Class-aware progressive self-training for learning convolutional networks on graphs
Learning convolutional networks on graphs have been a popular topic for machine learning on graph-structured data and achieved state-of-the-art results on various practical tasks. However, most existing works ignore the impact of per-class distribution, therefore their performance may be limited due...
Saved in:
| Published in | Expert systems with applications Vol. 238; p. 121805 |
|---|---|
| Main Authors | , |
| Format | Journal Article |
| Language | English |
| Published |
Elsevier Ltd
15.03.2024
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 0957-4174 1873-6793 |
| DOI | 10.1016/j.eswa.2023.121805 |
Cover
| Abstract | Learning convolutional networks on graphs have been a popular topic for machine learning on graph-structured data and achieved state-of-the-art results on various practical tasks. However, most existing works ignore the impact of per-class distribution, therefore their performance may be limited due to the diversity of various categories. In this paper, we propose a novel class-aware progressive self-training (CPS) algorithm for training graph convolutional networks (GCNs). Compared to other self-training algorithms for GCNs’ learning, the proposed CPS algorithm leverages the class distribution to update the original graph structure in each self-training loop, including: (a) find these high-confident unlabeled nodes in the graph for each category to add pseudo labels, in order to enlarge the current set of labeled nodes; (b) delete these noisy edges between different classes for graph sparsification. Then, the optimized graph is used for next self-training loops in hopes of enhancing the classification performance. We evaluate the proposed CPS on several datasets commonly used for GCNs’ learning, and the experimental results show that the proposed CPS algorithm outperforms other baselines. |
|---|---|
| AbstractList | Learning convolutional networks on graphs have been a popular topic for machine learning on graph-structured data and achieved state-of-the-art results on various practical tasks. However, most existing works ignore the impact of per-class distribution, therefore their performance may be limited due to the diversity of various categories. In this paper, we propose a novel class-aware progressive self-training (CPS) algorithm for training graph convolutional networks (GCNs). Compared to other self-training algorithms for GCNs’ learning, the proposed CPS algorithm leverages the class distribution to update the original graph structure in each self-training loop, including: (a) find these high-confident unlabeled nodes in the graph for each category to add pseudo labels, in order to enlarge the current set of labeled nodes; (b) delete these noisy edges between different classes for graph sparsification. Then, the optimized graph is used for next self-training loops in hopes of enhancing the classification performance. We evaluate the proposed CPS on several datasets commonly used for GCNs’ learning, and the experimental results show that the proposed CPS algorithm outperforms other baselines. |
| ArticleNumber | 121805 |
| Author | Wu, Weining Chen, Ke |
| Author_xml | – sequence: 1 givenname: Ke surname: Chen fullname: Chen, Ke email: krischen1999@hrbeu.edu.cn – sequence: 2 givenname: Weining orcidid: 0000-0002-3410-4460 surname: Wu fullname: Wu, Weining email: wuweining@hrbeu.edu.cn |
| BookMark | eNp9kM1OwzAQBi1UJNrCC3DKCySsnR8nEhdUAUWqxIHerY29KS7BruzQirenoZw49LTaw3zSzIxNnHfE2C2HjAOv7rYZxQNmAkSeccFrKC_YlNcyTyvZ5BM2haaUacFlccVmMW4BuASQU_a26DHGFA8YKNkFvwkUo91TEqnv0iGgddZtks6HpCcMv4_2bu_7r8F6h33iaDj48BET75JNwN17vGaXHfaRbv7unK2fHteLZbp6fX5ZPKxSnQMMaYOibWtoG1Og5AJMI8uq7LCUwhgwVVXXLUIJDVZSdsDRGCyLXJDu2iLHfM7EaVYHH2OgTu2C_cTwrTiosYraqrGKGquoU5UjVP-DtB1wVBld-_Po_Qmlo9PeUlBRW3KajA2kB2W8PYf_AL3Ogcs |
| CitedBy_id | crossref_primary_10_1109_ACCESS_2024_3394712 |
| Cites_doi | 10.3115/1220835.1220855 10.1609/aaai.v34i04.5747 10.1609/aaai.v32i1.11604 10.1016/j.patcog.2020.107637 10.24963/ijcai.2019/669 10.1145/3186727 10.1609/aaai.v34i04.6048 10.1016/j.knosys.2017.02.014 10.1145/1390156.1390303 10.1145/3394486.3403296 10.1016/j.neucom.2021.08.092 10.1016/j.ins.2022.07.186 10.1609/aaai.v32i1.11691 10.1145/1150402.1150479 10.3115/981658.981684 10.1145/2623330.2623732 10.1016/j.ipm.2020.102443 10.1145/3219819.3220078 |
| ContentType | Journal Article |
| Copyright | 2023 Elsevier Ltd |
| Copyright_xml | – notice: 2023 Elsevier Ltd |
| DBID | AAYXX CITATION |
| DOI | 10.1016/j.eswa.2023.121805 |
| DatabaseName | CrossRef |
| DatabaseTitle | CrossRef |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1873-6793 |
| ExternalDocumentID | 10_1016_j_eswa_2023_121805 S0957417423023072 |
| GrantInformation_xml | – fundername: National Natural Science Foundation of China grantid: 61976067 funderid: http://dx.doi.org/10.13039/501100001809 |
| GroupedDBID | --K --M .DC .~1 0R~ 13V 1B1 1RT 1~. 1~5 4.4 457 4G. 5GY 5VS 7-5 71M 8P~ 9JN 9JO AAAKF AABNK AACTN AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AARIN AAXUO AAYFN ABBOA ABFNM ABMAC ABMVD ABUCO ABYKQ ACDAQ ACGFS ACHRH ACNTT ACRLP ACZNC ADBBV ADEZE ADTZH AEBSH AECPX AEKER AENEX AFKWA AFTJW AGHFR AGJBL AGUBO AGUMN AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJOXV ALEQD ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD APLSM AXJTR BJAXD BKOJK BLXMC BNSAS CS3 DU5 EBS EFJIC EFLBG EO8 EO9 EP2 EP3 F5P FDB FIRID FNPLU FYGXN G-Q GBLVA GBOLZ HAMUX IHE J1W JJJVA KOM LG9 LY1 LY7 M41 MO0 N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. PQQKQ Q38 ROL RPZ SDF SDG SDP SDS SES SEW SPC SPCBC SSB SSD SSL SST SSV SSZ T5K TN5 ~G- 29G AAAKG AAQXK AATTM AAXKI AAYWO AAYXX ABJNI ABKBG ABUFD ABWVN ABXDB ACLOT ACNNM ACRPL ACVFH ADCNI ADJOM ADMUD ADNMO AEIPS AEUPX AFJKZ AFPUW AGQPQ AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP ASPBG AVWKF AZFZN CITATION EFKBS EJD FEDTE FGOYB G-2 HLZ HVGLF HZ~ R2- SBC SET WUQ XPP ZMT ~HD |
| ID | FETCH-LOGICAL-c300t-9a2bb80b9d4a7120d97565fa572dd0d6688ba0509a677f01adda5432ecfb43a3 |
| IEDL.DBID | .~1 |
| ISSN | 0957-4174 |
| IngestDate | Sat Oct 25 05:48:00 EDT 2025 Thu Apr 24 23:08:09 EDT 2025 Fri Feb 23 02:36:06 EST 2024 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | Graph convolution network (GCN) Class distribution Self-training |
| Language | English |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c300t-9a2bb80b9d4a7120d97565fa572dd0d6688ba0509a677f01adda5432ecfb43a3 |
| ORCID | 0000-0002-3410-4460 |
| ParticipantIDs | crossref_primary_10_1016_j_eswa_2023_121805 crossref_citationtrail_10_1016_j_eswa_2023_121805 elsevier_sciencedirect_doi_10_1016_j_eswa_2023_121805 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-03-15 |
| PublicationDateYYYYMMDD | 2024-03-15 |
| PublicationDate_xml | – month: 03 year: 2024 text: 2024-03-15 day: 15 |
| PublicationDecade | 2020 |
| PublicationTitle | Expert systems with applications |
| PublicationYear | 2024 |
| Publisher | Elsevier Ltd |
| Publisher_xml | – name: Elsevier Ltd |
| References | Perozzi, B., Al-Rfou, R., & Skiena, S. (2014). Deepwalk: Online learning of social representations. In Fey, Lenssen (b9) 2019 Paszke, Gross, Chintala, Chanan, Yang, DeVito, Lin, Desmaison, Antiga, Lerer (b22) 2017 Wu, Souza, Zhang, Fifty, Yu, Weinberger (b33) 2019 Yang, Cohen, Salakhudinov (b36) 2016 Veličković, P., Fedus, W., Hamilton, W. L., Liò, P., Bengio, Y., & Hjelm, R. D. (2019). Deep Graph Infomax. In Cui, Wang, Li, Welsch (b7) 2022; 611 Zhao, Wang, Li, Jin, Lang (b39) 2021; 464 (pp. 2847–2856). Zhou, Kantarcioglu, Thuraisingham (b41) 2012 (pp. 3538–3545). Li, R., Wang, S., Zhu, F., & Huang, J. (2018). Adaptive Graph Convolutional Neural Networks. In Xu, B., Hu, W., Leskovec, J., & Jegelka, S. (2019). Graph wavelet neural network. In Rong, Huang, Xu, Huang (b25) 2019 Sen, Getoor (b27) 2006 Bai, Zhang, Torr (b2) 2021; 110 (pp. 631–636). Defferrard, Bresson, Vandergheynst (b8) 2016 Sun, K., Lin, Z., & Zhu, Z. (2020). Multi-stage self-supervised learning for graph convolutional networks on graphs with few labeled nodes. In Weston, J., Ratle, F., & Collobert, R. (2008). Deep learning via semi-supervised embedding. In Leskovec, J., & Faloutsos, C. (2006). Sampling from large graphs. In Rosenberg, Schneiderman, Hebert (b26) 2005 Franceschi, Niepert, Pontil, He (b10) 2019 . Chen, D., Lin, Y., Li, W., Li, P., Zhou, J., & Sun, X. (2020). Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. In Ioannidis, Giannakis (b13) 2019 Szegedy, Zaremba, Sutskever, Bruna, Erhan, Goodfellow, Fergus (b29) 2014 (pp. 189–196). Bianchi, Grattarola, Livi, Alippi (b3) 2022; 44 Atwood, Towsley (b1) 2016 (pp. 3546–3553). Levatić, Ceci, Kocev, Džeroski (b16) 2017; 123 Li, Q., Han, Z., & Wu, X.-m. (2018). Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning. In (pp. 1168–1175). Zügner, D., Akbarnejad, A., & Günnemann, S. (2018). Adversarial attacks on neural networks for graph data. In Zhang, Cui, Wang, Pei, Zhu (b38) 2018 (pp. 152–159). Zheng, Zong, Cheng, Song, Ni, Yu, Chen, Wang (b40) 2020 Liu, Safavi, Dighe, Koutra (b19) 2018; 51 Wu, Wang, Tyshetskiy, Docherty, Lu, Zhu (b34) 2019 (pp. 3438–3445). (pp. 912–919). Kipf, T. N., & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. In McClosky, D., Charniak, E., & Johnson, M. (2006). Effective self-training for parsing. In Yarowsky, D. (1995). Unsupervised word sense disambiguation rivaling supervised methods. In Chen, Zhu, Song (b6) 2018 Pedronette, Latecki (b23) 2021; 58 (pp. 701–710). Zhu, X., Ghahramani, Z., & Lafferty, J. D. (2003). Semi-supervised learning using gaussian fields and harmonic functions. In Hamilton, Ying, Leskovec (b12) 2017 (pp. 5892–5899). Niepert, Ahmed, Kutzkov (b21) 2016 Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2018). Graph attention networks. In Gasteiger, J., Bojchevski, A., & Günnemann, S. (2019). Predict then Propagate: Graph Neural Networks meet Personalized PageRank. In Bruna, J., Zaremba, W., Szlam, A., & LeCun, Y. (2014). Spectral networks and deep locally connected networks on graphs. In Levatić (10.1016/j.eswa.2023.121805_b16) 2017; 123 10.1016/j.eswa.2023.121805_b18 Cui (10.1016/j.eswa.2023.121805_b7) 2022; 611 Szegedy (10.1016/j.eswa.2023.121805_b29) 2014 Bianchi (10.1016/j.eswa.2023.121805_b3) 2022; 44 Niepert (10.1016/j.eswa.2023.121805_b21) 2016 Zhou (10.1016/j.eswa.2023.121805_b41) 2012 Pedronette (10.1016/j.eswa.2023.121805_b23) 2021; 58 Zhao (10.1016/j.eswa.2023.121805_b39) 2021; 464 Atwood (10.1016/j.eswa.2023.121805_b1) 2016 10.1016/j.eswa.2023.121805_b4 10.1016/j.eswa.2023.121805_b5 10.1016/j.eswa.2023.121805_b31 10.1016/j.eswa.2023.121805_b30 10.1016/j.eswa.2023.121805_b11 Sen (10.1016/j.eswa.2023.121805_b27) 2006 10.1016/j.eswa.2023.121805_b32 10.1016/j.eswa.2023.121805_b35 Zhang (10.1016/j.eswa.2023.121805_b38) 2018 Chen (10.1016/j.eswa.2023.121805_b6) 2018 10.1016/j.eswa.2023.121805_b15 10.1016/j.eswa.2023.121805_b37 10.1016/j.eswa.2023.121805_b14 10.1016/j.eswa.2023.121805_b17 Wu (10.1016/j.eswa.2023.121805_b33) 2019 Fey (10.1016/j.eswa.2023.121805_b9) 2019 Zheng (10.1016/j.eswa.2023.121805_b40) 2020 Rosenberg (10.1016/j.eswa.2023.121805_b26) 2005 Yang (10.1016/j.eswa.2023.121805_b36) 2016 Hamilton (10.1016/j.eswa.2023.121805_b12) 2017 Bai (10.1016/j.eswa.2023.121805_b2) 2021; 110 Defferrard (10.1016/j.eswa.2023.121805_b8) 2016 Paszke (10.1016/j.eswa.2023.121805_b22) 2017 Wu (10.1016/j.eswa.2023.121805_b34) 2019 Ioannidis (10.1016/j.eswa.2023.121805_b13) 2019 Liu (10.1016/j.eswa.2023.121805_b19) 2018; 51 10.1016/j.eswa.2023.121805_b20 10.1016/j.eswa.2023.121805_b42 Franceschi (10.1016/j.eswa.2023.121805_b10) 2019 Rong (10.1016/j.eswa.2023.121805_b25) 2019 10.1016/j.eswa.2023.121805_b43 10.1016/j.eswa.2023.121805_b24 10.1016/j.eswa.2023.121805_b28 |
| References_xml | – reference: Weston, J., Ratle, F., & Collobert, R. (2008). Deep learning via semi-supervised embedding. In – reference: Yarowsky, D. (1995). Unsupervised word sense disambiguation rivaling supervised methods. In – start-page: 942 year: 2018 end-page: 950 ident: b6 article-title: Stochastic training of graph convolutional networks with variance reduction publication-title: International conference on machine learning – reference: (pp. 3538–3545). – reference: Xu, B., Hu, W., Leskovec, J., & Jegelka, S. (2019). Graph wavelet neural network. In – reference: (pp. 631–636). – volume: 110 year: 2021 ident: b2 article-title: Hypergraph convolution and hypergraph attention publication-title: Pattern Recognition – year: 2019 ident: b13 article-title: Edge dithering for robust adaptive graph convolutional networks – reference: Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2018). Graph attention networks. In – reference: Li, R., Wang, S., Zhu, F., & Huang, J. (2018). Adaptive Graph Convolutional Neural Networks. In – year: 2014 ident: b29 article-title: Intriguing properties of neural networks – reference: Bruna, J., Zaremba, W., Szlam, A., & LeCun, Y. (2014). Spectral networks and deep locally connected networks on graphs. In – volume: 123 start-page: 41 year: 2017 end-page: 60 ident: b16 article-title: Self-training for multi-target regression with tree ensembles publication-title: Knowledge-Based Systems – reference: (pp. 1168–1175). – start-page: 4816 year: 2019 end-page: 4823 ident: b34 article-title: Adversarial examples for graph data: Deep insights into attack and defense publication-title: Proceedings of the 28th international joint conference on artificial intelligence – volume: 58 year: 2021 ident: b23 article-title: Rank-based self-training for graph convolutional networks publication-title: Information Processing and Management – start-page: 1993 year: 2016 end-page: 2001 ident: b1 article-title: Diffusion-convolutional neural networks publication-title: Advances in neural information processing systems, vol. 29 – start-page: 2014 year: 2016 end-page: 2023 ident: b21 article-title: Learning convolutional neural networks for graphs publication-title: International conference on machine learning – start-page: 1024 year: 2017 end-page: 1034 ident: b12 article-title: Inductive representation learning on large graphs publication-title: Advances in neural information processing systems, vol. 30 – volume: 611 start-page: 18 year: 2022 end-page: 29 ident: b7 article-title: Self-training method based on GCN for semi-supervised short text classification publication-title: Information Sciences – reference: Li, Q., Han, Z., & Wu, X.-m. (2018). Deeper Insights Into Graph Convolutional Networks for Semi-Supervised Learning. In – start-page: 795 year: 2012 end-page: 803 ident: b41 article-title: Self-training with selection-by-rejection publication-title: 2012 IEEE 12th international conference on data mining – reference: Zhu, X., Ghahramani, Z., & Lafferty, J. D. (2003). Semi-supervised learning using gaussian fields and harmonic functions. In – volume: 464 start-page: 394 year: 2021 end-page: 407 ident: b39 article-title: Entropy-aware self-training for graph convolutional networks publication-title: Neurocomputing – reference: (pp. 912–919). – reference: McClosky, D., Charniak, E., & Johnson, M. (2006). Effective self-training for parsing. In – reference: (pp. 5892–5899). – reference: (pp. 3546–3553). – reference: Sun, K., Lin, Z., & Zhu, Z. (2020). Multi-stage self-supervised learning for graph convolutional networks on graphs with few labeled nodes. In – reference: (pp. 189–196). – reference: (pp. 3438–3445). – start-page: 29 year: 2005 end-page: 36 ident: b26 article-title: Semi-supervised self-training of object detection models publication-title: Applications of computer vision and the IEEE workshop on motion and video computing, IEEE workshop on, Vol. 1 – year: 2017 ident: b22 article-title: Automatic differentiation in pytorch – reference: Leskovec, J., & Faloutsos, C. (2006). Sampling from large graphs. In – reference: (pp. 152–159). – start-page: 11458 year: 2020 end-page: 11468 ident: b40 article-title: Robust graph representation learning via neural sparsification publication-title: International conference on machine learning – start-page: 3844 year: 2016 end-page: 3852 ident: b8 article-title: Convolutional neural networks on graphs with fast localized spectral filtering publication-title: Advances in neural information processing systems – year: 2019 ident: b25 article-title: Dropedge: Towards deep graph convolutional networks on node classification – reference: (pp. 701–710). – volume: 51 start-page: 1 year: 2018 end-page: 34 ident: b19 article-title: Graph summarization methods and applications: A survey publication-title: ACM Computing Surveys (CSUR) – reference: Perozzi, B., Al-Rfou, R., & Skiena, S. (2014). Deepwalk: Online learning of social representations. In – start-page: 40 year: 2016 end-page: 48 ident: b36 article-title: Revisiting semi-supervised learning with graph embeddings publication-title: International conference on machine learning – reference: (pp. 2847–2856). – reference: Gasteiger, J., Bojchevski, A., & Günnemann, S. (2019). Predict then Propagate: Graph Neural Networks meet Personalized PageRank. In – volume: 44 start-page: 3496 year: 2022 end-page: 3507 ident: b3 article-title: Graph neural networks with convolutional ARMA filters publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – reference: . – start-page: 1972 year: 2019 end-page: 1982 ident: b10 article-title: Learning discrete structures for graph neural networks publication-title: International conference on machine learning – reference: Zügner, D., Akbarnejad, A., & Günnemann, S. (2018). Adversarial attacks on neural networks for graph data. In – reference: Veličković, P., Fedus, W., Hamilton, W. L., Liò, P., Bengio, Y., & Hjelm, R. D. (2019). Deep Graph Infomax. In – reference: Kipf, T. N., & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. In – start-page: 6861 year: 2019 end-page: 6871 ident: b33 article-title: Simplifying graph convolutional networks publication-title: International conference on machine learning – year: 2019 ident: b9 article-title: Fast graph representation learning with PyTorch geometric – start-page: 777 year: 2006 end-page: 784 ident: b27 article-title: Link-based classification publication-title: Proceedings of the 23rd international conference on machine learning – start-page: 423 year: 2018 end-page: 432 ident: b38 article-title: GaAN: Gated attention networks for learning on large and spatiotemporal graphs publication-title: Proceedings of the 34th conference on uncertainty in artificial intelligence – reference: Chen, D., Lin, Y., Li, W., Li, P., Zhou, J., & Sun, X. (2020). Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. In – start-page: 11458 year: 2020 ident: 10.1016/j.eswa.2023.121805_b40 article-title: Robust graph representation learning via neural sparsification – ident: 10.1016/j.eswa.2023.121805_b30 – year: 2019 ident: 10.1016/j.eswa.2023.121805_b13 – ident: 10.1016/j.eswa.2023.121805_b20 doi: 10.3115/1220835.1220855 – ident: 10.1016/j.eswa.2023.121805_b5 doi: 10.1609/aaai.v34i04.5747 – ident: 10.1016/j.eswa.2023.121805_b17 doi: 10.1609/aaai.v32i1.11604 – volume: 110 issn: 0031-3203 year: 2021 ident: 10.1016/j.eswa.2023.121805_b2 article-title: Hypergraph convolution and hypergraph attention publication-title: Pattern Recognition doi: 10.1016/j.patcog.2020.107637 – start-page: 4816 year: 2019 ident: 10.1016/j.eswa.2023.121805_b34 article-title: Adversarial examples for graph data: Deep insights into attack and defense doi: 10.24963/ijcai.2019/669 – volume: 51 start-page: 1 issue: 3 year: 2018 ident: 10.1016/j.eswa.2023.121805_b19 article-title: Graph summarization methods and applications: A survey publication-title: ACM Computing Surveys (CSUR) doi: 10.1145/3186727 – ident: 10.1016/j.eswa.2023.121805_b28 doi: 10.1609/aaai.v34i04.6048 – year: 2019 ident: 10.1016/j.eswa.2023.121805_b9 – volume: 123 start-page: 41 year: 2017 ident: 10.1016/j.eswa.2023.121805_b16 article-title: Self-training for multi-target regression with tree ensembles publication-title: Knowledge-Based Systems doi: 10.1016/j.knosys.2017.02.014 – start-page: 2014 year: 2016 ident: 10.1016/j.eswa.2023.121805_b21 article-title: Learning convolutional neural networks for graphs – ident: 10.1016/j.eswa.2023.121805_b32 doi: 10.1145/1390156.1390303 – ident: 10.1016/j.eswa.2023.121805_b11 doi: 10.1145/3394486.3403296 – volume: 464 start-page: 394 year: 2021 ident: 10.1016/j.eswa.2023.121805_b39 article-title: Entropy-aware self-training for graph convolutional networks publication-title: Neurocomputing doi: 10.1016/j.neucom.2021.08.092 – ident: 10.1016/j.eswa.2023.121805_b42 – start-page: 1993 year: 2016 ident: 10.1016/j.eswa.2023.121805_b1 article-title: Diffusion-convolutional neural networks – start-page: 777 year: 2006 ident: 10.1016/j.eswa.2023.121805_b27 article-title: Link-based classification – year: 2014 ident: 10.1016/j.eswa.2023.121805_b29 – start-page: 29 year: 2005 ident: 10.1016/j.eswa.2023.121805_b26 article-title: Semi-supervised self-training of object detection models – year: 2017 ident: 10.1016/j.eswa.2023.121805_b22 – start-page: 1024 year: 2017 ident: 10.1016/j.eswa.2023.121805_b12 article-title: Inductive representation learning on large graphs – ident: 10.1016/j.eswa.2023.121805_b4 – volume: 611 start-page: 18 year: 2022 ident: 10.1016/j.eswa.2023.121805_b7 article-title: Self-training method based on GCN for semi-supervised short text classification publication-title: Information Sciences doi: 10.1016/j.ins.2022.07.186 – volume: 44 start-page: 3496 issue: 07 year: 2022 ident: 10.1016/j.eswa.2023.121805_b3 article-title: Graph neural networks with convolutional ARMA filters publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence – start-page: 3844 year: 2016 ident: 10.1016/j.eswa.2023.121805_b8 article-title: Convolutional neural networks on graphs with fast localized spectral filtering – ident: 10.1016/j.eswa.2023.121805_b18 doi: 10.1609/aaai.v32i1.11691 – ident: 10.1016/j.eswa.2023.121805_b15 doi: 10.1145/1150402.1150479 – start-page: 40 year: 2016 ident: 10.1016/j.eswa.2023.121805_b36 article-title: Revisiting semi-supervised learning with graph embeddings – ident: 10.1016/j.eswa.2023.121805_b37 doi: 10.3115/981658.981684 – start-page: 942 year: 2018 ident: 10.1016/j.eswa.2023.121805_b6 article-title: Stochastic training of graph convolutional networks with variance reduction – ident: 10.1016/j.eswa.2023.121805_b24 doi: 10.1145/2623330.2623732 – start-page: 423 year: 2018 ident: 10.1016/j.eswa.2023.121805_b38 article-title: GaAN: Gated attention networks for learning on large and spatiotemporal graphs – start-page: 795 year: 2012 ident: 10.1016/j.eswa.2023.121805_b41 article-title: Self-training with selection-by-rejection – volume: 58 year: 2021 ident: 10.1016/j.eswa.2023.121805_b23 article-title: Rank-based self-training for graph convolutional networks publication-title: Information Processing and Management doi: 10.1016/j.ipm.2020.102443 – ident: 10.1016/j.eswa.2023.121805_b35 – ident: 10.1016/j.eswa.2023.121805_b14 – year: 2019 ident: 10.1016/j.eswa.2023.121805_b25 – ident: 10.1016/j.eswa.2023.121805_b31 – start-page: 1972 year: 2019 ident: 10.1016/j.eswa.2023.121805_b10 article-title: Learning discrete structures for graph neural networks – start-page: 6861 year: 2019 ident: 10.1016/j.eswa.2023.121805_b33 article-title: Simplifying graph convolutional networks – ident: 10.1016/j.eswa.2023.121805_b43 doi: 10.1145/3219819.3220078 |
| SSID | ssj0017007 |
| Score | 2.4478264 |
| Snippet | Learning convolutional networks on graphs have been a popular topic for machine learning on graph-structured data and achieved state-of-the-art results on... |
| SourceID | crossref elsevier |
| SourceType | Enrichment Source Index Database Publisher |
| StartPage | 121805 |
| SubjectTerms | Class distribution Graph convolution network (GCN) Self-training |
| Title | Class-aware progressive self-training for learning convolutional networks on graphs |
| URI | https://dx.doi.org/10.1016/j.eswa.2023.121805 |
| Volume | 238 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVESC databaseName: Baden-Württemberg Complete Freedom Collection (Elsevier) customDbUrl: eissn: 1873-6793 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017007 issn: 0957-4174 databaseCode: GBLVA dateStart: 20110101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVESC databaseName: Elsevier ScienceDirect customDbUrl: eissn: 1873-6793 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017007 issn: 0957-4174 databaseCode: .~1 dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVESC databaseName: ScienceDirect customDbUrl: eissn: 1873-6793 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017007 issn: 0957-4174 databaseCode: ACRLP dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVESC databaseName: ScienceDirect Freedom Collection Journals customDbUrl: eissn: 1873-6793 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017007 issn: 0957-4174 databaseCode: AIKHN dateStart: 19950101 isFulltext: true titleUrlDefault: https://www.sciencedirect.com providerName: Elsevier – providerCode: PRVLSH databaseName: Elsevier Journals customDbUrl: mediaType: online eissn: 1873-6793 dateEnd: 99991231 omitProxy: true ssIdentifier: ssj0017007 issn: 0957-4174 databaseCode: AKRWK dateStart: 19900101 isFulltext: true providerName: Library Specific Holdings |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV3PS8MwFA5jXrz4W_w5cvAmdUmTNs1xDMdU2GUTditJk8pkdGOd7ubfbl6bDgXZwVtb8mj7eH352n75PoTuSJxkPJIMPi_JgCvqthxqCCJpaGIJk1xXbItRPHzlz9No2kL9Zi0M0Cp97697etWt_ZGuz2Z3OZt1xw4cuOkQ_jQCjhbQhzkX4GLw8LWleYD8nKj19kQAo_3CmZrjZcsNaA-FDEQWErCw-2ty-jHhDI7QgUeKuFdfzDFq2eIEHTYuDNg_lKdoXPlaBmqjVhZXdCtgtn5aXNp5HjQWENiBU-wtIt4wcM19zblTFDUVvMSLAlcC1uUZmgweJ_1h4K0SgowRsg6kCrVOiJaGK0FDYqRwSC1XkQiNISaOk0QrkHpRsRA5oa6rqYiz0Ga55kyxc9QuFoW9QFhIQC1UMW0y7uCiNnlMjKKxezFSDi1cItqkKM28jDjcyjxt-GLvKaQ1hbSmdVov0f02ZlmLaOwcHTWZT3-VQuq6_I64q3_GXaN9t8eBWEajG9Rerz7srUMaa92pSqmD9npPL8PRN76Z0dc |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV09T8MwELWqMsDCN6J8emBDoXbixPGIKqoCpUuL1C2yYwcVVWnVFLrx2_ElTgUS6sAWJT4lOV3unp3ndwjdkChOWSgCWF4SHpPUHlnU4IVC09iQQDBVsi0GUe-VPY3DcQN16r0wQKt0ub_K6WW2dmfazpvt-WTSHlpwYMsh_GkEHM1tHt5ioc9hBnb3teZ5gP4crwT3uAfD3c6ZiuRlihWID_kBqCzE0MPur-r0o-J099Gug4r4vnqaA9Qw-SHaq9swYPdVHqFh2djSkyu5MLjkWwG19dPgwkwzr-4BgS06xa5HxBsGsrkLOnuLvOKCF3iW41LBujhGo-7DqNPzXK8ELw0IWXpC-krFRAnNJKc-0YJbqJbJkPtaEx1FcawkaL3IiPOMUJvWZMgC36SZYoEMTlAzn-XmFGEuALZQGSidMosXlc4ioiWN7MxIWrjQQrR2UZI6HXF4lWlSE8beE3BrAm5NKre20O3aZl6paGwcHdaeT37FQmLT_Aa7s3_aXaPt3uiln_QfB8_naMdeYcAyo-EFai4XH-bSwo6luirD6hvFJ9Ns |
| 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=Class-aware+progressive+self-training+for+learning+convolutional+networks+on+graphs&rft.jtitle=Expert+systems+with+applications&rft.au=Chen%2C+Ke&rft.au=Wu%2C+Weining&rft.date=2024-03-15&rft.pub=Elsevier+Ltd&rft.issn=0957-4174&rft.eissn=1873-6793&rft.volume=238&rft_id=info:doi/10.1016%2Fj.eswa.2023.121805&rft.externalDocID=S0957417423023072 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0957-4174&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0957-4174&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0957-4174&client=summon |