Open-world structured sequence learning via dense target encoding
Structured sequences are popularly used to describe graph data with time-evolving node features and edges. A typical real-world scenario of structured sequences is that unknown class labels continuously arrive and thus the training and testing often across different class spaces. This scenario is al...
Gespeichert in:
| Veröffentlicht in: | Information sciences Jg. 680; S. 121147 |
|---|---|
| Hauptverfasser: | , , , , , , , |
| Format: | Journal Article |
| Sprache: | Englisch |
| Veröffentlicht: |
Elsevier Inc
01.10.2024
|
| Schlagworte: | |
| ISSN: | 0020-0255 |
| Online-Zugang: | Volltext |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| Abstract | Structured sequences are popularly used to describe graph data with time-evolving node features and edges. A typical real-world scenario of structured sequences is that unknown class labels continuously arrive and thus the training and testing often across different class spaces. This scenario is also referred to as the open-world learning problem on structured sequences. In this paper, we present a new Dense Open-world Structured Sequence Learning model (DOSSL for short) to learn graph streams in the open-world learning setting. To capture both structural and temporal information, DOSSL uses a GNN-based stochastic recurrent neural network for learning node representation in graph streams, then a truncated Laplacian distribution to describe the latent distribution of graph nodes, and a sampling function is used to generate node representations. Further, DOSSL learns dense target embeddings for the known classes to improve the compactness of known class distribution and reserve enough space for open-world unknown classes. The ultimate open-world classifier is optimized to detect the samples from unknown classes under the constraints of DVAE loss, label loss, class uncertainty loss, and dense target loss. Through empirical analysis conducted on real-world datasets, it has been demonstrated that the advanced technique known as DOSSL exhibits the ability to acquire precise node classifiers by harnessing the power of graph streams.
•We represent an initial endeavor in investigating the open-world learning problem within the context of graph streams. To address this challenge, we introduce a novel dense open-world structured sequence learning model, DOSSL, as a proposed solution.•We effectively solve the technical obstacles pertaining to the temporal and structural dynamics, as well as the fluctuating class labels observed in open-world graph streams. DOSSL employs a recurrent neural network based on GCN, which enables the capturing of both temporal and structural dynamics. To enhance the learning process, stochastic states are introduced alongside the conventional deterministic states within the Gaussian distribution. The stochastic components enable the learning of a latent probabilistic model for each node at every time step.•We enhance the proposed DOSSL model with the learning of dense target embedding. It can change the representation of the target classes and better match the known class space. According to the number of different topological spaces enabled by the type of encoding, dense target encoding avoids the limitation of the space complexity represented by the one-hot target encoding. |
|---|---|
| AbstractList | Structured sequences are popularly used to describe graph data with time-evolving node features and edges. A typical real-world scenario of structured sequences is that unknown class labels continuously arrive and thus the training and testing often across different class spaces. This scenario is also referred to as the open-world learning problem on structured sequences. In this paper, we present a new Dense Open-world Structured Sequence Learning model (DOSSL for short) to learn graph streams in the open-world learning setting. To capture both structural and temporal information, DOSSL uses a GNN-based stochastic recurrent neural network for learning node representation in graph streams, then a truncated Laplacian distribution to describe the latent distribution of graph nodes, and a sampling function is used to generate node representations. Further, DOSSL learns dense target embeddings for the known classes to improve the compactness of known class distribution and reserve enough space for open-world unknown classes. The ultimate open-world classifier is optimized to detect the samples from unknown classes under the constraints of DVAE loss, label loss, class uncertainty loss, and dense target loss. Through empirical analysis conducted on real-world datasets, it has been demonstrated that the advanced technique known as DOSSL exhibits the ability to acquire precise node classifiers by harnessing the power of graph streams.
•We represent an initial endeavor in investigating the open-world learning problem within the context of graph streams. To address this challenge, we introduce a novel dense open-world structured sequence learning model, DOSSL, as a proposed solution.•We effectively solve the technical obstacles pertaining to the temporal and structural dynamics, as well as the fluctuating class labels observed in open-world graph streams. DOSSL employs a recurrent neural network based on GCN, which enables the capturing of both temporal and structural dynamics. To enhance the learning process, stochastic states are introduced alongside the conventional deterministic states within the Gaussian distribution. The stochastic components enable the learning of a latent probabilistic model for each node at every time step.•We enhance the proposed DOSSL model with the learning of dense target embedding. It can change the representation of the target classes and better match the known class space. According to the number of different topological spaces enabled by the type of encoding, dense target encoding avoids the limitation of the space complexity represented by the one-hot target encoding. |
| ArticleNumber | 121147 |
| Author | Chen, Junyang Chen, Xiaojun Zhang, Peng Yu, Zhizhi Zhang, Qin Liu, Ziqi Li, Qincai Xiang, Haolong |
| Author_xml | – sequence: 1 givenname: Qin orcidid: 0000-0002-1449-5046 surname: Zhang fullname: Zhang, Qin email: qinzhang@szu.edu.cn organization: Big Data Institute, College of Computer Science and Software Engineering, ShenZhen University, ShenZhen, 518060, China – sequence: 2 givenname: Ziqi surname: Liu fullname: Liu, Ziqi email: liuziqi2022@email.szu.edu.cn organization: Big Data Institute, College of Computer Science and Software Engineering, ShenZhen University, ShenZhen, 518060, China – sequence: 3 givenname: Qincai surname: Li fullname: Li, Qincai email: liqincai2020@email.szu.edu.cn organization: Big Data Institute, College of Computer Science and Software Engineering, ShenZhen University, ShenZhen, 518060, China – sequence: 4 givenname: Haolong orcidid: 0000-0003-4565-8829 surname: Xiang fullname: Xiang, Haolong email: 200078@nuist.edu.cn organization: School of Software, Nanjing University of Information Science and Technology, NanJing, 210044, China – sequence: 5 givenname: Zhizhi surname: Yu fullname: Yu, Zhizhi email: yuzhizhi@tju.edu.cn organization: College of Intelligence and Computing, Tianjin University, Tianjin, 300350, China – sequence: 6 givenname: Junyang surname: Chen fullname: Chen, Junyang email: junyangchen@szu.edu.cn organization: Big Data Institute, College of Computer Science and Software Engineering, ShenZhen University, ShenZhen, 518060, China – sequence: 7 givenname: Peng surname: Zhang fullname: Zhang, Peng email: p.zhang@gzhu.edu.cn organization: Cyberspace Institute of Advanced Technology, Guangzhou University, Guangzhou, 510006, China – sequence: 8 givenname: Xiaojun surname: Chen fullname: Chen, Xiaojun email: xjchen@szu.edu.cn organization: Big Data Institute, College of Computer Science and Software Engineering, ShenZhen University, ShenZhen, 518060, China |
| BookMark | eNp9j8tqwzAQRbVIoUnaD-jOP2B39LBs01UIfUEgm3YtZGkcZFw5leyU_n1t3HVWd-Byhns2ZOV7j4Q8UMgoUPnYZs7HjAETGWWUimJF1gAMUmB5fks2MbYAIAop12R3PKNPf_rQ2SQOYTTDGHA68XtEbzDpUAfv_Cm5OJ1Y9BGTQYcTDslU93Zq7shNo7uI9_-5JZ8vzx_7t_RwfH3f7w6pYaIa0rJu0FZVyctC1LoseAUNUiYamtdCcMwLjiCFKJEXYJnhUjaQo5BY1dKImm8JXf6a0McYsFHn4L50-FUU1OytWjV5q9lbLd4T87QwOA27OAwqGjd7WRfQDMr27gr9B3xcZDw |
| Cites_doi | 10.1186/s40537-023-00760-1 10.1109/TPAMI.2015.2487986 10.1007/s00362-008-0183-7 10.1109/TASLP.2020.2983593 10.1016/0010-0285(73)90017-0 10.1016/j.ipm.2023.103292 10.1162/neco.2007.11-06-397 10.1109/5.58325 10.1109/TPAMI.2022.3200384 10.1016/j.patcog.2019.107000 10.1016/j.ipm.2020.102433 10.1007/s11633-020-1243-2 10.1109/TPAMI.2020.3045079 10.1016/j.imavis.2018.04.004 |
| ContentType | Journal Article |
| Copyright | 2024 Elsevier Inc. |
| Copyright_xml | – notice: 2024 Elsevier Inc. |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.ins.2024.121147 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Library & Information Science |
| ExternalDocumentID | 10_1016_j_ins_2024_121147 S0020025524010612 |
| 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 AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AARIN AAXUO AAYFN ABAOU ABBOA ABEFU ABFNM ABJNI ABMAC ABTAH ABUCO ABXDB 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 AJOXV AKRWK ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD APLSM ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC 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 AKYEP ANKPU APXCP CITATION EFKBS EFLBG ~HD |
| ID | FETCH-LOGICAL-c249t-8bfed9983874ba87390fe124f15b443e573e06448e370d2c366f05e46e9b6c4b3 |
| ISICitedReferencesCount | 1 |
| ISICitedReferencesURI | http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001302683400001&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 02:44:15 EST 2025 Sat Aug 24 15:41:23 EDT 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Dense target encoding Open-world learning Structured sequence Dynamical variational autoencoders |
| Language | English |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-c249t-8bfed9983874ba87390fe124f15b443e573e06448e370d2c366f05e46e9b6c4b3 |
| ORCID | 0000-0002-1449-5046 0000-0003-4565-8829 |
| ParticipantIDs | crossref_primary_10_1016_j_ins_2024_121147 elsevier_sciencedirect_doi_10_1016_j_ins_2024_121147 |
| PublicationCentury | 2000 |
| PublicationDate | October 2024 2024-10-00 |
| PublicationDateYYYYMMDD | 2024-10-01 |
| PublicationDate_xml | – month: 10 year: 2024 text: October 2024 |
| PublicationDecade | 2020 |
| PublicationTitle | Information sciences |
| PublicationYear | 2024 |
| Publisher | Elsevier Inc |
| Publisher_xml | – name: Elsevier Inc |
| References | Manessi, Rozza, Manzo (br0150) 2020; 97 Li, Yu, Zhu, Chen, Yu, Zheng, Tian, Wu, Meng (br0040) 2023 Chen, Peng, Wang, Tian (br0330) 2021; 44 Park, Kim, Kim (br0430) 2019 Xu, Cheng, Luo, Liu, Zhang (br0020) 2019 Li, Zhao, Gan, Cai, Liu, Mu, Sun (br0070) 2021; 58 Perera, Morariu, Jain, Manjunatha, Wigington, Ordonez, Patel (br0120) 2020 Zheng, Chen, Huang (br0240) 2020; 28 Sun, Yang, Zhang, Ling, Peng (br0050) 2020 Ma, Guo, Ren, Tang, Yin (br0080) 2020 Liu, Liang, Zhao, Tu, Zhou, Gan, Liu, He (br0220) 2024 Wang, Wang, Shan, Chen (br0340) 2017 Arslan (br0460) 2010; 51 You, Du, Leskovec (br0030) 2022 Akata, Perronnin, Harchaoui, Schmid (br0270) 2015; 38 Cavalin, Ribeiro, Appel, Pinhanez (br0280) 2020 Sato, Yamada (br0320) 1995; 8 Chen, Qiao, Shi, Peng, Li, Huang, Pu, Tian (br0400) 2020 Fan, Yao, Joe-Wong (br0180) 2021 Joseph, Khan, Khan, Balasubramanian (br0110) 2021 Bendale, Boult (br0230) 2016 Huang, Wang, Hu, Cheng (br0410) 2022 Yang, Zhang, Yin, Yang, Liu (br0290) 2020 Ritter, Botev, Barber (br0440) 2018 Hamilton, Ying, Leskovec (br0470) 2017; 30 Zhang, Li, Lu, Qiu, Pan, Chen, Chen (br0260) 2024; 38 Almeida, Brás, Sargento, Pinto (br0010) 2023; 10 Rosch (br0300) 1973; 4 Valin, Büthe, Mustafa (br0450) 2023 Rodríguez, Bautista, Gonzalez, Escalera (br0140) 2018; 75 Gao (br0420) 2008; 20 Huang, Lei (br0200) 2023; 60 Sankar, Wu, Gou, Zhang, Yang (br0190) 2020 Fraccaro, Sønderby, Paquet, Winther (br0370) 2016; 29 Zhang, Li, Chen, Zhang, Pan, Fournier-Viger, Huang (br0060) 2022 Pinhanez, Cavalin (br0130) 2022 Huang, Poursafaei, Danovitch, Fey, Hu, Rossi, Leskovec, Bronstein, Rabusseau, Rabbany (br0210) 2024; 36 Kipf, Welling (br0360) 2017 Wu, Pan, Zhu (br0090) 2021 Pareja, Domeniconi, Chen, Ma, Suzumura, Kanezashi, Kaler, Schardl, Leiserson (br0170) 2020 Li, Zhao, Botta, Ionescu, Hu (br0390) 2020 Kohonen (br0310) 1990; 78 Zhang, Shi, Zhang, Chen, Fournier-Viger, Pan (br0100) 2023 Domański (br0380) 2020; 17 Snell, Swersky, Zemel (br0350) 2017; 30 Yan, Fan, Li, Liu, Zhang, Wu, Lam (br0250) 2020 Rossi, Chamberlain, Frasca, Eynard, Monti, Bronstein (br0160) 2020 Veličković, Cucurull, Casanova, Romero, Liò, Bengio (br0480) 2018 Chen (10.1016/j.ins.2024.121147_br0330) 2021; 44 Huang (10.1016/j.ins.2024.121147_br0210) 2024; 36 Kohonen (10.1016/j.ins.2024.121147_br0310) 1990; 78 Zhang (10.1016/j.ins.2024.121147_br0260) 2024; 38 Li (10.1016/j.ins.2024.121147_br0070) 2021; 58 Li (10.1016/j.ins.2024.121147_br0040) 2023 Kipf (10.1016/j.ins.2024.121147_br0360) 2017 Akata (10.1016/j.ins.2024.121147_br0270) 2015; 38 Arslan (10.1016/j.ins.2024.121147_br0460) 2010; 51 Fan (10.1016/j.ins.2024.121147_br0180) 2021 Liu (10.1016/j.ins.2024.121147_br0220) 2024 Sato (10.1016/j.ins.2024.121147_br0320) 1995; 8 Ritter (10.1016/j.ins.2024.121147_br0440) 2018 Valin (10.1016/j.ins.2024.121147_br0450) 2023 Perera (10.1016/j.ins.2024.121147_br0120) 2020 Zhang (10.1016/j.ins.2024.121147_br0100) 2023 Huang (10.1016/j.ins.2024.121147_br0410) 2022 Veličković (10.1016/j.ins.2024.121147_br0480) 2018 Huang (10.1016/j.ins.2024.121147_br0200) 2023; 60 Wu (10.1016/j.ins.2024.121147_br0090) 2021 Almeida (10.1016/j.ins.2024.121147_br0010) 2023; 10 Yang (10.1016/j.ins.2024.121147_br0290) 2020 Joseph (10.1016/j.ins.2024.121147_br0110) 2021 Manessi (10.1016/j.ins.2024.121147_br0150) 2020; 97 Bendale (10.1016/j.ins.2024.121147_br0230) 2016 You (10.1016/j.ins.2024.121147_br0030) 2022 Ma (10.1016/j.ins.2024.121147_br0080) 2020 Zhang (10.1016/j.ins.2024.121147_br0060) 2022 Snell (10.1016/j.ins.2024.121147_br0350) 2017; 30 Rossi (10.1016/j.ins.2024.121147_br0160) Zheng (10.1016/j.ins.2024.121147_br0240) 2020; 28 Hamilton (10.1016/j.ins.2024.121147_br0470) 2017; 30 Rodríguez (10.1016/j.ins.2024.121147_br0140) 2018; 75 Li (10.1016/j.ins.2024.121147_br0390) 2020 Sankar (10.1016/j.ins.2024.121147_br0190) 2020 Xu (10.1016/j.ins.2024.121147_br0020) 2019 Domański (10.1016/j.ins.2024.121147_br0380) 2020; 17 Gao (10.1016/j.ins.2024.121147_br0420) 2008; 20 Yan (10.1016/j.ins.2024.121147_br0250) 2020 Wang (10.1016/j.ins.2024.121147_br0340) 2017 Fraccaro (10.1016/j.ins.2024.121147_br0370) 2016; 29 Rosch (10.1016/j.ins.2024.121147_br0300) 1973; 4 Park (10.1016/j.ins.2024.121147_br0430) 2019 Pinhanez (10.1016/j.ins.2024.121147_br0130) Chen (10.1016/j.ins.2024.121147_br0400) 2020 Sun (10.1016/j.ins.2024.121147_br0050) 2020 Pareja (10.1016/j.ins.2024.121147_br0170) 2020 Cavalin (10.1016/j.ins.2024.121147_br0280) 2020 |
| References_xml | – volume: 36 year: 2024 ident: br0210 article-title: Temporal graph benchmark for machine learning on temporal graphs publication-title: Adv. Neural Inf. Process. Syst. – volume: 29 year: 2016 ident: br0370 article-title: Sequential neural models with stochastic layers publication-title: Adv. Neural Inf. Process. Syst. – start-page: 8588 year: 2023 end-page: 8596 ident: br0040 article-title: Scaling up dynamic graph representation learning via spiking neural networks publication-title: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 37 – start-page: 1060 year: 2021 end-page: 1065 ident: br0180 article-title: Gcn-se: attention as explainability for node classification in dynamic graphs publication-title: 2021 IEEE International Conference on Data Mining (ICDM) – start-page: 3947 year: 2019 end-page: 3953 ident: br0020 article-title: Spatio-temporal attentive rnn for node classification in temporal attributed graphs publication-title: IJCAI – start-page: 1 year: 2021 end-page: 26 ident: br0090 article-title: Openwgl: open-world graph learning for unseen class node classification publication-title: Knowl. Inf. Syst. – year: 2020 ident: br0160 article-title: Temporal graph networks for deep learning on dynamic graphs – year: 2020 ident: br0290 article-title: Convolutional prototype network for open set recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 10 start-page: 83 year: 2023 ident: br0010 article-title: Time series big data: a survey on data stream frameworks, analysis and algorithms publication-title: J. Big Data – volume: 58 year: 2021 ident: br0070 article-title: Robust adaptive semi-supervised classification method based on dynamic graph and self-paced learning publication-title: Inf. Process. Manag. – volume: 20 start-page: 555 year: 2008 end-page: 572 ident: br0420 article-title: Robust l1 principal component analysis and its bayesian variational inference publication-title: Neural Comput. – start-page: 5830 year: 2021 end-page: 5840 ident: br0110 article-title: Towards open world object detection publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – start-page: 5032 year: 2019 end-page: 5041 ident: br0430 article-title: Variational Laplace autoencoders publication-title: International Conference on Machine Learning, PMLR – year: 2022 ident: br0130 article-title: Exploring the advantages of dense-vector to one-hot encoding of intent classes in out-of-scope detection tasks – start-page: 11814 year: 2020 end-page: 11823 ident: br0120 article-title: Generative-discriminative feature representations for open-set recognition publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – year: 2018 ident: br0480 article-title: Graph attention networks publication-title: International Conference on Learning Representations – volume: 75 start-page: 21 year: 2018 end-page: 31 ident: br0140 article-title: Beyond one-hot encoding: lower dimensional target embedding publication-title: Image Vis. Comput. – start-page: 1 year: 2023 end-page: 5 ident: br0450 article-title: Low-bitrate redundancy coding of speech using a rate-distortion-optimized variational autoencoder publication-title: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) – start-page: 1563 year: 2016 end-page: 1572 ident: br0230 article-title: Towards open set deep networks publication-title: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition – year: 2018 ident: br0440 article-title: A scalable Laplace approximation for neural networks publication-title: 6th International Conference on Learning Representations, ICLR 2018-Conference Track Proceedings, Vol. 6, International Conference on Representation Learning – year: 2022 ident: br0410 article-title: Class-specific semantic reconstruction for open set recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – volume: 8 year: 1995 ident: br0320 article-title: Generalized learning vector quantization publication-title: Adv. Neural Inf. Process. Syst. – volume: 44 start-page: 8065 year: 2021 end-page: 8081 ident: br0330 article-title: Adversarial reciprocal points learning for open set recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 3952 year: 2020 end-page: 3961 ident: br0280 article-title: Improving out-of-scope detection in intent classification by using embeddings of the word graph space of the classes publication-title: Empirical Methods in Natural Language Processing (EMNLP) – start-page: 1050 year: 2020 end-page: 1060 ident: br0250 article-title: Unknown intent detection using gaussian mixture model with an application to zero-shot intent classification publication-title: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics – volume: 17 start-page: 788 year: 2020 end-page: 811 ident: br0380 article-title: Study on statistical outlier detection and labelling publication-title: Int. J. Autom. Comput. – year: 2024 ident: br0220 article-title: Self-supervised temporal graph learning with temporal and structural intensity alignment publication-title: IEEE Trans. Neural Netw. Learn. Syst. – start-page: 2358 year: 2022 end-page: 2366 ident: br0030 article-title: Roland: graph learning framework for dynamic graphs publication-title: Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining – start-page: 507 year: 2020 end-page: 522 ident: br0400 article-title: Learning open set network with discriminative reciprocal points publication-title: European Conference on Computer Vision – volume: 38 start-page: 9350 year: 2024 end-page: 9358 ident: br0260 article-title: Rog publication-title: Proc. AAAI Conf. Artif. Intell. – start-page: 703 year: 2022 end-page: 712 ident: br0060 article-title: A dynamic variational framework for open-world node classification in structured sequences publication-title: 2022 IEEE International Conference on Data Mining (ICDM) – start-page: 4576 year: 2023 end-page: 4583 ident: br0100 article-title: G2pxy: generative open-set node classification on graphs with proxy unknowns publication-title: Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23, International Joint Conferences on Artificial Intelligence Organization – start-page: 13480 year: 2020 end-page: 13489 ident: br0050 article-title: Conditional gaussian distribution learning for open set recognition publication-title: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition – volume: 28 start-page: 1198 year: 2020 end-page: 1209 ident: br0240 article-title: Out-of-domain detection for natural language understanding in dialog systems publication-title: IEEE/ACM Trans. Audio Speech Lang. Process. – start-page: 719 year: 2020 end-page: 728 ident: br0080 article-title: Streaming graph neural networks publication-title: Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval – volume: 78 start-page: 1464 year: 1990 end-page: 1480 ident: br0310 article-title: The self-organizing map publication-title: Proc. IEEE – start-page: 344 year: 2017 end-page: 360 ident: br0340 article-title: Prototype discriminative learning for face image set classification publication-title: Asian Conference on Computer Vision – volume: 51 start-page: 865 year: 2010 end-page: 887 ident: br0460 article-title: An alternative multivariate skew Laplace distribution: properties and estimation publication-title: Stat. Pap. – start-page: 5363 year: 2020 end-page: 5370 ident: br0170 article-title: Evolvegcn: evolving graph convolutional networks for dynamic graphs publication-title: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 34 – start-page: 519 year: 2020 end-page: 527 ident: br0190 article-title: Dysat: deep neural representation learning on dynamic graphs via self-attention networks publication-title: Proceedings of the 13th International Conference on Web Search and Data Mining – volume: 60 year: 2023 ident: br0200 article-title: Temporal group-aware graph diffusion networks for dynamic link prediction publication-title: Inf. Process. Manag. – volume: 4 start-page: 328 year: 1973 end-page: 350 ident: br0300 article-title: Natural categories publication-title: Cogn. Psychol. – volume: 38 start-page: 1425 year: 2015 end-page: 1438 ident: br0270 article-title: Label-embedding for image classification publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – year: 2017 ident: br0360 article-title: Semi-supervised classification with graph convolutional networks publication-title: International Conference on Learning Representations – volume: 30 year: 2017 ident: br0350 article-title: Prototypical networks for few-shot learning publication-title: Adv. Neural Inf. Process. Syst. – volume: 30 year: 2017 ident: br0470 article-title: Inductive representation learning on large graphs publication-title: Adv. Neural Inf. Process. Syst. – volume: 97 year: 2020 ident: br0150 article-title: Dynamic graph convolutional networks publication-title: Pattern Recognit. – start-page: 1118 year: 2020 end-page: 1123 ident: br0390 article-title: Copod: copula-based outlier detection publication-title: 2020 IEEE International Conference on Data Mining (ICDM) – year: 2017 ident: 10.1016/j.ins.2024.121147_br0360 article-title: Semi-supervised classification with graph convolutional networks – start-page: 5032 year: 2019 ident: 10.1016/j.ins.2024.121147_br0430 article-title: Variational Laplace autoencoders – volume: 10 start-page: 83 issue: 1 year: 2023 ident: 10.1016/j.ins.2024.121147_br0010 article-title: Time series big data: a survey on data stream frameworks, analysis and algorithms publication-title: J. Big Data doi: 10.1186/s40537-023-00760-1 – start-page: 344 year: 2017 ident: 10.1016/j.ins.2024.121147_br0340 article-title: Prototype discriminative learning for face image set classification – volume: 38 start-page: 1425 issue: 7 year: 2015 ident: 10.1016/j.ins.2024.121147_br0270 article-title: Label-embedding for image classification publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2015.2487986 – volume: 51 start-page: 865 issue: 4 year: 2010 ident: 10.1016/j.ins.2024.121147_br0460 article-title: An alternative multivariate skew Laplace distribution: properties and estimation publication-title: Stat. Pap. doi: 10.1007/s00362-008-0183-7 – volume: 30 year: 2017 ident: 10.1016/j.ins.2024.121147_br0470 article-title: Inductive representation learning on large graphs publication-title: Adv. Neural Inf. Process. Syst. – start-page: 4576 year: 2023 ident: 10.1016/j.ins.2024.121147_br0100 article-title: G2pxy: generative open-set node classification on graphs with proxy unknowns – ident: 10.1016/j.ins.2024.121147_br0160 – volume: 28 start-page: 1198 year: 2020 ident: 10.1016/j.ins.2024.121147_br0240 article-title: Out-of-domain detection for natural language understanding in dialog systems publication-title: IEEE/ACM Trans. Audio Speech Lang. Process. doi: 10.1109/TASLP.2020.2983593 – volume: 38 start-page: 9350 issue: 8 year: 2024 ident: 10.1016/j.ins.2024.121147_br0260 article-title: RogPL: robust open-set graph learning via region-based prototype learning publication-title: Proc. AAAI Conf. Artif. Intell. – volume: 4 start-page: 328 issue: 3 year: 1973 ident: 10.1016/j.ins.2024.121147_br0300 article-title: Natural categories publication-title: Cogn. Psychol. doi: 10.1016/0010-0285(73)90017-0 – volume: 30 year: 2017 ident: 10.1016/j.ins.2024.121147_br0350 article-title: Prototypical networks for few-shot learning publication-title: Adv. Neural Inf. Process. Syst. – start-page: 13480 year: 2020 ident: 10.1016/j.ins.2024.121147_br0050 article-title: Conditional gaussian distribution learning for open set recognition – start-page: 2358 year: 2022 ident: 10.1016/j.ins.2024.121147_br0030 article-title: Roland: graph learning framework for dynamic graphs – volume: 60 issue: 3 year: 2023 ident: 10.1016/j.ins.2024.121147_br0200 article-title: Temporal group-aware graph diffusion networks for dynamic link prediction publication-title: Inf. Process. Manag. doi: 10.1016/j.ipm.2023.103292 – year: 2018 ident: 10.1016/j.ins.2024.121147_br0440 article-title: A scalable Laplace approximation for neural networks – start-page: 1 year: 2021 ident: 10.1016/j.ins.2024.121147_br0090 article-title: Openwgl: open-world graph learning for unseen class node classification publication-title: Knowl. Inf. Syst. – start-page: 1060 year: 2021 ident: 10.1016/j.ins.2024.121147_br0180 article-title: Gcn-se: attention as explainability for node classification in dynamic graphs – volume: 8 year: 1995 ident: 10.1016/j.ins.2024.121147_br0320 article-title: Generalized learning vector quantization publication-title: Adv. Neural Inf. Process. Syst. – volume: 44 start-page: 8065 issue: 11 year: 2021 ident: 10.1016/j.ins.2024.121147_br0330 article-title: Adversarial reciprocal points learning for open set recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. – start-page: 1563 year: 2016 ident: 10.1016/j.ins.2024.121147_br0230 article-title: Towards open set deep networks – start-page: 8588 year: 2023 ident: 10.1016/j.ins.2024.121147_br0040 article-title: Scaling up dynamic graph representation learning via spiking neural networks – volume: 20 start-page: 555 issue: 2 year: 2008 ident: 10.1016/j.ins.2024.121147_br0420 article-title: Robust l1 principal component analysis and its bayesian variational inference publication-title: Neural Comput. doi: 10.1162/neco.2007.11-06-397 – start-page: 519 year: 2020 ident: 10.1016/j.ins.2024.121147_br0190 article-title: Dysat: deep neural representation learning on dynamic graphs via self-attention networks – start-page: 5830 year: 2021 ident: 10.1016/j.ins.2024.121147_br0110 article-title: Towards open world object detection – year: 2018 ident: 10.1016/j.ins.2024.121147_br0480 article-title: Graph attention networks – start-page: 1 year: 2023 ident: 10.1016/j.ins.2024.121147_br0450 article-title: Low-bitrate redundancy coding of speech using a rate-distortion-optimized variational autoencoder – start-page: 1050 year: 2020 ident: 10.1016/j.ins.2024.121147_br0250 article-title: Unknown intent detection using gaussian mixture model with an application to zero-shot intent classification – start-page: 5363 year: 2020 ident: 10.1016/j.ins.2024.121147_br0170 article-title: Evolvegcn: evolving graph convolutional networks for dynamic graphs – start-page: 3947 year: 2019 ident: 10.1016/j.ins.2024.121147_br0020 article-title: Spatio-temporal attentive rnn for node classification in temporal attributed graphs – start-page: 719 year: 2020 ident: 10.1016/j.ins.2024.121147_br0080 article-title: Streaming graph neural networks – volume: 78 start-page: 1464 issue: 9 year: 1990 ident: 10.1016/j.ins.2024.121147_br0310 article-title: The self-organizing map publication-title: Proc. IEEE doi: 10.1109/5.58325 – year: 2022 ident: 10.1016/j.ins.2024.121147_br0410 article-title: Class-specific semantic reconstruction for open set recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2022.3200384 – volume: 97 year: 2020 ident: 10.1016/j.ins.2024.121147_br0150 article-title: Dynamic graph convolutional networks publication-title: Pattern Recognit. doi: 10.1016/j.patcog.2019.107000 – year: 2024 ident: 10.1016/j.ins.2024.121147_br0220 article-title: Self-supervised temporal graph learning with temporal and structural intensity alignment publication-title: IEEE Trans. Neural Netw. Learn. Syst. – start-page: 507 year: 2020 ident: 10.1016/j.ins.2024.121147_br0400 article-title: Learning open set network with discriminative reciprocal points – start-page: 1118 year: 2020 ident: 10.1016/j.ins.2024.121147_br0390 article-title: Copod: copula-based outlier detection – volume: 58 issue: 1 year: 2021 ident: 10.1016/j.ins.2024.121147_br0070 article-title: Robust adaptive semi-supervised classification method based on dynamic graph and self-paced learning publication-title: Inf. Process. Manag. doi: 10.1016/j.ipm.2020.102433 – volume: 17 start-page: 788 issue: 6 year: 2020 ident: 10.1016/j.ins.2024.121147_br0380 article-title: Study on statistical outlier detection and labelling publication-title: Int. J. Autom. Comput. doi: 10.1007/s11633-020-1243-2 – year: 2020 ident: 10.1016/j.ins.2024.121147_br0290 article-title: Convolutional prototype network for open set recognition publication-title: IEEE Trans. Pattern Anal. Mach. Intell. doi: 10.1109/TPAMI.2020.3045079 – ident: 10.1016/j.ins.2024.121147_br0130 – volume: 75 start-page: 21 year: 2018 ident: 10.1016/j.ins.2024.121147_br0140 article-title: Beyond one-hot encoding: lower dimensional target embedding publication-title: Image Vis. Comput. doi: 10.1016/j.imavis.2018.04.004 – start-page: 703 year: 2022 ident: 10.1016/j.ins.2024.121147_br0060 article-title: A dynamic variational framework for open-world node classification in structured sequences – start-page: 3952 year: 2020 ident: 10.1016/j.ins.2024.121147_br0280 article-title: Improving out-of-scope detection in intent classification by using embeddings of the word graph space of the classes – start-page: 11814 year: 2020 ident: 10.1016/j.ins.2024.121147_br0120 article-title: Generative-discriminative feature representations for open-set recognition – volume: 29 year: 2016 ident: 10.1016/j.ins.2024.121147_br0370 article-title: Sequential neural models with stochastic layers publication-title: Adv. Neural Inf. Process. Syst. – volume: 36 year: 2024 ident: 10.1016/j.ins.2024.121147_br0210 article-title: Temporal graph benchmark for machine learning on temporal graphs publication-title: Adv. Neural Inf. Process. Syst. |
| SSID | ssj0004766 |
| Score | 2.4565854 |
| Snippet | Structured sequences are popularly used to describe graph data with time-evolving node features and edges. A typical real-world scenario of structured... |
| SourceID | crossref elsevier |
| SourceType | Index Database Publisher |
| StartPage | 121147 |
| SubjectTerms | Dense target encoding Dynamical variational autoencoders Open-world learning Structured sequence |
| Title | Open-world structured sequence learning via dense target encoding |
| URI | https://dx.doi.org/10.1016/j.ins.2024.121147 |
| Volume | 680 |
| WOSCitedRecordID | wos001302683400001&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 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/eLvHCXMwtV3NS8MwFA-6edCD6FScOslBPFgqXZN-HYdM1MNQmLBbabJUukOd7oP9-b40STunA3fwUkpo05D36_tIXn4PoSv4wcDKu22bucK3acQ53BHfZilJiBsysDJJUWwi6PXCwSB61uWOJkU5gSDPw8UiGv-rqKENhC2Pzm4g7rJTaIB7EDpcQexw_ZPgZYqIXRChWoocdiZTzE3KtCkT8WbNs8QCpTMRlsoGtySlZWnJRibDvTzdaGljWTrh5VrzS1bl9WSzYrsj-8iqJv0MT8q2QaZffUhA-epP6rUHl5ZZbNVZAGhwFdGu0ae-Ks2kNaKkkFOcmj-UtVo3GEGEIXnTXXpbPfudGHvFYJVphCZDbRRDF7HsIlZdbKO6G3gRKOp657E7eKpOygZq99qM2-xzFxl_K-P43VNZ8j76B2hfhw24o8R9iLZE3kB7S2SSDdTSR1DwNV6SGtbK-wh1KmDgChjYAAMbYGAABi6AgRUwsAHGMXq97_bvHmxdQMPmEFVP7ZClYgjxNAkDypIwIJGTCnDo0rbHKCXCC4hwZIAuSOAMXU58P3U8QX0RMZ9TRk5QLX_PxSnCQhL1scQR7SiknLBItFPfY4TwUDCI2ZvoxkxWPFY8KfFa8TQRNdMZa-wqBy4GaKx_7WyTb5yj3QqxF6gG8ypaaIfPp9nk81Lj4gvXvXG_ |
| 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=Open-world+structured+sequence+learning+via+dense+target+encoding&rft.jtitle=Information+sciences&rft.au=Zhang%2C+Qin&rft.au=Liu%2C+Ziqi&rft.au=Li%2C+Qincai&rft.au=Xiang%2C+Haolong&rft.date=2024-10-01&rft.issn=0020-0255&rft.volume=680&rft.spage=121147&rft_id=info:doi/10.1016%2Fj.ins.2024.121147&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ins_2024_121147 |
| 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 |