T-GAE: A Timespan-aware Graph Attention-based Embedding Model for Temporal Knowledge Graph Completion
Temporal knowledge graphs (TKGs) often suffer from incompleteness, leading to an important research issue: Temporal Knowledge Graph Completion (TKGC). Knowledge Graph Embedding (KGE) methods have proven to be effective in solving this issue. However, most of them handle triples independently and do...
Saved in:
| Published in: | Information sciences Vol. 642; p. 119225 |
|---|---|
| Main Authors: | , , , |
| Format: | Journal Article |
| Language: | English |
| Published: |
Elsevier Inc
01.09.2023
|
| Subjects: | |
| ISSN: | 0020-0255, 1872-6291 |
| Online Access: | Get full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Abstract | Temporal knowledge graphs (TKGs) often suffer from incompleteness, leading to an important research issue: Temporal Knowledge Graph Completion (TKGC). Knowledge Graph Embedding (KGE) methods have proven to be effective in solving this issue. However, most of them handle triples independently and do not capture complex information embedded in the neighborhood topology of central entities. To this end, we propose a Timespan-awareGraphAttention-basedEmbedding Model named T-GAE to tackle the TKGC task. To the best of our knowledge, T-GAE is the first KGE model in which Graph-Attention-Networks (GATs) and Long Short-Term Memory (LSTM) Networks are simultaneously applied to the TKGC task. In essence, our model is an Encoder-Decoder architecture, where the encoder consists of an LSTM network and a GAT network. Firstly, we employ LSTM layers to learn new time-aware relational embeddings to incorporate time information. Then, we utilize these time-aware relational embedding and GATs considered as neighborhood aggregators to learn the entity and relational features of the central entity neighborhoods. Thus, T-GAE can capture the interaction features between multi-relational facts and the abundant temporal information in TKGs. As for the decoder, we choose the ConvKB model, which is essentially a scoring function. Our experiments demonstrate that T-GAE significantly outperforms most of the existing baseline methods for TKGC in terms of MRR and Hit@1/3/10. |
|---|---|
| AbstractList | Temporal knowledge graphs (TKGs) often suffer from incompleteness, leading to an important research issue: Temporal Knowledge Graph Completion (TKGC). Knowledge Graph Embedding (KGE) methods have proven to be effective in solving this issue. However, most of them handle triples independently and do not capture complex information embedded in the neighborhood topology of central entities. To this end, we propose a Timespan-awareGraphAttention-basedEmbedding Model named T-GAE to tackle the TKGC task. To the best of our knowledge, T-GAE is the first KGE model in which Graph-Attention-Networks (GATs) and Long Short-Term Memory (LSTM) Networks are simultaneously applied to the TKGC task. In essence, our model is an Encoder-Decoder architecture, where the encoder consists of an LSTM network and a GAT network. Firstly, we employ LSTM layers to learn new time-aware relational embeddings to incorporate time information. Then, we utilize these time-aware relational embedding and GATs considered as neighborhood aggregators to learn the entity and relational features of the central entity neighborhoods. Thus, T-GAE can capture the interaction features between multi-relational facts and the abundant temporal information in TKGs. As for the decoder, we choose the ConvKB model, which is essentially a scoring function. Our experiments demonstrate that T-GAE significantly outperforms most of the existing baseline methods for TKGC in terms of MRR and Hit@1/3/10. |
| ArticleNumber | 119225 |
| Author | Ma, Zongmin Hou, Xiangning Yan, Li Ma, Ruizhe |
| Author_xml | – sequence: 1 givenname: Xiangning surname: Hou fullname: Hou, Xiangning organization: College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China – sequence: 2 givenname: Ruizhe surname: Ma fullname: Ma, Ruizhe organization: Richard A. Miner School of Computer & Information Sciences, University of Massachusetts Lowell, Lowell, MA 01854, USA – sequence: 3 givenname: Li surname: Yan fullname: Yan, Li organization: College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China – sequence: 4 givenname: Zongmin orcidid: 0000-0001-7780-6473 surname: Ma fullname: Ma, Zongmin email: zongminma@nuaa.edu.cn organization: College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106, China |
| BookMark | eNp90L9OwzAQBnALFYkWeAA2v0CC7cT5A1NUlYIoYgmzZceX4iqxIzui4u1JVFgYOt30u_vuW6GFdRYQuqMkpoRm94fY2BAzwpKY0pIxfoGWtMhZlLGSLtCSEEYiwji_QqsQDoSQNM-yJYI62labB1zh2vQQBmkjeZQe8NbL4RNX4wh2NM5GSgbQeNMr0NrYPX5zGjrcOo9r6AfnZYdfrTt2oPd_eO36oYNZ36DLVnYBbn_nNfp42tTr52j3vn1ZV7uoYWU-RoVUrGUsKTM55Ut1oxqgmgPlKufQTpdBMd6qotBKyYxLSIErYDyHNCsTlVyj_LS38S4ED61ozCjnBKOXphOUiLktcRBTW2JuS5zamiT9Jwdveum_z5rHk4HppS8DXoTGgG1AGw_NKLQzZ_QPMQaF0A |
| CitedBy_id | crossref_primary_10_1016_j_ins_2023_119857 crossref_primary_10_1177_14727978251380802 crossref_primary_10_1016_j_neucom_2025_131067 crossref_primary_10_1016_j_ipm_2024_104001 crossref_primary_10_26599_TST_2023_9010142 crossref_primary_10_1016_j_engappai_2024_109717 crossref_primary_10_1016_j_asoc_2025_113144 crossref_primary_10_1016_j_cosrev_2025_100809 crossref_primary_10_3390_app14198871 crossref_primary_10_1109_TFUZZ_2023_3300295 crossref_primary_10_1016_j_neucom_2024_127680 crossref_primary_10_1016_j_eswa_2025_128016 crossref_primary_10_1016_j_ipm_2024_103848 crossref_primary_10_1016_j_ins_2024_121357 crossref_primary_10_3390_math12091324 crossref_primary_10_1016_j_neucom_2025_129693 crossref_primary_10_1007_s10489_023_05254_4 crossref_primary_10_23919_cje_2024_00_182 crossref_primary_10_3390_app15073727 |
| Cites_doi | 10.1162/neco_a_01199 10.3390/electronics9050750 10.1016/j.knosys.2022.109234 10.18653/v1/2020.emnlp-main.593 10.1002/isaf.1500 10.1609/aaai.v35i7.16802 10.1609/aaai.v29i1.9491 10.18653/v1/2020.emnlp-main.305 10.1007/s10994-013-5363-6 10.18653/v1/2020.emnlp-main.541 10.1609/aaai.v35i5.16604 10.1609/aaai.v34i04.5815 10.1609/aaai.v32i1.11573 10.18653/v1/D15-1082 10.1609/aaai.v28i1.8870 |
| ContentType | Journal Article |
| Copyright | 2023 |
| Copyright_xml | – notice: 2023 |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.ins.2023.119225 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Library & Information Science |
| EISSN | 1872-6291 |
| ExternalDocumentID | 10_1016_j_ins_2023_119225 S0020025523008101 |
| GroupedDBID | --K --M --Z -~X .DC .~1 0R~ 1B1 1OL 1RT 1~. 1~5 29I 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN 9JO AAAKF AAAKG AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AARIN AAXUO AAYFN ABAOU ABBOA ABEFU ABFNM ABJNI ABMAC ABTAH ABUCO ABXDB ABYKQ ACAZW ACDAQ ACGFS ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADTZH AEBSH AECPX AEKER AENEX AFFNX AFKWA AFTJW AGHFR AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIGVJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD APLSM ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HAMUX HLZ HVGLF HZ~ H~9 IHE J1W JJJVA KOM LG9 LY1 M41 MHUIS MO0 MS~ N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SDF SDG SDP SDS SES SEW SPC SPCBC SSB SSD SST SSV SSW SSZ T5K TN5 TWZ UHS WH7 WUQ XPP YYP ZMT ZY4 ~02 ~G- 77I 9DU AATTM AAXKI AAYWO AAYXX ABWVN ACLOT ACRPL ACVFH ADCNI ADNMO ADVLN AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP CITATION EFKBS ~HD |
| ID | FETCH-LOGICAL-c297t-8ab2f22396a0044dcbce1d5e15b75efeddeb25fb88dbba65ae4e5be257e4693b3 |
| ISICitedReferencesCount | 21 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001011529700001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D |
| ISSN | 0020-0255 |
| IngestDate | Sat Nov 29 07:25:59 EST 2025 Tue Nov 18 22:18:50 EST 2025 Fri Feb 23 02:38:29 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Temporal Knowledge Graph Encoder-Decoder architecture Long Short-Term Memory Network Graph Attention Network Temporal Knowledge Graph Completion |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c297t-8ab2f22396a0044dcbce1d5e15b75efeddeb25fb88dbba65ae4e5be257e4693b3 |
| ORCID | 0000-0001-7780-6473 |
| ParticipantIDs | crossref_citationtrail_10_1016_j_ins_2023_119225 crossref_primary_10_1016_j_ins_2023_119225 elsevier_sciencedirect_doi_10_1016_j_ins_2023_119225 |
| PublicationCentury | 2000 |
| PublicationDate | September 2023 2023-09-00 |
| PublicationDateYYYYMMDD | 2023-09-01 |
| PublicationDate_xml | – month: 09 year: 2023 text: September 2023 |
| PublicationDecade | 2020 |
| PublicationTitle | Information sciences |
| PublicationYear | 2023 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | Trouillon, Welbl, Riedel (b0120) 2016 Sun, Deng, Nie (b0080) 2018 Nickel, Rosasco, Poggio (b0075) 2016 Welling, Kipf (b0185) 2016 T. Dettmers, P. Minervini, P. Stenetorp, et al., Convolutional 2D knowledge graph embeddings. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence. 2018. pp. 1811-1818. Diefenbach, Singh, Maret (b0010) 2018 Garcia-Duran, Dumančić, Niepert (b0065) 2018 B. Yang, S.W. Yih, X. He, et al. Embedding Entities and Relations for Learning and Inference in Knowledge Bases. In Proceedings of the 2015 International Conference on Learning Representations, 2015. 2015. Cao, Wang, He (b0005) 2019 Schlichtkrull, Kipf, Bloem (b0135) 2018 Veličković, Cucurull, Casanova (b0095) 2018 Lacroix, Obozinski, Usunier (b0165) 2019 Han, Chen, Ma (b0215) 2021 Perozzi, Al-Rfou, Deepwalk (b0130) 2014 Jain P, Rathi S, Chakrabarti S. Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. 2020: 3733-3747. Vaswani, Shazeer, Parmar (b0190) 2017; 30 C. Zhu, M. Chen, C. Fan, et al., Learning from history: Modeling temporal knowledge graphs with sequential copy-generation networks. In Proceedings of the AAAI Conference on Artificial Intelligence. 2021. pp. 4732-4740. Socher, Chen, Manning (b0055) 2013 Kazemi, Poole (b0125) 2018; 31 Y. Lin, Z. Liu, M. Sun, et al. Learning entity and relation embeddings for knowledge graph completion. In Proceedings of the Twenty-ninth AAAI Conference on Artificial Intelligence. 2015. pp. 2181-2187. A. Sadeghian, M. Armandpour, A. Colas, et al., ChronoR: rotation based temporal knowledge graph embedding. In Proceedings of the AAAI Conference on Artificial Intelligence. 2021. pp. 6471-6479. Ji, He, Xu (b0115) 2015 A. Bordes, N. Usunier, A. Garcia-Duran, et al., Translating embeddings for modeling multi-relational data. Advances in neural information processing systems. 2013. 26. Jørgensen, Igel (b0105) 2021; 28 Z. Han, P. Chen, Y. Ma, et al. DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. 2020: 7301-7316. Zhang, Sheng, Wang (b0145) 2020 Xu, Chen, Nayyeri (b0220) 2021 R. Jenatton, N. Roux, A. Bordes, et al. A latent factor model for highly multi-relational data. Advances in neural information processing systems, 2012. 25. pp. 3176-3184. Dasgupta, Ray, Hyte (b0070) 2018 Fu, Meng, Han (b0195) 2022 L. Feddoul, Semantics-driven Keyword Search over Knowledge Graphs. In DC@ ISWC. 2020. pp. 17-24. Liu, Hua, Xin (b0150) 2020 W. Jin, M. Qu, X. Jin, et al. Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. 2020: 6669-6683. Wu, Cao, Cheung (b0205) 2020 Y. Lin, Z. Liu, H. Luan, et al., Modeling Relation Paths for Representation Learning of Knowledge Bases. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015: 705-714. T.D.N. Dai Quoc Nguyen, D.Q. Nguyen, D. Phung, A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics. 2018. pp. 327-333. Jiang, Liu, Ge (b0140) 2016 Z. Wang, J. Zhang, J. Feng, et al. Knowledge graph embedding by translating on hyperplanes. In Proceedings of the 2014 AAAI Conference on Artificial Intelligence. 2014. pp. 1112-1119. Zhang, Liang, Sheng, Shao (b0225) 2022; 251 Bordes, Glorot, Weston, Bengio (b0050) 2014; 94 R. Goel, S.M. Kazemi, M. Brubaker, et al. Diachronic embedding for temporal knowledge graph completion. In Proceedings of the AAAI Conference on Artificial Intelligence. 2020. pp. 3988-3995. Nickel, Tresp, Kriegel (b0025) 2011 Dai, Wang, Xiong, Guo (b0060) 2020; 9 Yu, Si, Hu, Zhang (b0100) 2019; 31 Vashishth, Sanyal, Nitin (b0210) 2020 Dai (10.1016/j.ins.2023.119225_b0060) 2020; 9 Schlichtkrull (10.1016/j.ins.2023.119225_b0135) 2018 Kazemi (10.1016/j.ins.2023.119225_b0125) 2018; 31 Fu (10.1016/j.ins.2023.119225_b0195) 2022 Han (10.1016/j.ins.2023.119225_b0215) 2021 Wu (10.1016/j.ins.2023.119225_b0205) 2020 10.1016/j.ins.2023.119225_b0180 Vaswani (10.1016/j.ins.2023.119225_b0190) 2017; 30 10.1016/j.ins.2023.119225_b0160 Lacroix (10.1016/j.ins.2023.119225_b0165) 2019 10.1016/j.ins.2023.119225_b0085 10.1016/j.ins.2023.119225_b0040 10.1016/j.ins.2023.119225_b0020 10.1016/j.ins.2023.119225_b0045 Diefenbach (10.1016/j.ins.2023.119225_b0010) 2018 Bordes (10.1016/j.ins.2023.119225_b0050) 2014; 94 Veličković (10.1016/j.ins.2023.119225_b0095) 2018 Jørgensen (10.1016/j.ins.2023.119225_b0105) 2021; 28 10.1016/j.ins.2023.119225_b0200 Perozzi (10.1016/j.ins.2023.119225_b0130) 2014 Xu (10.1016/j.ins.2023.119225_b0220) 2021 Dasgupta (10.1016/j.ins.2023.119225_b0070) 2018 Cao (10.1016/j.ins.2023.119225_b0005) 2019 Welling (10.1016/j.ins.2023.119225_b0185) 2016 Ji (10.1016/j.ins.2023.119225_b0115) 2015 Sun (10.1016/j.ins.2023.119225_b0080) 2018 10.1016/j.ins.2023.119225_b0090 Yu (10.1016/j.ins.2023.119225_b0100) 2019; 31 Liu (10.1016/j.ins.2023.119225_b0150) 2020 10.1016/j.ins.2023.119225_b0170 Vashishth (10.1016/j.ins.2023.119225_b0210) 2020 10.1016/j.ins.2023.119225_b0030 10.1016/j.ins.2023.119225_b0175 Zhang (10.1016/j.ins.2023.119225_b0225) 2022; 251 Jiang (10.1016/j.ins.2023.119225_b0140) 2016 10.1016/j.ins.2023.119225_b0155 10.1016/j.ins.2023.119225_b0110 10.1016/j.ins.2023.119225_b0035 10.1016/j.ins.2023.119225_b0015 Trouillon (10.1016/j.ins.2023.119225_b0120) 2016 Socher (10.1016/j.ins.2023.119225_b0055) 2013 Nickel (10.1016/j.ins.2023.119225_b0025) 2011 Zhang (10.1016/j.ins.2023.119225_b0145) 2020 Nickel (10.1016/j.ins.2023.119225_b0075) 2016 Garcia-Duran (10.1016/j.ins.2023.119225_b0065) 2018 |
| References_xml | – reference: B. Yang, S.W. Yih, X. He, et al. Embedding Entities and Relations for Learning and Inference in Knowledge Bases. In Proceedings of the 2015 International Conference on Learning Representations, 2015. 2015. – reference: A. Sadeghian, M. Armandpour, A. Colas, et al., ChronoR: rotation based temporal knowledge graph embedding. In Proceedings of the AAAI Conference on Artificial Intelligence. 2021. pp. 6471-6479. – year: 2011 ident: b0025 article-title: A three-way model for collective learning on multi-relational data publication-title: Proceedings of the 2011 International Conference on Machine Learning – reference: C. Zhu, M. Chen, C. Fan, et al., Learning from history: Modeling temporal knowledge graphs with sequential copy-generation networks. In Proceedings of the AAAI Conference on Artificial Intelligence. 2021. pp. 4732-4740. – reference: Jain P, Rathi S, Chakrabarti S. Temporal Knowledge Base Completion: New Algorithms and Evaluation Protocols. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. 2020: 3733-3747. – start-page: 701 year: 2014 end-page: 710 ident: b0130 article-title: Online learning of social representations publication-title: Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining – year: 2016 ident: b0185 article-title: Semi-supervised classification with graph convolutional networks publication-title: Proceedings of the 2016 International Conference on Learning Representations – start-page: 2350 year: 2016 end-page: 2354 ident: b0140 article-title: Encoding temporal information for time-aware link prediction publication-title: Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing – start-page: 687 year: 2015 end-page: 696 ident: b0115 article-title: Knowledge graph embedding via dynamic mapping matrix publication-title: Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing – year: 2020 ident: b0210 article-title: Composition-based Multi-Relational Graph Convolutional Networks publication-title: Proceedings of the 2020 International Conference on Learning Representations – year: 2021 ident: b0215 article-title: Explainable subgraph reasoning for forecasting on temporal knowledge graphs publication-title: Proceedings of the 2021 International Conference on Learning Representations – volume: 94 start-page: 233 year: 2014 end-page: 259 ident: b0050 article-title: A semantic matching energy function for learning with multi-relational data publication-title: Machine Learning. – start-page: 1955 year: 2016 end-page: 1961 ident: b0075 article-title: Holographic embeddings of knowledge graphs publication-title: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence – reference: Z. Han, P. Chen, Y. Ma, et al. DyERNIE: Dynamic Evolution of Riemannian Manifold Embeddings for Temporal Knowledge Graph Completion. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. 2020: 7301-7316. – start-page: 2071 year: 2016 end-page: 2080 ident: b0120 article-title: Complex embeddings for simple link prediction publication-title: Proceedings of the 2016 International Conference on Machine Learning – volume: 30 year: 2017 ident: b0190 article-title: Attention is all you need publication-title: Advances in neural information processing systems – year: 2019 ident: b0165 article-title: Tensor decompositions for temporal knowledge base completion publication-title: Proceedings of the 2019 International Conference on Learning Representations – reference: Y. Lin, Z. Liu, H. Luan, et al., Modeling Relation Paths for Representation Learning of Knowledge Bases. In Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing. 2015: 705-714. – reference: L. Feddoul, Semantics-driven Keyword Search over Knowledge Graphs. In DC@ ISWC. 2020. pp. 17-24. – start-page: 4816 year: 2018 end-page: 4821 ident: b0065 article-title: Learning sequence encoders for temporal knowledge graph completion publication-title: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing – start-page: 2001 year: 2018 end-page: 2011 ident: b0070 article-title: Hyperplane-based temporally aware knowledge graph embedding publication-title: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing – reference: T.D.N. Dai Quoc Nguyen, D.Q. Nguyen, D. Phung, A Novel Embedding Model for Knowledge Base Completion Based on Convolutional Neural Network. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics. 2018. pp. 327-333. – volume: 251 start-page: 109234 year: 2022 ident: b0225 article-title: Temporal knowledge graph representation learning with local and global evolutions publication-title: Knowledge-Based Systems – reference: W. Jin, M. Qu, X. Jin, et al. Recurrent Event Network: Autoregressive Structure Inferenceover Temporal Knowledge Graphs. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. 2020: 6669-6683. – volume: 31 start-page: 1235 year: 2019 end-page: 1270 ident: b0100 article-title: A review of recurrent neural networks: LSTM cells and network architectures publication-title: Neural Computation – start-page: 926 year: 2013 end-page: 934 ident: b0055 article-title: Reasoning with neural tensor networks for knowledge base completion publication-title: Proceedings of the 26th International Conference on Neural Information Processing Systems – volume: 31 year: 2018 ident: b0125 article-title: Simple embedding for link prediction in knowledge graphs publication-title: Advances in neural information processing systems – reference: T. Dettmers, P. Minervini, P. Stenetorp, et al., Convolutional 2D knowledge graph embeddings. In Proceedings of the Thirty-Second AAAI Conference on Artificial Intelligence. 2018. pp. 1811-1818. – start-page: 593 year: 2018 end-page: 607 ident: b0135 article-title: Modeling relational data with graph convolutional networks publication-title: Proceedings of the 2018 European Semantic Web Conference – volume: 28 start-page: 159 year: 2021 end-page: 172 ident: b0105 article-title: Machine learning for financial transaction classification across companies using character-level word embeddings of text fields publication-title: Intelligent Systems in Accounting, Finance and Management. – reference: A. Bordes, N. Usunier, A. Garcia-Duran, et al., Translating embeddings for modeling multi-relational data. Advances in neural information processing systems. 2013. 26. – start-page: 2569 year: 2021 end-page: 2578 ident: b0220 article-title: Temporal knowledge graph completion using a linear temporal regularizer and multivector embeddings publication-title: Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies – start-page: 151 year: 2019 end-page: 161 ident: b0005 article-title: Unifying knowledge graph learning and recommendation: towards a better understanding of user preferences publication-title: Proceedings of the 2019 World Wide Web Conference – volume: 9 start-page: 750 year: 2020 ident: b0060 article-title: A survey on knowledge graph embedding: Approaches, applications and benchmarks publication-title: Electronics – year: 2018 ident: b0095 article-title: Graph Attention Networks publication-title: Proceedings of the 2018 International Conference on Learning Representations – start-page: 22 year: 2022 end-page: 31 ident: b0195 article-title: TempCaps: a capsule network-based embedding model for temporal knowledge graph completion publication-title: Proceedings of the Sixth Workshop on Structured Prediction for NLP – year: 2018 ident: b0080 article-title: RotatE: knowledge graph embedding by relational rotation in complex space publication-title: Proceedings of the 2018 International Conference on Learning Representations – start-page: 583 year: 2020 end-page: 598 ident: b0150 article-title: Context-aware temporal knowledge graph embedding publication-title: Proceedings of the 2020 International Conference on Web Information Systems Engineering – start-page: 196 year: 2020 end-page: 211 ident: b0145 article-title: TKGFrame: a two-phase framework for temporal-aware knowledge graph completion publication-title: Proceedings of the 2020 Asia-Pacific Web and Web-Age Information Management Joint International Conference on Web and Big Data – reference: R. Goel, S.M. Kazemi, M. Brubaker, et al. Diachronic embedding for temporal knowledge graph completion. In Proceedings of the AAAI Conference on Artificial Intelligence. 2020. pp. 3988-3995. – start-page: 5730 year: 2020 end-page: 5746 ident: b0205 article-title: TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion publication-title: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing – reference: Y. Lin, Z. Liu, M. Sun, et al. Learning entity and relation embeddings for knowledge graph completion. In Proceedings of the Twenty-ninth AAAI Conference on Artificial Intelligence. 2015. pp. 2181-2187. – reference: R. Jenatton, N. Roux, A. Bordes, et al. A latent factor model for highly multi-relational data. Advances in neural information processing systems, 2012. 25. pp. 3176-3184. – start-page: 1087 year: 2018 end-page: 1091 ident: b0010 article-title: Wdaqua-core1: a question answering service for rdf knowledge bases publication-title: Companion Proceedings of the Web Conference 2018 – reference: Z. Wang, J. Zhang, J. Feng, et al. Knowledge graph embedding by translating on hyperplanes. In Proceedings of the 2014 AAAI Conference on Artificial Intelligence. 2014. pp. 1112-1119. – volume: 31 start-page: 1235 issue: 7 year: 2019 ident: 10.1016/j.ins.2023.119225_b0100 article-title: A review of recurrent neural networks: LSTM cells and network architectures publication-title: Neural Computation doi: 10.1162/neco_a_01199 – volume: 9 start-page: 750 issue: 5 year: 2020 ident: 10.1016/j.ins.2023.119225_b0060 article-title: A survey on knowledge graph embedding: Approaches, applications and benchmarks publication-title: Electronics doi: 10.3390/electronics9050750 – year: 2019 ident: 10.1016/j.ins.2023.119225_b0165 article-title: Tensor decompositions for temporal knowledge base completion – year: 2016 ident: 10.1016/j.ins.2023.119225_b0185 article-title: Semi-supervised classification with graph convolutional networks – volume: 251 start-page: 109234 year: 2022 ident: 10.1016/j.ins.2023.119225_b0225 article-title: Temporal knowledge graph representation learning with local and global evolutions publication-title: Knowledge-Based Systems doi: 10.1016/j.knosys.2022.109234 – ident: 10.1016/j.ins.2023.119225_b0160 doi: 10.18653/v1/2020.emnlp-main.593 – volume: 28 start-page: 159 issue: 3 year: 2021 ident: 10.1016/j.ins.2023.119225_b0105 article-title: Machine learning for financial transaction classification across companies using character-level word embeddings of text fields publication-title: Intelligent Systems in Accounting, Finance and Management. doi: 10.1002/isaf.1500 – ident: 10.1016/j.ins.2023.119225_b0170 doi: 10.1609/aaai.v35i7.16802 – year: 2011 ident: 10.1016/j.ins.2023.119225_b0025 article-title: A three-way model for collective learning on multi-relational data – start-page: 2350 year: 2016 ident: 10.1016/j.ins.2023.119225_b0140 article-title: Encoding temporal information for time-aware link prediction – ident: 10.1016/j.ins.2023.119225_b0020 – year: 2018 ident: 10.1016/j.ins.2023.119225_b0080 article-title: RotatE: knowledge graph embedding by relational rotation in complex space – start-page: 593 year: 2018 ident: 10.1016/j.ins.2023.119225_b0135 article-title: Modeling relational data with graph convolutional networks – volume: 31 year: 2018 ident: 10.1016/j.ins.2023.119225_b0125 article-title: Simple embedding for link prediction in knowledge graphs publication-title: Advances in neural information processing systems – start-page: 2001 year: 2018 ident: 10.1016/j.ins.2023.119225_b0070 article-title: Hyperplane-based temporally aware knowledge graph embedding – ident: 10.1016/j.ins.2023.119225_b0040 doi: 10.1609/aaai.v29i1.9491 – ident: 10.1016/j.ins.2023.119225_b0200 doi: 10.18653/v1/2020.emnlp-main.305 – ident: 10.1016/j.ins.2023.119225_b0045 – ident: 10.1016/j.ins.2023.119225_b0085 – volume: 94 start-page: 233 issue: 2 year: 2014 ident: 10.1016/j.ins.2023.119225_b0050 article-title: A semantic matching energy function for learning with multi-relational data publication-title: Machine Learning. doi: 10.1007/s10994-013-5363-6 – year: 2018 ident: 10.1016/j.ins.2023.119225_b0095 article-title: Graph Attention Networks – ident: 10.1016/j.ins.2023.119225_b0175 doi: 10.18653/v1/2020.emnlp-main.541 – start-page: 2569 year: 2021 ident: 10.1016/j.ins.2023.119225_b0220 article-title: Temporal knowledge graph completion using a linear temporal regularizer and multivector embeddings – start-page: 1087 year: 2018 ident: 10.1016/j.ins.2023.119225_b0010 article-title: Wdaqua-core1: a question answering service for rdf knowledge bases – start-page: 196 year: 2020 ident: 10.1016/j.ins.2023.119225_b0145 article-title: TKGFrame: a two-phase framework for temporal-aware knowledge graph completion – ident: 10.1016/j.ins.2023.119225_b0030 – start-page: 151 year: 2019 ident: 10.1016/j.ins.2023.119225_b0005 article-title: Unifying knowledge graph learning and recommendation: towards a better understanding of user preferences – ident: 10.1016/j.ins.2023.119225_b0180 doi: 10.1609/aaai.v35i5.16604 – ident: 10.1016/j.ins.2023.119225_b0155 doi: 10.1609/aaai.v34i04.5815 – ident: 10.1016/j.ins.2023.119225_b0090 doi: 10.1609/aaai.v32i1.11573 – start-page: 1955 year: 2016 ident: 10.1016/j.ins.2023.119225_b0075 article-title: Holographic embeddings of knowledge graphs – start-page: 701 year: 2014 ident: 10.1016/j.ins.2023.119225_b0130 article-title: Online learning of social representations – start-page: 5730 year: 2020 ident: 10.1016/j.ins.2023.119225_b0205 article-title: TeMP: Temporal Message Passing for Temporal Knowledge Graph Completion – year: 2021 ident: 10.1016/j.ins.2023.119225_b0215 article-title: Explainable subgraph reasoning for forecasting on temporal knowledge graphs – start-page: 583 year: 2020 ident: 10.1016/j.ins.2023.119225_b0150 article-title: Context-aware temporal knowledge graph embedding – ident: 10.1016/j.ins.2023.119225_b0015 – start-page: 926 year: 2013 ident: 10.1016/j.ins.2023.119225_b0055 article-title: Reasoning with neural tensor networks for knowledge base completion – year: 2020 ident: 10.1016/j.ins.2023.119225_b0210 article-title: Composition-based Multi-Relational Graph Convolutional Networks – start-page: 4816 year: 2018 ident: 10.1016/j.ins.2023.119225_b0065 article-title: Learning sequence encoders for temporal knowledge graph completion – start-page: 687 year: 2015 ident: 10.1016/j.ins.2023.119225_b0115 article-title: Knowledge graph embedding via dynamic mapping matrix – volume: 30 year: 2017 ident: 10.1016/j.ins.2023.119225_b0190 article-title: Attention is all you need publication-title: Advances in neural information processing systems – start-page: 2071 year: 2016 ident: 10.1016/j.ins.2023.119225_b0120 article-title: Complex embeddings for simple link prediction – ident: 10.1016/j.ins.2023.119225_b0110 doi: 10.18653/v1/D15-1082 – ident: 10.1016/j.ins.2023.119225_b0035 doi: 10.1609/aaai.v28i1.8870 – start-page: 22 year: 2022 ident: 10.1016/j.ins.2023.119225_b0195 article-title: TempCaps: a capsule network-based embedding model for temporal knowledge graph completion |
| SSID | ssj0004766 |
| Score | 2.511304 |
| Snippet | Temporal knowledge graphs (TKGs) often suffer from incompleteness, leading to an important research issue: Temporal Knowledge Graph Completion (TKGC).... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 119225 |
| SubjectTerms | Encoder-Decoder architecture Graph Attention Network Long Short-Term Memory Network Temporal Knowledge Graph Temporal Knowledge Graph Completion |
| Title | T-GAE: A Timespan-aware Graph Attention-based Embedding Model for Temporal Knowledge Graph Completion |
| URI | https://dx.doi.org/10.1016/j.ins.2023.119225 |
| Volume | 642 |
| WOSCitedRecordID | wos001011529700001&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: Elsevier SD Freedom Collection Journals 2021 customDbUrl: eissn: 1872-6291 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0004766 issn: 0020-0255 databaseCode: AIEXJ dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3Pb9MwFLZg48AOEwwQ2xjyAXEgMmp-OI65RahsgDRxKFLhEsWxO1pt6bSl28Rfz_PPtIUhduASVZHtRP0-v_fsvO8ZoVcwfyh4Uk4a85kxZxkRijFSw8yjA8nSlElz2AQ7Pi7GY_7F7SpdmuMEWNsWNzf8_L9CDfcAbC2dvQPcYVC4Ab8BdLgC7HD9N-DJYTm0gnOj74DpTuprneB1qItTR2XX2RRHoj2YjIZnQkkjbdHnohk5YzSyBatOo89-y8111uZDl-t2YM58HnzQQEbOpYZQ_Wi-0DCOgYYnrfeTZgvcoLuY_vwRuPXNCSGmq42-z9uTM1ch3G1QJGnIwOoFAwOily7LRje3NbWc2YwhzrT6598sut1cmMEyRBdXT9K3fdvV6tlrXi3kGvo0tlkFQ1R6iMoOcR9tJoxyMIWb5cfh-FMvp2X2E7d_b_8x3KQFrr3Hn8OZpRBl9Ahtu7UFLi0nHqN7qt1BW0sVJ3fQgdOp4Nd4CTTsLPwTpAx73uESr3IHG_jxGndw4A423MEwIvbcwYE7rnPPnafo64fh6P0RcSdxkCbhrCNFLZIJBJI8r3UGgGxEo2JJVUwFo2oCT1IioRNRFFKIOqe1yhQVCtyBynKeivQZ2mjnrXqOcNZwGXPdTMqsGeSwwMhNFC3jmlKZ7KKB_0OrxpWp16elnFa3ArmL3oQu57ZGy98aZx6lys0IGzxWwLjbu-3d5Rn76GE_EV6gje5ioQ7Qg-aqm15evHR0-wW7j5rE |
| 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=T-GAE%3A+A+Timespan-aware+Graph+Attention-based+Embedding+Model+for+Temporal+Knowledge+Graph+Completion&rft.jtitle=Information+sciences&rft.au=Hou%2C+Xiangning&rft.au=Ma%2C+Ruizhe&rft.au=Yan%2C+Li&rft.au=Ma%2C+Zongmin&rft.date=2023-09-01&rft.issn=0020-0255&rft.volume=642&rft.spage=119225&rft_id=info:doi/10.1016%2Fj.ins.2023.119225&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ins_2023_119225 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0020-0255&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0020-0255&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0020-0255&client=summon |