NodeHGAE: Node-oriented heterogeneous graph autoencoder
Heterogeneous graph autoencoder (HGAE), as an unsupervised learning approach, aims to encode nodes and edges of heterogeneous graphs into low-dimensional vector representations, and simultaneously reconstruct the original graph structure from node representations. Existing heterogeneous graph encode...
Uloženo v:
| Vydáno v: | Information sciences Ročník 719; s. 122448 |
|---|---|
| Hlavní autoři: | , , , , , |
| Médium: | Journal Article |
| Jazyk: | angličtina |
| Vydáno: |
Elsevier Inc
01.11.2025
|
| Témata: | |
| ISSN: | 0020-0255 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
| Abstract | Heterogeneous graph autoencoder (HGAE), as an unsupervised learning approach, aims to encode nodes and edges of heterogeneous graphs into low-dimensional vector representations, and simultaneously reconstruct the original graph structure from node representations. Existing heterogeneous graph encoders typically follow the metapath paradigm, encoding different semantic information and then employing decoders to reconstruct nodes attributes and edges information. However, the interaction between different semantic structures is underestimated which may lead to loss of semantic information. Moreover, employing graph-level unified attention mechanism to weigh the importance of different semantic structures of nodes is a suboptimal choice. Motivated by these challenges, a novel method named Node-oriented Heterogeneous Graph Autoencoder (NodeHGAE) is proposed. It first aggregates different semantic information based on node neighborhoods and utilizes the Chebyshev function to derive high-order neighborhood information of nodes. Then, low-rank matrix and parameter decoupling are proposed to assign node-specific attention and semantic information is integrated from different levels. Additionally, node-level and graph-level contrastive loss are proposed to redress the noise problem in the process of feature and topology coupling in HGAE. Experiments have shown that NodeHGAE outperforms state-of-the-art methods on four public heterogeneous graph datasets. The code of NodeHGAE can be found at Github.1 |
|---|---|
| AbstractList | Heterogeneous graph autoencoder (HGAE), as an unsupervised learning approach, aims to encode nodes and edges of heterogeneous graphs into low-dimensional vector representations, and simultaneously reconstruct the original graph structure from node representations. Existing heterogeneous graph encoders typically follow the metapath paradigm, encoding different semantic information and then employing decoders to reconstruct nodes attributes and edges information. However, the interaction between different semantic structures is underestimated which may lead to loss of semantic information. Moreover, employing graph-level unified attention mechanism to weigh the importance of different semantic structures of nodes is a suboptimal choice. Motivated by these challenges, a novel method named Node-oriented Heterogeneous Graph Autoencoder (NodeHGAE) is proposed. It first aggregates different semantic information based on node neighborhoods and utilizes the Chebyshev function to derive high-order neighborhood information of nodes. Then, low-rank matrix and parameter decoupling are proposed to assign node-specific attention and semantic information is integrated from different levels. Additionally, node-level and graph-level contrastive loss are proposed to redress the noise problem in the process of feature and topology coupling in HGAE. Experiments have shown that NodeHGAE outperforms state-of-the-art methods on four public heterogeneous graph datasets. The code of NodeHGAE can be found at Github.1 |
| ArticleNumber | 122448 |
| Author | Li, Chao Zhu, Xiangkai Duan, Hua Yan, Yeyu Zeng, Qingtian Zhao, Zhongying |
| Author_xml | – sequence: 1 givenname: Xiangkai orcidid: 0009-0007-0623-7016 surname: Zhu fullname: Zhu, Xiangkai email: 18063597830@163.com organization: School of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao, 266590, China – sequence: 2 givenname: Chao orcidid: 0000-0002-3131-2723 surname: Li fullname: Li, Chao email: lichao@sdust.edu.cn organization: School of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao, 266590, China – sequence: 3 givenname: Yeyu orcidid: 0000-0002-6288-453X surname: Yan fullname: Yan, Yeyu email: yanyeyu-work@foxmail.com organization: Institute of Information Science, Beijing Jiaotong University, Beijing, 100044, China – sequence: 4 givenname: Zhongying surname: Zhao fullname: Zhao, Zhongying email: zzysuin@163.com organization: School of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, 266590, China – sequence: 5 givenname: Hua surname: Duan fullname: Duan, Hua email: huaduan59@163.com organization: College of Mathematics and Systems Science, Shandong University of Science and Technology, Qianwangang Road, Qingdao 266590, Shandong, China – sequence: 6 givenname: Qingtian surname: Zeng fullname: Zeng, Qingtian email: qtzeng@sdust.edu.cn organization: School of Electronic and Information Engineering, Shandong University of Science and Technology, Qingdao, 266590, China |
| BookMark | eNp9j0FOwzAQRb0oEm3hAOxygYSxE9sJrKqqtEgVbGBtOfa4TQRxZadI3B5X6ZrVjEb_jf5bkNngByTkgUJBgYrHvuiGWDBgvKCMVVU9I3MABnm68FuyiLEHgEoKMSfyzVvcbVebp-yy5T50OIxosyOOGPwBB_TnmB2CPh0zfR49Diblwh25cfor4v11Lsnny-Zjvcv379vX9WqfG8bpmDcN11JWwhnmmAXeiNpJW_GWo9RY1caV3ApR87axhqaqDByroawNtg22ZbkkdPprgo8xoFOn0H3r8KsoqIut6lWyVRdbNdkm5nliMBX76TCoaJKVQdsFNKOyvvuH_gNq8GBR |
| Cites_doi | 10.1016/j.ins.2023.02.092 10.1016/j.ins.2023.119139 10.1145/3474379 10.1145/3706115 10.3166/ejc.7.311-327 10.1016/j.eswa.2023.120115 10.1109/TKDE.2024.3377431 10.1109/TKDE.2021.3138788 10.1016/j.ins.2023.03.034 10.1109/TKDE.2021.3101356 |
| ContentType | Journal Article |
| Copyright | 2025 Elsevier Inc. |
| Copyright_xml | – notice: 2025 Elsevier Inc. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.ins.2025.122448 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Library & Information Science |
| ExternalDocumentID | 10_1016_j_ins_2025_122448 S0020025525005808 |
| GroupedDBID | --K --M --Z -~X .DC .~1 0R~ 1B1 1OL 1RT 1~. 1~5 29I 4.4 457 4G. 5GY 5VS 7-5 71M 77I 8P~ 9JN 9JO AAAKF AAAKG AABNK AAEDT AAEDW AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AARIN AATTM AAXKI AAXUO AAYFN AAYWO ABAOU ABBOA ABEFU ABFNM ABJNI ABMAC ABUCO ABWVN ABXDB ACDAQ ACGFS ACLOT ACNNM ACRLP ACRPL ACVFH ACZNC ADBBV ADCNI ADEZE ADGUI ADJOM ADMUD ADNMO ADTZH ADVLN AEBSH AECPX AEIPS AEKER AENEX AEUPX AFFNX AFJKZ AFPUW AFTJW AGHFR AGQPQ AGUBO AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIGII AIGVJ AIIUN AIKHN AITUG AKBMS AKRWK AKYEP ALMA_UNASSIGNED_HOLDINGS AMRAJ ANKPU AOUOD APLSM APXCP ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFKBS 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- 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- ~HD 9DU AAYXX CITATION |
| ID | FETCH-LOGICAL-c251t-995a7746fc2f2d05968f7d45b5e7ae48cf35d6685b9dc144820f28038ceb9eb33 |
| ISICitedReferencesCount | 0 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001523186300005&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 07:00:58 EST 2025 Sat Oct 11 16:51:56 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Heterogeneous graph autoencoder Heterogeneous graph representation learning Graph neural network |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c251t-995a7746fc2f2d05968f7d45b5e7ae48cf35d6685b9dc144820f28038ceb9eb33 |
| ORCID | 0000-0002-3131-2723 0009-0007-0623-7016 0000-0002-6288-453X |
| ParticipantIDs | crossref_primary_10_1016_j_ins_2025_122448 elsevier_sciencedirect_doi_10_1016_j_ins_2025_122448 |
| PublicationCentury | 2000 |
| PublicationDate | November 2025 2025-11-00 |
| PublicationDateYYYYMMDD | 2025-11-01 |
| PublicationDate_xml | – month: 11 year: 2025 text: November 2025 |
| PublicationDecade | 2020 |
| PublicationTitle | Information sciences |
| PublicationYear | 2025 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | Ji, Wang, Shi, Wang, Philip (br0250) 2021; 35 Jin, Huo, Liang, Yang (br0350) 2021 Li, Lu, Wu, Ling (br0120) 2023; 632 Park, Kim, Han, Yu (br0230) 2020 Yang, Wang, Tao, Sun, Liu, Yu, Wang (br0030) 2023 Wang, Li, Yu, Han, Gao, Shen (br0060) 2023 Yang, Guan, Li, Zhao, Cui, Wang (br0300) 2021 Jing, Park, Tong (br0330) 2021 Tan, Liu, Huang, Choi, Li, Chen, Hu (br0160) 2023 He, Wei, Wen (br0280) 2022; 35 Liu, Gao, Ji (br0320) 2020 Liu, Guan, Giunchiglia, Liang, Feng (br0020) 2021 Hou, He, Cen, Liu, Dong, Kharlamov, Tang (br0150) 2023 Suykens (br0360) 2001; 7 Xie, Xu, Chen, Li, Jiang, Su, Wang, Pei (br0090) 2023 Li, Yan, Fu, Zhao, Zeng (br0040) 2023; 632 Simonovsky, Komodakis (br0140) October 2018 Zhuang, Wang, Zhao, Sun (br0210) 2023; 642 Zhang, Li, Zhao (br0180) 2025 Wang, Suo, Wei, Wang, Wang, Dai, Zhang (br0080) 2023; 35 Wang, Liu, Han, Shi (br0240) 2021 Yan, Li, Yu, Li, Zhao (br0290) 2023; 225 Tian, Dong, Zhang, Zhang, Chawla (br0070) 2023 Zheng, Zhu, Liu, Li, Zhao (br0110) 2023 Huo, He, Li, Jin, Dang, Pedrycz, Wu, Zhang (br0190) 2025; 16 Hou, Liu, Cen, Dong, Yang, Wang, Tang (br0310) 2022 Van der Maaten, Hinton (br0370) 2008; 9 Zhang, Li, Huang, Wu, Zhou, Yang, Gao (br0010) 2022; 40 Dong, Chawla, Swami (br0200) 2017 Yu, Ge, Li, Zhou (br0050) 2024 Kipf, Welling (br0260) 2016 Yan, Liu, Wei, Li, Li, Lin (br0100) 2023 Chen, Wu, Wang, Guo (br0170) 2023 Ren, Liu (br0220) 2020 Kipf, Welling (br0130) 2016 Wang, Ji, Shi, Wang, Ye, Cui, Yu (br0270) 2019 Wang, Ji, Shi, Wang, Ye, Cui, Yu (br0340) 2019 He (10.1016/j.ins.2025.122448_br0280) 2022; 35 Yang (10.1016/j.ins.2025.122448_br0030) 2023 Yang (10.1016/j.ins.2025.122448_br0300) 2021 Xie (10.1016/j.ins.2025.122448_br0090) 2023 Wang (10.1016/j.ins.2025.122448_br0340) 2019 Chen (10.1016/j.ins.2025.122448_br0170) 2023 Hou (10.1016/j.ins.2025.122448_br0150) 2023 Dong (10.1016/j.ins.2025.122448_br0200) 2017 Yan (10.1016/j.ins.2025.122448_br0100) 2023 Ren (10.1016/j.ins.2025.122448_br0220) 2020 Hou (10.1016/j.ins.2025.122448_br0310) 2022 Park (10.1016/j.ins.2025.122448_br0230) 2020 Ji (10.1016/j.ins.2025.122448_br0250) 2021; 35 Wang (10.1016/j.ins.2025.122448_br0240) 2021 Jing (10.1016/j.ins.2025.122448_br0330) 2021 Jin (10.1016/j.ins.2025.122448_br0350) 2021 Wang (10.1016/j.ins.2025.122448_br0080) 2023; 35 Liu (10.1016/j.ins.2025.122448_br0020) 2021 Yu (10.1016/j.ins.2025.122448_br0050) 2024 Tan (10.1016/j.ins.2025.122448_br0160) 2023 Kipf (10.1016/j.ins.2025.122448_br0260) 2016 Van der Maaten (10.1016/j.ins.2025.122448_br0370) 2008; 9 Wang (10.1016/j.ins.2025.122448_br0060) 2023 Huo (10.1016/j.ins.2025.122448_br0190) 2025; 16 Zhuang (10.1016/j.ins.2025.122448_br0210) 2023; 642 Li (10.1016/j.ins.2025.122448_br0040) 2023; 632 Li (10.1016/j.ins.2025.122448_br0120) 2023; 632 Simonovsky (10.1016/j.ins.2025.122448_br0140) 2018 Kipf (10.1016/j.ins.2025.122448_br0130) Zheng (10.1016/j.ins.2025.122448_br0110) 2023 Yan (10.1016/j.ins.2025.122448_br0290) 2023; 225 Suykens (10.1016/j.ins.2025.122448_br0360) 2001; 7 Zhang (10.1016/j.ins.2025.122448_br0010) 2022; 40 Liu (10.1016/j.ins.2025.122448_br0320) 2020 Tian (10.1016/j.ins.2025.122448_br0070) 2023 Wang (10.1016/j.ins.2025.122448_br0270) 2019 Zhang (10.1016/j.ins.2025.122448_br0180) 2025 |
| References_xml | – start-page: 338 year: 2020 end-page: 348 ident: br0320 article-title: Towards deeper graph neural networks publication-title: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining – start-page: 594 year: 2022 end-page: 604 ident: br0310 article-title: Graphmae: self-supervised masked graph autoencoders publication-title: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining – start-page: 2874 year: 2023 end-page: 2884 ident: br0090 article-title: Unsupervised anomaly detection on microservice traces through graph vae publication-title: Proceedings of the ACM Web Conference 2023 – year: 2023 ident: br0110 article-title: Node-oriented spectral filtering for graph neural networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2016 ident: br0130 article-title: Variational graph auto-encoders – year: 2020 ident: br0220 article-title: Heterogeneous deep graph infomax publication-title: Workshop of Deep Learning on Graphs: Methodologies and Applications Co-Located with the Thirty-Fourth AAAI Conference on Artificial Intelligence – start-page: 5371 year: 2020 end-page: 5378 ident: br0230 article-title: Unsupervised attributed multiplex network embedding publication-title: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34 – volume: 35 start-page: 7264 year: 2022 end-page: 7276 ident: br0280 article-title: Convolutional neural networks on graphs with Chebyshev approximation, revisited publication-title: Adv. Neural Inf. Process. Syst. – start-page: 4191 year: 2023 end-page: 4198 ident: br0170 article-title: Dual low-rank graph autoencoder for semantic and topological networks publication-title: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37 – start-page: 8142 year: 2021 end-page: 8152 ident: br0020 article-title: Deep attention diffusion graph neural networks for text classification publication-title: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing – start-page: 2414 year: 2021 end-page: 2424 ident: br0330 article-title: Hdmi: high-order deep multiplex infomax publication-title: Proceedings of the Web Conference 2021 – start-page: 9997 year: 2023 end-page: 10005 ident: br0070 article-title: Heterogeneous graph masked autoencoders publication-title: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 37 – start-page: 135 year: 2017 end-page: 144 ident: br0200 article-title: metapath2vec: scalable representation learning for heterogeneous networks publication-title: Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining – start-page: 787 year: 2023 end-page: 795 ident: br0160 article-title: S2gae: self-supervised graph autoencoders are generalizable learners with graph masking publication-title: Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining – year: 2016 ident: br0260 article-title: Semi-supervised classification with graph convolutional networks publication-title: International Conference on Learning Representations – volume: 642 year: 2023 ident: br0210 article-title: Adaptive dual graph contrastive learning based on heterogeneous signed network for predicting adverse drug reaction publication-title: Inf. Sci. – start-page: 1726 year: 2021 end-page: 1736 ident: br0240 article-title: Self-supervised heterogeneous graph neural network with co-contrastive learning publication-title: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining – volume: 225 year: 2023 ident: br0290 article-title: Osgnn: original graph and subgraph aggregated graph neural network publication-title: Expert Syst. Appl. – volume: 632 start-page: 424 year: 2023 end-page: 438 ident: br0040 article-title: Hetregat-fc: heterogeneous residual graph attention network via feature completion publication-title: Inf. Sci. – volume: 7 start-page: 311 year: 2001 end-page: 327 ident: br0360 article-title: Support vector machines: a nonlinear modelling and control perspective publication-title: Eur. J. Control – year: 2024 ident: br0050 article-title: Heterogeneous graph contrastive learning with meta-path contexts and adaptively weighted negative samples publication-title: IEEE Trans. Knowl. Data Eng. – start-page: 5606 year: 2023 end-page: 5618 ident: br0100 article-title: Skeletonmae: graph-based masked autoencoder for skeleton sequence pre-training publication-title: Proceedings of the IEEE/CVF International Conference on Computer Vision – volume: 16 start-page: 1 year: 2025 end-page: 21 ident: br0190 article-title: Heterogeneous graph neural networks using self-supervised reciprocally contrastive learning publication-title: ACM Trans. Intell. Syst. Technol. – start-page: 661 year: 2023 end-page: 669 ident: br0030 article-title: Dgrec: graph neural network for recommendation with diversified embedding generation publication-title: Proceedings of the Sixteenth ACM International Conference on Web Search and Data Mining – volume: 40 start-page: 1 year: 2022 end-page: 29 ident: br0010 article-title: efraudcom: an e-commerce fraud detection system via competitive graph neural networks publication-title: ACM Trans. Inf. Syst. – start-page: 412 year: October 2018 end-page: 422 ident: br0140 article-title: Graphvae: towards generation of small graphs using variational autoencoders publication-title: Artificial Neural Networks and Machine Learning–ICANN 2018: 27th International Conference on Artificial Neural Networks, Rhodes, Greece, October 4-7, 2018, Proceedings, Part I 27 – start-page: 2022 year: 2019 end-page: 2032 ident: br0270 article-title: Heterogeneous graph attention network publication-title: The World Wide Web Conference – start-page: 2022 year: 2019 end-page: 2032 ident: br0340 article-title: Heterogeneous graph attention network publication-title: The World Wide Web Conference – start-page: 737 year: 2023 end-page: 746 ident: br0150 article-title: Graphmae2: a decoding-enhanced masked self-supervised graph learner publication-title: Proceedings of the ACM Web Conference 2023 – start-page: 13269 year: 2025 end-page: 13276 ident: br0180 article-title: Teacher-guided edge discriminator for personalized graph masked autoencoder publication-title: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 39 – start-page: 391 year: 2021 end-page: 400 ident: br0350 article-title: Heterogeneous graph neural network via attribute completion publication-title: Proceedings of the Web Conference 2021 – start-page: 136 year: 2023 end-page: 144 ident: br0060 article-title: Heterogeneous graph contrastive multi-view learning publication-title: Proceedings of the 2023 SIAM International Conference on Data Mining (SDM) – year: 2021 ident: br0300 article-title: Interpretable and efficient heterogeneous graph convolutional network publication-title: IEEE Trans. Knowl. Data Eng. – volume: 9 year: 2008 ident: br0370 article-title: Visualizing data using t-sne publication-title: J. Mach. Learn. Res. – volume: 632 start-page: 439 year: 2023 end-page: 453 ident: br0120 article-title: Multi-view representation model based on graph autoencoder publication-title: Inf. Sci. – volume: 35 start-page: 3938 year: 2023 end-page: 3951 ident: br0080 article-title: Hgate: heterogeneous graph attention auto-encoders publication-title: IEEE Trans. Knowl. Data Eng. – volume: 35 start-page: 521 year: 2021 end-page: 532 ident: br0250 article-title: Heterogeneous graph propagation network publication-title: IEEE Trans. Knowl. Data Eng. – volume: 632 start-page: 439 year: 2023 ident: 10.1016/j.ins.2025.122448_br0120 article-title: Multi-view representation model based on graph autoencoder publication-title: Inf. Sci. doi: 10.1016/j.ins.2023.02.092 – start-page: 136 year: 2023 ident: 10.1016/j.ins.2025.122448_br0060 article-title: Heterogeneous graph contrastive multi-view learning – start-page: 737 year: 2023 ident: 10.1016/j.ins.2025.122448_br0150 article-title: Graphmae2: a decoding-enhanced masked self-supervised graph learner – start-page: 2022 year: 2019 ident: 10.1016/j.ins.2025.122448_br0270 article-title: Heterogeneous graph attention network – year: 2016 ident: 10.1016/j.ins.2025.122448_br0260 article-title: Semi-supervised classification with graph convolutional networks – start-page: 2022 year: 2019 ident: 10.1016/j.ins.2025.122448_br0340 article-title: Heterogeneous graph attention network – volume: 642 year: 2023 ident: 10.1016/j.ins.2025.122448_br0210 article-title: Adaptive dual graph contrastive learning based on heterogeneous signed network for predicting adverse drug reaction publication-title: Inf. Sci. doi: 10.1016/j.ins.2023.119139 – start-page: 2414 year: 2021 ident: 10.1016/j.ins.2025.122448_br0330 article-title: Hdmi: high-order deep multiplex infomax – start-page: 661 year: 2023 ident: 10.1016/j.ins.2025.122448_br0030 article-title: Dgrec: graph neural network for recommendation with diversified embedding generation – start-page: 594 year: 2022 ident: 10.1016/j.ins.2025.122448_br0310 article-title: Graphmae: self-supervised masked graph autoencoders – volume: 40 start-page: 1 issue: 3 year: 2022 ident: 10.1016/j.ins.2025.122448_br0010 article-title: efraudcom: an e-commerce fraud detection system via competitive graph neural networks publication-title: ACM Trans. Inf. Syst. doi: 10.1145/3474379 – start-page: 4191 year: 2023 ident: 10.1016/j.ins.2025.122448_br0170 article-title: Dual low-rank graph autoencoder for semantic and topological networks – volume: 16 start-page: 1 issue: 1 year: 2025 ident: 10.1016/j.ins.2025.122448_br0190 article-title: Heterogeneous graph neural networks using self-supervised reciprocally contrastive learning publication-title: ACM Trans. Intell. Syst. Technol. doi: 10.1145/3706115 – start-page: 5371 year: 2020 ident: 10.1016/j.ins.2025.122448_br0230 article-title: Unsupervised attributed multiplex network embedding – volume: 7 start-page: 311 issue: 2–3 year: 2001 ident: 10.1016/j.ins.2025.122448_br0360 article-title: Support vector machines: a nonlinear modelling and control perspective publication-title: Eur. J. Control doi: 10.3166/ejc.7.311-327 – volume: 9 issue: 11 year: 2008 ident: 10.1016/j.ins.2025.122448_br0370 article-title: Visualizing data using t-sne publication-title: J. Mach. Learn. Res. – start-page: 412 year: 2018 ident: 10.1016/j.ins.2025.122448_br0140 article-title: Graphvae: towards generation of small graphs using variational autoencoders – start-page: 135 year: 2017 ident: 10.1016/j.ins.2025.122448_br0200 article-title: metapath2vec: scalable representation learning for heterogeneous networks – volume: 225 year: 2023 ident: 10.1016/j.ins.2025.122448_br0290 article-title: Osgnn: original graph and subgraph aggregated graph neural network publication-title: Expert Syst. Appl. doi: 10.1016/j.eswa.2023.120115 – year: 2023 ident: 10.1016/j.ins.2025.122448_br0110 article-title: Node-oriented spectral filtering for graph neural networks publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 5606 year: 2023 ident: 10.1016/j.ins.2025.122448_br0100 article-title: Skeletonmae: graph-based masked autoencoder for skeleton sequence pre-training – volume: 35 start-page: 7264 year: 2022 ident: 10.1016/j.ins.2025.122448_br0280 article-title: Convolutional neural networks on graphs with Chebyshev approximation, revisited publication-title: Adv. Neural Inf. Process. Syst. – volume: 35 start-page: 521 issue: 1 year: 2021 ident: 10.1016/j.ins.2025.122448_br0250 article-title: Heterogeneous graph propagation network publication-title: IEEE Trans. Knowl. Data Eng. – start-page: 2874 year: 2023 ident: 10.1016/j.ins.2025.122448_br0090 article-title: Unsupervised anomaly detection on microservice traces through graph vae – start-page: 8142 year: 2021 ident: 10.1016/j.ins.2025.122448_br0020 article-title: Deep attention diffusion graph neural networks for text classification – start-page: 338 year: 2020 ident: 10.1016/j.ins.2025.122448_br0320 article-title: Towards deeper graph neural networks – year: 2024 ident: 10.1016/j.ins.2025.122448_br0050 article-title: Heterogeneous graph contrastive learning with meta-path contexts and adaptively weighted negative samples publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2024.3377431 – start-page: 13269 year: 2025 ident: 10.1016/j.ins.2025.122448_br0180 article-title: Teacher-guided edge discriminator for personalized graph masked autoencoder – start-page: 391 year: 2021 ident: 10.1016/j.ins.2025.122448_br0350 article-title: Heterogeneous graph neural network via attribute completion – ident: 10.1016/j.ins.2025.122448_br0130 – start-page: 787 year: 2023 ident: 10.1016/j.ins.2025.122448_br0160 article-title: S2gae: self-supervised graph autoencoders are generalizable learners with graph masking – start-page: 9997 year: 2023 ident: 10.1016/j.ins.2025.122448_br0070 article-title: Heterogeneous graph masked autoencoders – volume: 35 start-page: 3938 issue: 4 year: 2023 ident: 10.1016/j.ins.2025.122448_br0080 article-title: Hgate: heterogeneous graph attention auto-encoders publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2021.3138788 – start-page: 1726 year: 2021 ident: 10.1016/j.ins.2025.122448_br0240 article-title: Self-supervised heterogeneous graph neural network with co-contrastive learning – volume: 632 start-page: 424 year: 2023 ident: 10.1016/j.ins.2025.122448_br0040 article-title: Hetregat-fc: heterogeneous residual graph attention network via feature completion publication-title: Inf. Sci. doi: 10.1016/j.ins.2023.03.034 – year: 2020 ident: 10.1016/j.ins.2025.122448_br0220 article-title: Heterogeneous deep graph infomax – year: 2021 ident: 10.1016/j.ins.2025.122448_br0300 article-title: Interpretable and efficient heterogeneous graph convolutional network publication-title: IEEE Trans. Knowl. Data Eng. doi: 10.1109/TKDE.2021.3101356 |
| SSID | ssj0004766 |
| Score | 2.4764419 |
| Snippet | Heterogeneous graph autoencoder (HGAE), as an unsupervised learning approach, aims to encode nodes and edges of heterogeneous graphs into low-dimensional... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 122448 |
| SubjectTerms | Graph neural network Heterogeneous graph autoencoder Heterogeneous graph representation learning |
| Title | NodeHGAE: Node-oriented heterogeneous graph autoencoder |
| URI | https://dx.doi.org/10.1016/j.ins.2025.122448 |
| Volume | 719 |
| WOSCitedRecordID | wos001523186300005&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) issn: 0020-0255 databaseCode: AIEXJ dateStart: 19950101 customDbUrl: isFulltext: true dateEnd: 99991231 titleUrlDefault: https://www.sciencedirect.com omitProxy: false ssIdentifier: ssj0004766 providerName: Elsevier |
| link | http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3PT9swFLYY3WE7TNAxrduYfEAcQJnAjuN4twp1A4QqDkXquESJf9B2UlJBM8F_v-fYSdMyJDjsEkVR4kT5Pj1_7_n5PYT2jjSIWm5IoIVQQWiOZJCRKA2OuQL6SBmFpqquf8GHw3g8Fpe-2-hd1U6A53l8fy_m_xVquAZg262zL4C7GRQuwDmADkeAHY7PAn5YKH36sz-wvr49DwpbytgKy4lNfSngQW3zXqtS1YdpuShsLUvls3RndWZ7s6vx0E-Sjfi-npQWmDEQ6-Z3Om1SeqZ--b5oLIkLrv7SD2UrPl3FZq8nRX7zUE-bPupAmN9-17Kk4HZaf6RtSbm3fs4W2jU7V0XzkZl2EYMZ-Ba2Yjph35b3rpbEXpuqmgTCOjdtlsAQiR0icUO8Qh3CmQD71umfDcbnyz2y3K1b199dr3BXuX5r3_FvjdLSHaMt9M47DLjvgN5GGzrvoretMpJdtOs3n-B93MINe7P9HvGaEt_xCiHwCiFwRQjcIsQOuvoxGJ2cBr5hRiBBpi4CIVgKcj4ykhiibGOl2HAVsoxpnuowloYyFUUxy4SS4EmD-jO2O1ksdSZ0RukHtJkXuf6IMAPhbLQ2PDIgmA1NCaVSEE1TGoeSqh46qH9RMnd1UZInQemhsP6JieesE2wJEOLpxz695B2f0ZslT7-gzcVtqXfRa_lnMb27_erZ8BfFdmtN |
| 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=NodeHGAE%3A+Node-oriented+heterogeneous+graph+autoencoder&rft.jtitle=Information+sciences&rft.au=Zhu%2C+Xiangkai&rft.au=Li%2C+Chao&rft.au=Yan%2C+Yeyu&rft.au=Zhao%2C+Zhongying&rft.date=2025-11-01&rft.issn=0020-0255&rft.volume=719&rft.spage=122448&rft_id=info:doi/10.1016%2Fj.ins.2025.122448&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ins_2025_122448 |
| 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 |