dyngraph2vec: Capturing network dynamics using dynamic graph representation learning
Learning graph representations is a fundamental task aimed at capturing various properties of graphs in vector space. The most recent methods learn such representations for static networks. However, real-world networks evolve over time and have varying dynamics. Capturing such evolution is key to pr...
Saved in:
| Published in: | Knowledge-based systems Vol. 187; p. 104816 |
|---|---|
| Main Authors: | , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Amsterdam
Elsevier B.V
01.01.2020
Elsevier Science Ltd |
| Subjects: | |
| ISSN: | 0950-7051, 1872-7409 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Learning graph representations is a fundamental task aimed at capturing various properties of graphs in vector space. The most recent methods learn such representations for static networks. However, real-world networks evolve over time and have varying dynamics. Capturing such evolution is key to predicting the properties of unseen networks. To understand how the network dynamics affect the prediction performance, we propose an embedding approach which learns the structure of evolution in dynamic graphs and can predict unseen links with higher precision. Our model, dyngraph2vec, learns the temporal transitions in the network using a deep architecture composed of dense and recurrent layers. We motivate the need for capturing dynamics for the prediction on a toy dataset created using stochastic block models. We then demonstrate the efficacy of dyngraph2vec over existing state-of-the-art methods on two real-world datasets. We observe that learning dynamics can improve the quality of embedding and yield better performance in link prediction. |
|---|---|
| AbstractList | Learning graph representations is a fundamental task aimed at capturing various properties of graphs in vector space. The most recent methods learn such representations for static networks. However, real-world networks evolve over time and have varying dynamics. Capturing such evolution is key to predicting the properties of unseen networks. To understand how the network dynamics affect the prediction performance, we propose an embedding approach which learns the structure of evolution in dynamic graphs and can predict unseen links with higher precision. Our model, dyngraph2vec, learns the temporal transitions in the network using a deep architecture composed of dense and recurrent layers. We motivate the need for capturing dynamics for the prediction on a toy dataset created using stochastic block models. We then demonstrate the efficacy of dyngraph2vec over existing state-of-the-art methods on two real-world datasets. We observe that learning dynamics can improve the quality of embedding and yield better performance in link prediction. |
| ArticleNumber | 104816 |
| Author | Chhetri, Sujit Rokka Canedo, Arquimedes Goyal, Palash |
| Author_xml | – sequence: 1 givenname: Palash surname: Goyal fullname: Goyal, Palash email: palashgo@usc.edu organization: University of Southern California, Information Sciences Institute, 4676 Admiralty Way, Suite 1001, Marina del Rey, CA 90292, USA – sequence: 2 givenname: Sujit Rokka surname: Chhetri fullname: Chhetri, Sujit Rokka organization: University of California-Irvine Irvine, CA 92697, USA – sequence: 3 givenname: Arquimedes surname: Canedo fullname: Canedo, Arquimedes organization: Siemens Corporate Technology, 755 College Rd E, Princeton, NJ 08540, USA |
| BookMark | eNqFkMtOwzAQRS1UJNrCH7CIxDph7DivLpBQxUuqxKZ7y7EnxWnrBDsp6t-Tkq5YwGo0M_fM487IxDYWCbmlEFGg6X0dbW3jjz5iQIsI0ggYvyBTmmcszDgUEzKFIoEwg4RekZn3NQAwRvMpWeuj3TjZfrADqkWwlG3XO2M3gcXuq3HbYOjLvVE-6P2pfE6DHyZw2Dr0aDvZmcYGO5TODqprclnJncebc5yT9fPTevkart5f3paPq1BxgC5kCeo8iyUtyiThrIirvMwlS3MuUatS8VJBGeu8ZDTWRYVphRUvOdUaMkyyeE7uxrGtaz579J2om97ZYaNgcQxJnhQZHVSLUaVc473DSigz3ts5aXaCgjiZKGoxmihOJgpIxWDiAPNfcOvMXrrjf9jDiOHw_cGgE14ZtAq1cag6oRvz94Bvg2aS0g |
| CitedBy_id | crossref_primary_10_1007_s10115_024_02261_w crossref_primary_10_1016_j_knosys_2023_110936 crossref_primary_10_1109_TKDE_2024_3402234 crossref_primary_10_3389_fdata_2023_1135191 crossref_primary_10_48084_etasr_10791 crossref_primary_10_1038_s41598_023_29098_7 crossref_primary_10_1145_3723359 crossref_primary_10_1016_j_knosys_2020_105502 crossref_primary_10_1016_j_eswa_2021_116240 crossref_primary_10_1016_j_cose_2024_103981 crossref_primary_10_3390_app122211464 crossref_primary_10_1145_3745024 crossref_primary_10_7717_peerj_cs_357 crossref_primary_10_1007_s00500_023_08220_x crossref_primary_10_1145_3588771 crossref_primary_10_1016_j_neucom_2021_02_101 crossref_primary_10_1016_j_knosys_2021_108050 crossref_primary_10_1016_j_trc_2020_102851 crossref_primary_10_1145_3716391 crossref_primary_10_1016_j_knosys_2022_109659 crossref_primary_10_1109_ACCESS_2024_3367971 crossref_primary_10_1155_2022_6945397 crossref_primary_10_1109_TKDE_2023_3238360 crossref_primary_10_1016_j_ins_2023_120085 crossref_primary_10_1109_TKDE_2021_3085758 crossref_primary_10_1145_3483595 crossref_primary_10_1109_TNNLS_2024_3394161 crossref_primary_10_1145_3769107 crossref_primary_10_1007_s11063_024_11645_6 crossref_primary_10_1007_s11704_020_0088_8 crossref_primary_10_1016_j_ins_2024_120499 crossref_primary_10_1109_TKDE_2021_3135898 crossref_primary_10_1109_TETC_2022_3223058 crossref_primary_10_1371_journal_pone_0322202 crossref_primary_10_1007_s10489_024_05548_1 crossref_primary_10_3390_app11135861 crossref_primary_10_1016_j_cose_2025_104534 crossref_primary_10_1109_TKDE_2023_3295367 crossref_primary_10_1109_TNSE_2020_3035352 crossref_primary_10_1002_widm_1393 crossref_primary_10_1007_s11192_024_05132_x crossref_primary_10_1016_j_ins_2022_04_024 crossref_primary_10_1109_TSMC_2022_3196506 crossref_primary_10_1016_j_ins_2022_10_092 crossref_primary_10_1109_TKDE_2023_3329238 crossref_primary_10_1109_TKDE_2021_3094332 crossref_primary_10_1007_s13042_023_01803_y crossref_primary_10_1016_j_ins_2023_119637 crossref_primary_10_1007_s41109_020_00339_2 crossref_primary_10_1016_j_knosys_2022_108308 crossref_primary_10_1016_j_jcp_2024_113061 crossref_primary_10_1016_j_knosys_2020_106168 crossref_primary_10_1016_j_neucom_2021_03_138 crossref_primary_10_23919_JSC_2025_0008 crossref_primary_10_1049_ise2_9706647 crossref_primary_10_1109_TNNLS_2022_3185527 crossref_primary_10_1109_ACCESS_2025_3568695 crossref_primary_10_3390_electronics12051092 crossref_primary_10_1109_TKDE_2020_3033829 crossref_primary_10_1016_j_knosys_2023_110855 crossref_primary_10_1016_j_knosys_2024_112635 crossref_primary_10_1109_TSMC_2021_3130149 crossref_primary_10_1016_j_ipm_2023_103292 crossref_primary_10_1109_ACCESS_2020_3007835 crossref_primary_10_1145_3485189 crossref_primary_10_3390_electronics9060895 crossref_primary_10_3390_s22041402 crossref_primary_10_1145_3565575 crossref_primary_10_1016_j_physd_2025_134632 crossref_primary_10_1145_3654977 crossref_primary_10_1109_TKDE_2024_3438238 crossref_primary_10_1016_j_eswa_2023_122964 crossref_primary_10_3389_fnins_2023_1168112 crossref_primary_10_1109_ACCESS_2022_3172746 crossref_primary_10_1007_s40314_022_02071_2 crossref_primary_10_1109_TCYB_2022_3159661 crossref_primary_10_1002_int_22880 crossref_primary_10_1007_s11704_024_3853_2 crossref_primary_10_1007_s10479_024_05867_z crossref_primary_10_1145_3524124 crossref_primary_10_1109_TCSS_2024_3416837 crossref_primary_10_3390_s22166279 crossref_primary_10_1109_TKDE_2023_3246059 crossref_primary_10_1109_TAI_2024_3350545 crossref_primary_10_1109_TCBB_2022_3153963 crossref_primary_10_1089_big_2020_0086 crossref_primary_10_1109_TKDE_2022_3144083 crossref_primary_10_1080_00207543_2024_2344661 crossref_primary_10_1109_TCSS_2022_3180586 crossref_primary_10_1016_j_physa_2023_128525 crossref_primary_10_1007_s10489_021_02518_9 crossref_primary_10_1109_TKDE_2020_3017687 crossref_primary_10_1145_3593314 crossref_primary_10_1016_j_neucom_2023_127038 crossref_primary_10_1177_01655515211034407 crossref_primary_10_1016_j_neucom_2025_131447 crossref_primary_10_1002_int_22967 crossref_primary_10_1109_TNNLS_2021_3084957 crossref_primary_10_1007_s13278_021_00816_1 crossref_primary_10_1016_j_neucom_2022_05_105 crossref_primary_10_1109_ACCESS_2021_3055280 crossref_primary_10_1016_j_neucom_2022_05_109 crossref_primary_10_1016_j_asoc_2023_110272 crossref_primary_10_1111_exsy_13083 crossref_primary_10_1016_j_ins_2022_01_020 crossref_primary_10_3233_AIC_230028 crossref_primary_10_1016_j_eswa_2025_129028 crossref_primary_10_1109_TNSE_2024_3485093 crossref_primary_10_1016_j_neunet_2025_108006 crossref_primary_10_1145_3669906 crossref_primary_10_1016_j_patcog_2023_109663 crossref_primary_10_3390_math12020285 crossref_primary_10_1016_j_neucom_2023_02_060 crossref_primary_10_1145_3387726_3387729 crossref_primary_10_1145_3676559 crossref_primary_10_1007_s10489_022_03919_0 crossref_primary_10_1007_s10618_021_00784_2 crossref_primary_10_3390_electronics12040837 crossref_primary_10_1016_j_ins_2023_119240 crossref_primary_10_3390_e25020257 crossref_primary_10_1109_TNNLS_2022_3222165 crossref_primary_10_1145_3480243 crossref_primary_10_1007_s10618_023_00935_7 crossref_primary_10_1109_TKDE_2020_3034396 crossref_primary_10_1140_epjds_s13688_021_00277_8 crossref_primary_10_1007_s41019_020_00138_w crossref_primary_10_1016_j_neunet_2024_106384 crossref_primary_10_1049_cit2_12367 crossref_primary_10_1177_03611981241248160 crossref_primary_10_1016_j_ins_2023_119371 crossref_primary_10_1016_j_neunet_2025_107731 crossref_primary_10_3390_sym14102218 crossref_primary_10_1140_epjds_s13688_022_00344_8 crossref_primary_10_1016_j_neunet_2025_108056 crossref_primary_10_1109_TITS_2025_3526946 crossref_primary_10_1109_TC_2021_3057082 crossref_primary_10_1109_TNNLS_2022_3178706 crossref_primary_10_1016_j_neunet_2023_11_060 crossref_primary_10_3390_s23084168 crossref_primary_10_1016_j_asoc_2023_110059 crossref_primary_10_1109_ACCESS_2025_3553377 crossref_primary_10_1145_3762668 crossref_primary_10_1049_cit2_12215 crossref_primary_10_1016_j_knosys_2022_110167 crossref_primary_10_1016_j_neucom_2022_11_002 crossref_primary_10_1016_j_neunet_2024_106240 crossref_primary_10_3390_electronics13050957 crossref_primary_10_1109_TKDE_2022_3149999 crossref_primary_10_1016_j_neucom_2022_08_050 crossref_primary_10_1016_j_eswa_2024_125086 crossref_primary_10_1109_TCYB_2022_3168343 crossref_primary_10_1007_s10115_022_01792_4 crossref_primary_10_1016_j_knosys_2023_111308 crossref_primary_10_1016_j_patcog_2024_110577 crossref_primary_10_1109_JBHI_2022_3212863 crossref_primary_10_1016_j_neunet_2023_12_040 crossref_primary_10_1016_j_cities_2025_106334 crossref_primary_10_1016_j_neucom_2025_129439 crossref_primary_10_12677_mos_2024_133238 crossref_primary_10_1145_3633518 crossref_primary_10_1109_TKDE_2024_3388453 crossref_primary_10_1016_j_compbiomed_2024_109287 crossref_primary_10_1016_j_knosys_2024_111714 crossref_primary_10_1186_s40537_022_00595_2 crossref_primary_10_1007_s41019_021_00160_6 crossref_primary_10_1016_j_knosys_2021_107453 crossref_primary_10_1016_j_neucom_2023_126557 crossref_primary_10_1016_j_knosys_2025_113845 crossref_primary_10_1109_TNSE_2023_3301673 crossref_primary_10_1007_s44295_024_00042_3 crossref_primary_10_1109_TKDE_2023_3335223 crossref_primary_10_1016_j_neucom_2024_127265 crossref_primary_10_1109_ACCESS_2022_3192608 crossref_primary_10_1007_s43684_024_00067_9 crossref_primary_10_1109_TKDE_2022_3150272 crossref_primary_10_1016_j_eswa_2021_114913 crossref_primary_10_1016_j_patrec_2021_02_004 crossref_primary_10_1109_TNNLS_2024_3379735 crossref_primary_10_1007_s13721_022_00406_x crossref_primary_10_1007_s41060_022_00376_3 crossref_primary_10_1016_j_ins_2022_05_079 crossref_primary_10_1016_j_neunet_2024_106151 crossref_primary_10_1109_TNNLS_2023_3328924 crossref_primary_10_1016_j_neucom_2023_01_039 crossref_primary_10_1109_ACCESS_2021_3082932 crossref_primary_10_1016_j_neunet_2023_04_022 crossref_primary_10_1145_3625820 crossref_primary_10_1109_TIM_2023_3284956 crossref_primary_10_1109_MCI_2022_3222049 crossref_primary_10_12677_mos_2025_145422 crossref_primary_10_3390_math9020168 crossref_primary_10_1109_TNSE_2022_3164659 crossref_primary_10_1109_TKDE_2021_3110580 crossref_primary_10_1088_2632_2153_ad66af crossref_primary_10_1137_20M1386062 crossref_primary_10_1016_j_jpdc_2022_09_013 crossref_primary_10_1007_s00521_021_06706_z crossref_primary_10_1016_j_patcog_2024_111093 crossref_primary_10_1016_j_knosys_2024_112110 crossref_primary_10_1016_j_neunet_2023_05_048 |
| Cites_doi | 10.1145/980972.980992 10.1186/1756-0381-1-12 10.1038/nprot.2009.177 10.1109/TKDE.2016.2591009 10.1080/01621459.1987.10478385 10.1016/j.physa.2017.12.092 10.1016/j.laa.2005.07.021 10.1016/j.knosys.2018.03.022 |
| ContentType | Journal Article |
| Copyright | 2019 Elsevier B.V. Copyright Elsevier Science Ltd. Jan 2020 |
| Copyright_xml | – notice: 2019 Elsevier B.V. – notice: Copyright Elsevier Science Ltd. Jan 2020 |
| DBID | AAYXX CITATION 7SC 8FD E3H F2A JQ2 L7M L~C L~D |
| DOI | 10.1016/j.knosys.2019.06.024 |
| DatabaseName | CrossRef Computer and Information Systems Abstracts Technology Research Database Library & Information Sciences Abstracts (LISA) Library & Information Science Abstracts (LISA) ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional |
| DatabaseTitle | CrossRef Technology Research Database Computer and Information Systems Abstracts – Academic Library and Information Science Abstracts (LISA) ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional |
| DatabaseTitleList | Technology Research Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1872-7409 |
| ExternalDocumentID | 10_1016_j_knosys_2019_06_024 S0950705119302916 |
| GroupedDBID | --K --M .DC .~1 0R~ 1B1 1~. 1~5 29L 4.4 457 4G. 5VS 7-5 71M 77K 8P~ 9JN AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXUO AAYFN ABAOU ABBOA ABIVO ABJNI ABMAC ABXDB ABYKQ ACAZW ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HLZ HVGLF HZ~ IHE J1W JJJVA KOM LG9 LY7 M41 MHUIS MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 R2- RIG ROL RPZ SBC SDF SDG SDP SES SET SEW SPC SPCBC SST SSV SSW SSZ T5K UHS WH7 WUQ XPP ZMT ~02 ~G- 77I 9DU AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD 7SC 8FD E3H F2A JQ2 L7M L~C L~D |
| ID | FETCH-LOGICAL-c400t-25ed873a19b554293f8b8a2684aedcbc4bc0b3d8b213d9fe6fef4b41dd07e573 |
| ISICitedReferencesCount | 312 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000501653900021&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0950-7051 |
| IngestDate | Fri Nov 14 18:45:30 EST 2025 Sat Nov 29 07:07:05 EST 2025 Tue Nov 18 22:11:22 EST 2025 Fri Feb 23 02:18:39 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Python graph embedding methods GEM library Graph embedding applications Graph embedding techniques |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c400t-25ed873a19b554293f8b8a2684aedcbc4bc0b3d8b213d9fe6fef4b41dd07e573 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 |
| PQID | 2330585971 |
| PQPubID | 2035257 |
| ParticipantIDs | proquest_journals_2330585971 crossref_citationtrail_10_1016_j_knosys_2019_06_024 crossref_primary_10_1016_j_knosys_2019_06_024 elsevier_sciencedirect_doi_10_1016_j_knosys_2019_06_024 |
| PublicationCentury | 2000 |
| PublicationDate | January 2020 2020-01-00 20200101 |
| PublicationDateYYYYMMDD | 2020-01-01 |
| PublicationDate_xml | – month: 01 year: 2020 text: January 2020 |
| PublicationDecade | 2020 |
| PublicationPlace | Amsterdam |
| PublicationPlace_xml | – name: Amsterdam |
| PublicationTitle | Knowledge-based systems |
| PublicationYear | 2020 |
| Publisher | Elsevier B.V Elsevier Science Ltd |
| Publisher_xml | – name: Elsevier B.V – name: Elsevier Science Ltd |
| References | Goyal, Hosseinmardi, Ferrara, Galstyan (b14) 2018 P. Sarkar, D. Chakrabarti, M. Jordan, Nonparametric link prediction in dynamic networks, arXiv preprint Tang, Qu, Wang, Zhang, Yan, Mei (b13) 2015 Gehrke, Ginsparg, Kleinberg (b1) 2003; 5 Belkin, Niyogi (b18) 2001 Leskovec, Kleinberg, Faloutsos (b37) 2005 Freeman (b2) 2000; 1 Theocharidis, Van Dongen, Enright, Freeman (b3) 2009; 4 T.N. Kipf, M. Welling, Semi-supervised classification with graph convolutional networks, arXiv preprint Goyal, Sapienza, Ferrara (b4) 2018 Ou, Cui, Pei, Zhang, Zhu (b38) 2016 M. Rahman, T.K. Saha, M.A. Hasan, K.S. Xu, C.K. Reddy, Dylink2vec: Effective feature representation for link prediction in dynamic networks, arXiv preprint Ou, Cui, Pei, Zhang, Zhu (b9) 2016 Talasu, Jonnalagadda, Pillai, Rahul (b32) 2017 Pavlopoulos, Wegener, Schneider (b5) 2008; 1 Grover, Leskovec (b8) 2016 Goyal, Kamra, He, Liu (b26) 2017 Ma, Sun, Wang (b31) 2018; 496 Wasserman, Faust (b6) 1994 Wang, Wong (b34) 1987; 82 Yang, Khot, Kersting, Natarajan (b29) 2016 D. Kingma, J. Ba, Adam: A method for stochastic optimization, arXiv preprint Wang, Cui, Zhu (b19) 2016 Perozzi, Al-Rfou, Skiena (b11) 2014 T.N. Kipf, M. Welling, Variational graph auto-encoders, arXiv preprint J. Bruna, W. Zaremba, A. Szlam, Y. LeCun, Spectral networks and locally connected networks on graphs, arXiv preprint Li, Cheng, Wu, Liu (b33) 2018 P. Goyal, N. Kamra, X. He, Y. Liu, Dyngem: Deep Embedding Method for Dynamic Graphs, arXiv preprint Rumelhart, Hinton, Williams (b35) 1988 . M. Henaff, J. Bruna, Y. LeCun, Deep convolutional networks on graph-structured data, arXiv preprint Brand (b39) 2006; 415 Zhou, Yang, Ren, Wu, Zhuang (b15) 2018 Z. Zhang, P. Cui, J. Pei, X. Wang, W. Zhu, Timers: Error-Bounded svd restart on dynamic networks, arXiv preprint Cao, Lu, Xu (b20) 2016 Ahmed, Shervashidze, Narayanamurthy, Josifovski, Smola (b10) 2013 Dunlavy, Kolda, Acar (b30) 2011; 5 Cao, Lu, Xu (b12) 2015 Goyal, Ferrara (b7) 2018 Zhu, Guo, Yin, Ver Steeg, Galstyan (b25) 2016; 28 Grover (10.1016/j.knosys.2019.06.024_b8) 2016 Theocharidis (10.1016/j.knosys.2019.06.024_b3) 2009; 4 Perozzi (10.1016/j.knosys.2019.06.024_b11) 2014 Rumelhart (10.1016/j.knosys.2019.06.024_b35) 1988 Ahmed (10.1016/j.knosys.2019.06.024_b10) 2013 Freeman (10.1016/j.knosys.2019.06.024_b2) 2000; 1 Gehrke (10.1016/j.knosys.2019.06.024_b1) 2003; 5 10.1016/j.knosys.2019.06.024_b21 Wasserman (10.1016/j.knosys.2019.06.024_b6) 1994 10.1016/j.knosys.2019.06.024_b28 Goyal (10.1016/j.knosys.2019.06.024_b14) 2018 Zhu (10.1016/j.knosys.2019.06.024_b25) 2016; 28 Ou (10.1016/j.knosys.2019.06.024_b38) 2016 Cao (10.1016/j.knosys.2019.06.024_b12) 2015 10.1016/j.knosys.2019.06.024_b27 Leskovec (10.1016/j.knosys.2019.06.024_b37) 2005 Pavlopoulos (10.1016/j.knosys.2019.06.024_b5) 2008; 1 10.1016/j.knosys.2019.06.024_b24 10.1016/j.knosys.2019.06.024_b22 Yang (10.1016/j.knosys.2019.06.024_b29) 2016 10.1016/j.knosys.2019.06.024_b23 Talasu (10.1016/j.knosys.2019.06.024_b32) 2017 Ou (10.1016/j.knosys.2019.06.024_b9) 2016 Wang (10.1016/j.knosys.2019.06.024_b19) 2016 Ma (10.1016/j.knosys.2019.06.024_b31) 2018; 496 Brand (10.1016/j.knosys.2019.06.024_b39) 2006; 415 Goyal (10.1016/j.knosys.2019.06.024_b26) 2017 Goyal (10.1016/j.knosys.2019.06.024_b7) 2018 Cao (10.1016/j.knosys.2019.06.024_b20) 2016 Wang (10.1016/j.knosys.2019.06.024_b34) 1987; 82 Belkin (10.1016/j.knosys.2019.06.024_b18) 2001 Goyal (10.1016/j.knosys.2019.06.024_b4) 2018 Zhou (10.1016/j.knosys.2019.06.024_b15) 2018 Li (10.1016/j.knosys.2019.06.024_b33) 2018 Tang (10.1016/j.knosys.2019.06.024_b13) 2015 10.1016/j.knosys.2019.06.024_b17 10.1016/j.knosys.2019.06.024_b16 10.1016/j.knosys.2019.06.024_b36 Dunlavy (10.1016/j.knosys.2019.06.024_b30) 2011; 5 |
| References_xml | – start-page: 1067 year: 2015 end-page: 1077 ident: b13 article-title: Line: Large-scale information network embedding publication-title: Proceedings 24th International Conference on World Wide Web – reference: J. Bruna, W. Zaremba, A. Szlam, Y. LeCun, Spectral networks and locally connected networks on graphs, arXiv preprint – start-page: 701 year: 2014 end-page: 710 ident: b11 article-title: Deepwalk: Online learning of social representations publication-title: Proceedings 20th International Conference on Knowledge Discovery and Data Mining – start-page: 585 year: 2001 end-page: 591 ident: b18 article-title: Laplacian eigenmaps and spectral techniques for embedding and clustering publication-title: NIPS, Vol. 14 – start-page: 855 year: 2016 end-page: 864 ident: b8 article-title: Node2vec: Scalable feature learning for networks publication-title: Proceedings of the 22nd International Conference on Knowledge Discovery and Data Mining – start-page: 1105 year: 2016 end-page: 1114 ident: b9 article-title: Asymmetric transitivity preserving graph embedding publication-title: Proc. of ACM SIGKDD – start-page: 38 year: 2018 end-page: 42 ident: b14 article-title: Embedding networks with edge attributes publication-title: Proceedings of the 29th on Hypertext and Social Media – start-page: 2059 year: 2017 end-page: 2062 ident: b32 article-title: A link prediction based approach for recommendation systems publication-title: 2017 International Conference on Advances in Computing, Communications and Informatics (ICACCI) – reference: Z. Zhang, P. Cui, J. Pei, X. Wang, W. Zhu, Timers: Error-Bounded svd restart on dynamic networks, arXiv preprint – volume: 28 start-page: 2765 year: 2016 end-page: 2777 ident: b25 article-title: Scalable temporal latent space inference for link prediction in dynamic social networks publication-title: IEEE Trans. Knowl. Data Eng. – year: 2017 ident: b26 article-title: Dyngem: Deep embedding method for dynamic graphs publication-title: IJCAI International Workshop on Representation Learning for Graphs – start-page: 1225 year: 2016 end-page: 1234 ident: b19 article-title: Structural deep network embedding publication-title: Proceedings of the 22nd International Conference on Knowledge Discovery and Data Mining – reference: D. Kingma, J. Ba, Adam: A method for stochastic optimization, arXiv preprint – volume: 415 start-page: 20 year: 2006 end-page: 30 ident: b39 article-title: Fast low-rank modifications of the thin singular value decomposition publication-title: Linear Algebr. Appl. – reference: M. Rahman, T.K. Saha, M.A. Hasan, K.S. Xu, C.K. Reddy, Dylink2vec: Effective feature representation for link prediction in dynamic networks, arXiv preprint – volume: 5 year: 2003 ident: b1 article-title: Overview of the 2003 kdd cup publication-title: ACM SIGKDD Explor. – volume: 1 start-page: 4 year: 2000 ident: b2 article-title: Visualizing social networks publication-title: J. Soc. Struct. – reference: M. Henaff, J. Bruna, Y. LeCun, Deep convolutional networks on graph-structured data, arXiv preprint – start-page: 1145 year: 2016 end-page: 1152 ident: b20 article-title: Deep neural networks for learning graph representations publication-title: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence – year: 1994 ident: b6 article-title: Social Network Analysis: Methods and Applications, Vol. 8 – year: 2018 ident: b7 article-title: Graph embedding techniques, applications, and performance: A survey publication-title: Knowl.-Based Syst. – start-page: 1105 year: 2016 end-page: 1114 ident: b38 article-title: Asymmetric transitivity preserving graph embedding publication-title: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining – start-page: 696 year: 1988 end-page: 699 ident: b35 publication-title: Neurocomputing: Foundations of research – start-page: 177 year: 2005 end-page: 187 ident: b37 article-title: Graphs over time: densification laws, shrinking diameters and possible explanations publication-title: Proceedings of the Eleventh ACM SIGKDD International Conference on Knowledge Discovery in Data Mining – year: 2018 ident: b15 article-title: Dynamic network embedding by modelling triadic closure process publication-title: AAAI – reference: P. Sarkar, D. Chakrabarti, M. Jordan, Nonparametric link prediction in dynamic networks, arXiv preprint – volume: 4 start-page: 1535 year: 2009 end-page: 1550 ident: b3 article-title: Network visualization and analysis of gene expression data using biolayout express3d publication-title: Nat. Protoc. – start-page: 57 year: 2018 end-page: 61 ident: b4 article-title: Recommending teammates with deep neural networks publication-title: Proceedings of the 29th on Hypertext and Social Media – reference: . – start-page: 891 year: 2015 end-page: 900 ident: b12 article-title: Grarep: Learning graph representations with global structural information publication-title: KDD15 – volume: 5 start-page: 10 year: 2011 ident: b30 article-title: Temporal link prediction using matrix and tensor factorizations publication-title: ACM Trans. Knowl. Discov. Data (TKDD) – start-page: 37 year: 2013 end-page: 48 ident: b10 article-title: Distributed large-scale natural graph factorization publication-title: Proceedings of the 22nd International Conference on World Wide Web – reference: P. Goyal, N. Kamra, X. He, Y. Liu, Dyngem: Deep Embedding Method for Dynamic Graphs, arXiv preprint – reference: T.N. Kipf, M. Welling, Variational graph auto-encoders, arXiv preprint – reference: T.N. Kipf, M. Welling, Semi-supervised classification with graph convolutional networks, arXiv preprint – volume: 496 start-page: 121 year: 2018 end-page: 136 ident: b31 article-title: Graph regularized nonnegative matrix factorization for temporal link prediction in dynamic networks publication-title: Physica A – volume: 82 start-page: 8 year: 1987 end-page: 19 ident: b34 article-title: Stochastic blockmodels for directed graphs publication-title: J. Amer. Statist. Assoc. – start-page: 369 year: 2018 end-page: 377 ident: b33 article-title: Streaming link prediction on dynamic attributed networks publication-title: Proceedings of the Eleventh ACM International Conference on Web Search and Data Mining – year: 2016 ident: b29 article-title: Learning continuous-time bayesian networks in relational domains: A non-parametric approach publication-title: Thirtieth AAAI Conference on Artificial Intelligence – volume: 1 start-page: 12 year: 2008 ident: b5 article-title: A survey of visualization tools for biological network analysis publication-title: Biodata Min. – ident: 10.1016/j.knosys.2019.06.024_b17 – year: 2017 ident: 10.1016/j.knosys.2019.06.024_b26 article-title: Dyngem: Deep embedding method for dynamic graphs – start-page: 585 year: 2001 ident: 10.1016/j.knosys.2019.06.024_b18 article-title: Laplacian eigenmaps and spectral techniques for embedding and clustering – year: 2018 ident: 10.1016/j.knosys.2019.06.024_b15 article-title: Dynamic network embedding by modelling triadic closure process – ident: 10.1016/j.knosys.2019.06.024_b23 – volume: 5 issue: 2 year: 2003 ident: 10.1016/j.knosys.2019.06.024_b1 article-title: Overview of the 2003 kdd cup publication-title: ACM SIGKDD Explor. doi: 10.1145/980972.980992 – start-page: 2059 year: 2017 ident: 10.1016/j.knosys.2019.06.024_b32 article-title: A link prediction based approach for recommendation systems – start-page: 177 year: 2005 ident: 10.1016/j.knosys.2019.06.024_b37 article-title: Graphs over time: densification laws, shrinking diameters and possible explanations – volume: 1 start-page: 12 issue: 1 year: 2008 ident: 10.1016/j.knosys.2019.06.024_b5 article-title: A survey of visualization tools for biological network analysis publication-title: Biodata Min. doi: 10.1186/1756-0381-1-12 – start-page: 37 year: 2013 ident: 10.1016/j.knosys.2019.06.024_b10 article-title: Distributed large-scale natural graph factorization – ident: 10.1016/j.knosys.2019.06.024_b21 – ident: 10.1016/j.knosys.2019.06.024_b27 – start-page: 1105 year: 2016 ident: 10.1016/j.knosys.2019.06.024_b38 article-title: Asymmetric transitivity preserving graph embedding – ident: 10.1016/j.knosys.2019.06.024_b28 – volume: 4 start-page: 1535 year: 2009 ident: 10.1016/j.knosys.2019.06.024_b3 article-title: Network visualization and analysis of gene expression data using biolayout express3d publication-title: Nat. Protoc. doi: 10.1038/nprot.2009.177 – year: 2016 ident: 10.1016/j.knosys.2019.06.024_b29 article-title: Learning continuous-time bayesian networks in relational domains: A non-parametric approach – volume: 5 start-page: 10 issue: 2 year: 2011 ident: 10.1016/j.knosys.2019.06.024_b30 article-title: Temporal link prediction using matrix and tensor factorizations publication-title: ACM Trans. Knowl. Discov. Data (TKDD) – start-page: 369 year: 2018 ident: 10.1016/j.knosys.2019.06.024_b33 article-title: Streaming link prediction on dynamic attributed networks – volume: 28 start-page: 2765 issue: 10 year: 2016 ident: 10.1016/j.knosys.2019.06.024_b25 article-title: Scalable temporal latent space inference for link prediction in dynamic social networks publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2016.2591009 – start-page: 696 year: 1988 ident: 10.1016/j.knosys.2019.06.024_b35 – ident: 10.1016/j.knosys.2019.06.024_b16 – volume: 82 start-page: 8 issue: 397 year: 1987 ident: 10.1016/j.knosys.2019.06.024_b34 article-title: Stochastic blockmodels for directed graphs publication-title: J. Amer. Statist. Assoc. doi: 10.1080/01621459.1987.10478385 – year: 1994 ident: 10.1016/j.knosys.2019.06.024_b6 – start-page: 57 year: 2018 ident: 10.1016/j.knosys.2019.06.024_b4 article-title: Recommending teammates with deep neural networks – start-page: 1105 year: 2016 ident: 10.1016/j.knosys.2019.06.024_b9 article-title: Asymmetric transitivity preserving graph embedding – start-page: 701 year: 2014 ident: 10.1016/j.knosys.2019.06.024_b11 article-title: Deepwalk: Online learning of social representations – ident: 10.1016/j.knosys.2019.06.024_b22 – ident: 10.1016/j.knosys.2019.06.024_b24 – volume: 496 start-page: 121 year: 2018 ident: 10.1016/j.knosys.2019.06.024_b31 article-title: Graph regularized nonnegative matrix factorization for temporal link prediction in dynamic networks publication-title: Physica A doi: 10.1016/j.physa.2017.12.092 – start-page: 1225 year: 2016 ident: 10.1016/j.knosys.2019.06.024_b19 article-title: Structural deep network embedding – volume: 415 start-page: 20 issue: 1 year: 2006 ident: 10.1016/j.knosys.2019.06.024_b39 article-title: Fast low-rank modifications of the thin singular value decomposition publication-title: Linear Algebr. Appl. doi: 10.1016/j.laa.2005.07.021 – start-page: 38 year: 2018 ident: 10.1016/j.knosys.2019.06.024_b14 article-title: Embedding networks with edge attributes – start-page: 891 year: 2015 ident: 10.1016/j.knosys.2019.06.024_b12 article-title: Grarep: Learning graph representations with global structural information – start-page: 1067 year: 2015 ident: 10.1016/j.knosys.2019.06.024_b13 article-title: Line: Large-scale information network embedding – start-page: 1145 year: 2016 ident: 10.1016/j.knosys.2019.06.024_b20 article-title: Deep neural networks for learning graph representations – volume: 1 start-page: 4 issue: 1 year: 2000 ident: 10.1016/j.knosys.2019.06.024_b2 article-title: Visualizing social networks publication-title: J. Soc. Struct. – year: 2018 ident: 10.1016/j.knosys.2019.06.024_b7 article-title: Graph embedding techniques, applications, and performance: A survey publication-title: Knowl.-Based Syst. doi: 10.1016/j.knosys.2018.03.022 – ident: 10.1016/j.knosys.2019.06.024_b36 – start-page: 855 year: 2016 ident: 10.1016/j.knosys.2019.06.024_b8 article-title: Node2vec: Scalable feature learning for networks |
| SSID | ssj0002218 |
| Score | 2.6548734 |
| Snippet | Learning graph representations is a fundamental task aimed at capturing various properties of graphs in vector space. The most recent methods learn such... |
| SourceID | proquest crossref elsevier |
| SourceType | Aggregation Database Enrichment Source Index Database Publisher |
| StartPage | 104816 |
| SubjectTerms | Datasets Dynamics Efficacy Embedding Evolution Graph embedding applications Graph embedding techniques Graph representations Graphical representations Graphs Learning Machine learning Networks Performance prediction Predictions Property Python graph embedding methods GEM library Recurrent Stochastic models |
| Title | dyngraph2vec: Capturing network dynamics using dynamic graph representation learning |
| URI | https://dx.doi.org/10.1016/j.knosys.2019.06.024 https://www.proquest.com/docview/2330585971 |
| Volume | 187 |
| WOSCitedRecordID | wos000501653900021&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: PRVESC databaseName: ScienceDirect Freedom Collection - Elsevier customDbUrl: eissn: 1872-7409 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002218 issn: 0950-7051 databaseCode: AIEXJ dateStart: 19950201 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV1Lb9NAEF6FlAMX3qiFgvbAzTKy17vZNbcqKk-pQpBDbsb7ME1SOSFNovLvmX25TQoqIHGxYifrdXY-z3w7mgdCL6kRQpoBS5lig5RKm6wMG-dUlvUANi0sy5V2zSb4yYkYj8tPvd7XmAuzOeNtKy4uysV_FTVcA2Hb1Nm_EHd3U7gAn0HocASxw_GPBK9_tK4KNdkY-1DJsF6sfC5i60O-E-270J8na-coCKeJG5W4KpcxI6mNXSW-XSWxH6MfLrU2UIdq0B05f2s9Ep6dAjXv3M3D01PbvcuHAk0nq-TzfDa7jBOqQd_7lJvl9_UEbLTZ8kiQbMcjcT1VJvgbs5Rnobqs8dpWcKD3NCu31TH_pWr3Xobpq1k7h79lg_JKV3nVp2DvFM3-YqezswE_zQhQ4Ftoj3BWij7aO3p_PP7QWWtCnA-4e7yYXuliAK_P9Tv6smPIHTsZ3Ud3w7YCH3k4PEA90z5E92LLDhw0-CM0uoqO17jDBg7YwBEb2GEjnmI3Bm9jA0dsPEajN8ej4bs0NNZIFajsVUqY0YIXdV5KZvuVFY2QorZ1f2qjlVRUqkwWWkiSF7pszKAxDZU01zrjhvHiCeq389bsI1zShpGG1qzMKDVa2902ZVJxkytSU32AirhclQpF523vk7MqRhdOK7_IlV3kygZZEnqA0m7UwhddueH3PEqiCsTRE8IKwHPDyMMouCq8w_B9AUZQwE47f_rPN36G7ly-Goeov1quzXN0W21Wk_PliwDCnxhroxU |
| linkProvider | Elsevier |
| 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=dyngraph2vec%3A+Capturing+network+dynamics+using+dynamic+graph+representation+learning&rft.jtitle=Knowledge-based+systems&rft.au=Goyal%2C+Palash&rft.au=Chhetri%2C+Sujit+Rokka&rft.au=Canedo%2C+Arquimedes&rft.date=2020-01-01&rft.pub=Elsevier+B.V&rft.issn=0950-7051&rft.eissn=1872-7409&rft.volume=187&rft_id=info:doi/10.1016%2Fj.knosys.2019.06.024&rft.externalDocID=S0950705119302916 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0950-7051&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0950-7051&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0950-7051&client=summon |