: 53 year: 2006 ident: mlstacc0d8bib34 article-title: Diffusion wavelets publication-title: Appl. Comput. Harmon. Anal. doi: 10.1016/j.acha.2006.04.004 |
| SSID | ssj0002513520 |
| Score | 2.3573608 |
| Snippet | In this paper, we propose
Multiresolution Equivariant Graph Variational Autoencoders
(MGVAE), the first hierarchical generative model to learn and generate... In this paper, we propose Multiresolution Equivariant Graph Variational Autoencoders (MGVAE), the first hierarchical generative model to learn and generate... |
| SourceID | doaj proquest crossref iop |
| SourceType | Open Website Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 15031 |
| SubjectTerms | Coarsening graph neural networks graph variational autoencoders Graphs hierarchical generative models Image processing Learning Message passing Molecular properties molecule generation Permutations supervised and unsupervised molecular representation learning |
| SummonAdditionalLinks | – databaseName: Institute of Physics Open Access Journals (Activated by CARLI) dbid: O3W link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8QwEB58Hbz4FtcXPejBQ920iW2CJxXFk3pQ9FYyeYAgu-u66-93kmZXRBHBW1smbZmZZL7J4xuAA-t1SakPpanMyVygVrnWWOSlIjjnLfe1wlhsor65kU9P6m4GTqdnYfqDNPQf02VLFNyqMG2Ik93AMJ5TpOJdbQyzchbmuaQwTs58yx-nEywUuAlcsLQ0-VPDL6EoMvZTgKGvfhuWY6y5Wv7XX67AUoKY2VkrugozrrcGy5PyDVnqzeug4uFbSreT92Xudfz8TrkzKTuLRNZZvGtnCzM9HvUD66V1ww14uLq8v7jOUyWF3BDgGuWITDM06GoukCAcNyVzwkushfBKOWGsokjOqwJ5dWJVIAXDwmNYpnS183wT5nr9ntuCzHIeYKI0yL3QkmlCGM6eVHWF2hVMdaA7UWpjEs14qHbx0sTlbimboJkmaKZpNdOBo2mLQUux8YvsebDTVC6QY8cHZIImmaBxhWacO65FZYT1FWI4dIfWc2GRAF4HDslqTeqsb798bHfiB5_C4eRwWddVVW7_8TU7sBhq1Lc7AHdhbjQcuz1YMO-j57fhfnTaDxXY7LQ priority: 102 providerName: IOP Publishing – databaseName: Science Database (ProQuest) dbid: M2P link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV07T8MwELagMLDwRpSXMsDAENWJTRJPCBAVC4gBJLbI5weqhJrSB7-fO8ctQkhdGJNclMjn8313Z3_H2Ln1OsfQB8NU7qpUglap1pCluUI4563wpYLQbKJ8eqre3tRzTLhN4rbK-ZoYFmrbGMqR9-jEZl6WRZFfjz5T6hpF1dXYQmOVrSGyyWhL12P-vMixoO9GfMFjdRLtqUfs5Cl6OdHTxnBb_fJGgbQffcygGf1ZmYO76W_990e32WYEmslNOzN22Iob7rKteROHJNr0HlPhCC4G3XEOJu5zNvjCCBqHPAl01km4anOGiZ5NG-K-tG68z1779y93D2nsp5AahF3TFIBrDgZcKSQgkBMm5076CkopvVJOGqvQn4siA1FcWUXUYJB5oGKlK50XB6wzbIbukCVWCAKLlQHhpa64Rpzh7FVRFqBdxlWX9ebjWptINk49Lz7qUPSuqpo0UZMm6lYTXXa5eGPUEm0skb0lVS3kiCI73GjG73W0uNplmgvhhJaFkdYXAHT0DqwX0gLCvC67QEXX0WQnSz52Mtfzj_CPko-WPz5mG9Sgvt21dsI60_HMnbJ18zUdTMZnYbp-Awu68hc priority: 102 providerName: ProQuest |
| Title | Multiresolution equivariant graph variational autoencoder |
| URI | https://iopscience.iop.org/article/10.1088/2632-2153/acc0d8 https://www.proquest.com/docview/2789277662 https://doaj.org/article/e1a033e3a46c4df6bb2702bdf34db600 |
| Volume | 4 |
| WOSCitedRecordID | wos000957021100001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVAON databaseName: DOAJ Directory of Open Access Journals customDbUrl: eissn: 2632-2153 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002513520 issn: 2632-2153 databaseCode: DOA dateStart: 20200101 isFulltext: true titleUrlDefault: https://www.doaj.org/ providerName: Directory of Open Access Journals – providerCode: PRVIOP databaseName: Institute of Physics Open Access Journals (Activated by CARLI) customDbUrl: eissn: 2632-2153 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002513520 issn: 2632-2153 databaseCode: O3W dateStart: 20200301 isFulltext: true titleUrlDefault: http://iopscience.iop.org/ providerName: IOP Publishing – providerCode: PRVHPJ databaseName: ROAD: Directory of Open Access Scholarly Resources (ISSN International Center) customDbUrl: eissn: 2632-2153 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002513520 issn: 2632-2153 databaseCode: M~E dateStart: 20200101 isFulltext: true titleUrlDefault: https://road.issn.org providerName: ISSN International Centre – providerCode: PRVPQU databaseName: Computer Science Database customDbUrl: eissn: 2632-2153 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002513520 issn: 2632-2153 databaseCode: K7- dateStart: 20200301 isFulltext: true titleUrlDefault: http://search.proquest.com/compscijour providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 2632-2153 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002513520 issn: 2632-2153 databaseCode: BENPR dateStart: 20200301 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Publicly Available Content Database customDbUrl: eissn: 2632-2153 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002513520 issn: 2632-2153 databaseCode: PIMPY dateStart: 20200301 isFulltext: true titleUrlDefault: http://search.proquest.com/publiccontent providerName: ProQuest – providerCode: PRVPQU databaseName: Science Database (ProQuest) customDbUrl: eissn: 2632-2153 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002513520 issn: 2632-2153 databaseCode: M2P dateStart: 20200301 isFulltext: true titleUrlDefault: https://search.proquest.com/sciencejournals providerName: ProQuest |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwrV1Lj9MwELZWZQ9ceC2IQqlygMMeojqxG8dHilqBUEuEWG05RR4_pEqrdunryG9nxkmXrlYqFy4jJZoo1je2Z8aPbxh774LJMfXBNJX7MpVgdGoMZGmuMZwLTgSlIRabULNZOZ_r6qjUF50Ja-iBG-AGPjNcCC-MLKx0oQCgG1TggpAO0FvT7MuVPkqmaA5Gr42RBW_3JXEkDYiXPEX_JgbGWu7Ke34o0vWjd1msbh_MydHRTJ6xJ22EmHxsWvacnfnlC_b0UH0haQfjBdPx7ixmy23nSfyv3WKPqS9ilUQe6iQ-NYt9idltV0Ra6fz6JbuajH98-py2hRBSi_HSNgXghoMFr4QEjMCEzbmXoQQlZdDaS-s0OmJRZCCKodPE6QVZANpl9MoH8Yp1lqulf80SJwRFeaUFEaQpucEAwbthoQowPuO6ywYHWGrbsoRTsYqbOu5Wl2VNQNYEZN0A2WWXd1_cNgwZJ3RHhPSdHnFbxxdo8bq1eP0vi3fZB7RT3Y61zYmf9Q6W_KtMF39zpYoif_M_2vKWPab6882htB7rbNc7_46d2_12sVn32aPReFZ978e-ifKrSlFO84rk7zHKb-Iataov0-rnH1cs67c |
| linkProvider | Directory of Open Access Journals |
| linkToHtml | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VggQXylMsFMiBHjhEm9huEh9Q1RaqVi2rHorUm_GzWgltttlsEX-K38iMk2yFkPbWA8ckTqJkXp89nm8APrigGU59cJqa-SoVRstUa5OnTCKcC46HUprYbKKcTKrLS3m-Ab-HWhjaVjn4xOioXW1pjXxMFZusLIuC7c2vU-oaRdnVoYVGpxan_tdPnLItPp18RvnuMHb05eLwOO27CqQWwUebGpPpzFjjSy4MwhluWeZFqEwpRJDSC-skRjVe5IYXu04SQZbJg6GUnS994Pjce3BfELMYbRVk56s1HcQKiGeyPhuK9jsmNvQUoyofa2szV_0V_WKTAIxp03r-TySI4e1o63_7MU_gcQ-kk_1O85_Chp89g62hSUXS-6znIGOJceMHG0v89XJ6o9HuZm0S6bqTeNStiSZ62dbE7el88wK-3ckHvITNWT3zryBxnBMYrqzhQegq04ijvNstysJon2dyBONBjsr2ZOrU0-OHikn9qlIkeUWSV53kR_Bxdce8IxJZM_aAVGM1jijA44m6uVK9R1E-1xnnnmtRWOFCYQyVFhoXuHAGYewIdlCxVO-SFmtetj3o1e3gW6V6vf7ye3h4fPH1TJ2dTE7fwCOGELDbobcNm22z9G_hgb1pp4vmXTSVBL7ftQr-AeSyTpM |
| linkToPdf | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LTxsxEB61FFW9lEJbNRTaPcCBwzbetdm1j7yiVkWBAwhulscPCQklaUj4_Yy9ThCiQpV627XG69XM2DNje74B2HHB1BT6UJjKvCwFGlUag1VZK3LnguOhVZiKTbTDoby-Vue5zmnKhRlP8tL_gx47oOCOhflCnOxHhPGSLBXvG2uZk_2JC6_hTcQpiWp9xq-WmyxkvKmV5ePJv3V-Yo4Saj8ZGRr52dKc7M1g7b__9AO8z65mcdCRr8MrP9qAtUUZhyLP6o-gUhIuhd1ZCwv_Z35zTzE0Mb1IgNZFeut2DQszn40j-qXz009wOTi5OPpZ5ooKpSXHa1YiMsPQom-5QHLluK2ZF0FiK0RQygvrFFl03lTIm32nIjgYVgHjcaVvfeCfYWU0HvkvUDjOo7soLfIgjGSGPA3v9pu2QeMrpnrQXzBW2ww3Hqte3Op07C2ljtzRkTu6404P9pY9Jh3Uxgu0h1FWS7oIkp0aSAw6i0H7yjDOPTeiscKFBjEm36ELXDgkR68HuyQ5nSft3QuDbS104ZE4ZhDXbds09eY_fuY7vD0_HujTX8PfX-FdLFvf3WXbgpXZdO63YdXez27upt-SDj8AFCvyHg |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Multiresolution+equivariant+graph+variational+autoencoder&rft.jtitle=Machine+learning%3A+science+and+technology&rft.au=Truong+Son+Hy&rft.au=Risi+Kondor&rft.date=2023-03-01&rft.pub=IOP+Publishing&rft.eissn=2632-2153&rft.volume=4&rft.issue=1&rft.spage=015031&rft_id=info:doi/10.1088%2F2632-2153%2Facc0d8&rft.externalDBID=DOA&rft.externalDocID=oai_doaj_org_article_e1a033e3a46c4df6bb2702bdf34db600 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2632-2153&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2632-2153&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2632-2153&client=summon |