{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T17:31:18Z","timestamp":1767720678463,"version":"3.37.3"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,1,18]],"date-time":"2022-01-18T00:00:00Z","timestamp":1642464000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2022,1,18]],"date-time":"2022-01-18T00:00:00Z","timestamp":1642464000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Complex Intell. Syst."],"published-print":{"date-parts":[[2023,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Several deep models were proposed in image processing, data interpretation, speech recognition, and video analysis. Most of these architectures need a massive proportion of training samples and use arbitrary configuration. This paper constructs a deep learning architecture with feature learning. Graph convolution networks (GCNs), semi-supervised learning and graph data representation, have become increasingly popular as cost-effective and efficient methods. Most existing merging node descriptions for node distribution on the graph use stabilised neighbourhood knowledge, typically requiring a significant amount of variables and a high degree of computational complexity. To address these concerns, this research presents DLM-SSC, a unique method semi-supervised node classification tasks that can combine knowledge from multiple neighbourhoods at the same time by integrating high-order convolution and feature learning. This paper employs two function learning techniques for reducing the number of parameters and hidden layers: modified marginal fisher analysis (MMFA) and kernel principal component analysis (KPCA). The MMFA and KPCA weight matrices are modified layer by layer when implementing the DLM, a supervised pretraining technique that doesn't require a lot of information. Free measuring on citation datasets (Citeseer, Pubmed, and Cora) and other data sets demonstrate that the suggested approaches outperform similar algorithms.<\/jats:p>","DOI":"10.1007\/s40747-022-00641-9","type":"journal-article","created":{"date-parts":[[2022,1,18]],"date-time":"2022-01-18T09:17:50Z","timestamp":1642497470000},"page":"3011-3021","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Deep learning model construction for a semi-supervised classification with feature learning"],"prefix":"10.1007","volume":"9","author":[{"given":"Sridhar","family":"Mandapati","sequence":"first","affiliation":[]},{"given":"Seifedine","family":"Kadry","sequence":"additional","affiliation":[]},{"given":"R. Lakshmana","family":"Kumar","sequence":"additional","affiliation":[]},{"given":"Krongkarn","family":"Sutham","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1664-0059","authenticated-orcid":false,"given":"Orawit","family":"Thinnukool","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,1,18]]},"reference":[{"key":"641_CR1","doi-asserted-by":"publisher","first-page":"19143","DOI":"10.1109\/ACCESS.2019.2896880","volume":"7","author":"AB Nassif","year":"2019","unstructured":"Nassif AB, Shahin I, Attili I, Azzeh M, Shaalan K (2019) Speech recognition using deep neural networks: a systematic review. IEEE Access 7:19143\u201319165","journal-title":"IEEE Access"},{"issue":"10","key":"641_CR2","doi-asserted-by":"publisher","first-page":"2733","DOI":"10.1109\/JBHI.2020.3001216","volume":"24","author":"H Jelodar","year":"2020","unstructured":"Jelodar H, Wang Y, Orji R, Huang S (2020) Deep sentiment classification and topic discovery on novel coronavirus or COVID-19 online discussions: NLP using LSTM recurrent neural network approach. IEEE J Biomed Health Inform 24(10):2733\u20132742","journal-title":"IEEE J Biomed Health Inform"},{"key":"641_CR3","first-page":"5693","volume":"2019","author":"K Sun","year":"2019","unstructured":"Sun K, Xiao B, Liu DS, Wang JD (2019) Deep, high-resolution representation learning for human pose estimation. Proc CVPR 2019:5693\u20135703","journal-title":"Proc CVPR"},{"key":"641_CR4","doi-asserted-by":"publisher","first-page":"410","DOI":"10.1016\/j.patrec.2020.08.005","volume":"138","author":"M Wang","year":"2020","unstructured":"Wang M, Du X, Shu X, Wang X, Tang J (2020) Deep supervised feature selection for social relationship recognition\". Pattern Recogn Lett 138:410\u2013416","journal-title":"Pattern Recogn Lett"},{"issue":"9","key":"641_CR5","doi-asserted-by":"publisher","first-page":"100142","DOI":"10.1016\/j.patter.2020.100142","volume":"1","author":"W Gao","year":"2020","unstructured":"Gao W, Pooja Mahajan S, Sulam J, Gray JJ (2020) Deep learning in protein structural modeling and design. Patterns 1(9):100142","journal-title":"Patterns"},{"issue":"2","key":"641_CR6","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1016\/j.joi.2019.02.011","volume":"13","author":"A Abrishami","year":"2019","unstructured":"Abrishami A, Aliakbary S (2019) Predicting citation counts based on deep neural network learning techniques. J Informetr 13(2):485\u2013499","journal-title":"J Informetr"},{"issue":"2","key":"641_CR7","doi-asserted-by":"publisher","first-page":"1138","DOI":"10.1109\/TITS.2019.2963722","volume":"22","author":"K Guo","year":"2021","unstructured":"Guo K et al (2021) Optimized graph convolution recurrent neural network for traffic prediction. IEEE Trans Intell Transp Syst 22(2):1138\u20131149","journal-title":"IEEE Trans Intell Transp Syst"},{"key":"641_CR8","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/j.neunet.2020.04.016","volume":"127","author":"M Tavassoli Kejani","year":"2020","unstructured":"Tavassoli Kejani M, Dornaika F, Talebi H (2020) Graph convolution networks with manifold regularisation for semi-supervised learning. Neural Netw 127:160\u2013167","journal-title":"Neural Netw"},{"key":"641_CR9","doi-asserted-by":"publisher","first-page":"201752","DOI":"10.1109\/ACCESS.2020.3035886","volume":"8","author":"NI Kajla","year":"2020","unstructured":"Kajla NI, Missen MMS, Luqman MM, Coustaty M, Mehmood A, Choi GS (2020) Additive angular margin loss in deep graph neural network classifier for learning graph edit distance. IEEE Access 8:201752\u2013201761","journal-title":"IEEE Access"},{"issue":"1","key":"641_CR10","doi-asserted-by":"publisher","first-page":"43","DOI":"10.23919\/JSC.2021.0001","volume":"2","author":"W Gu","year":"2021","unstructured":"Gu W, Gao F, Li R, Zhang J (2021) Learning universal network representation via link prediction by graph convolutional neural network. J Soc Comput 2(1):43\u201351","journal-title":"J Soc Comput"},{"key":"641_CR11","doi-asserted-by":"crossref","unstructured":"Li Q, Han Z, Wu X-M (2018) Deeper insights into graph convolutional networks for semi-supervised learning. In: Proc. AAAI, pp 1\u20138","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"641_CR12","unstructured":"Atwood J, Towsley D (2016) Diffusion-convolutional neural networks [online]. http:\/\/arxiv.org\/abs\/1511.02136v2"},{"key":"641_CR13","doi-asserted-by":"publisher","first-page":"170578","DOI":"10.1109\/ACCESS.2019.2955487","volume":"7","author":"P Gong","year":"2019","unstructured":"Gong P, Ai L (2019) Neighborhood adaptive graph convolutional network for node classification. IEEE Access 7:170578\u2013170588","journal-title":"IEEE Access"},{"key":"641_CR14","doi-asserted-by":"crossref","unstructured":"Zhang M, Cui Z, Neumann M, Chen Y (2018) An end-to-end deep learning architecture for graph classification. In: Proc. AAAI, pp. 1\u20138","DOI":"10.1609\/aaai.v32i1.11782"},{"key":"641_CR15","doi-asserted-by":"publisher","first-page":"148226","DOI":"10.1109\/ACCESS.2020.3015838","volume":"8","author":"N Jia","year":"2020","unstructured":"Jia N, Tian X, Zhang Y, Wang F (2020) Semi-supervised node classification with discriminable squeeze excitation graph convolutional networks. IEEE Access 8:148226\u2013148236","journal-title":"IEEE Access"},{"key":"641_CR16","doi-asserted-by":"crossref","unstructured":"Zhong G, Chherawala Y, Cheriet M (2013) An empirical evaluation of supervised dimensionality reduction for recognition. In: ICDAR, pp 1315\u20131319","DOI":"10.1109\/ICDAR.2013.266"},{"key":"641_CR17","doi-asserted-by":"crossref","unstructured":"Shen Y, Traganitis PA, Giannakis GB (2018) Graph-adaptive non-linear dimensionality reduction. Unknown Journal","DOI":"10.1109\/CAMSAP.2017.8313127"},{"key":"641_CR18","unstructured":"Abu-El-Haija S, Kapoor A, Perozzi B, Lee L (2019) N-GCN: multi-scale graph convolution for semi-supervised node classification. In: Proc. UAI, pp 1\u20139"},{"key":"641_CR19","doi-asserted-by":"crossref","unstructured":"Wu J, He J, Xu J (2019) Demo-Net: degree-specific graph neural networks for node and graph classification. http:\/\/arxiv.org\/abs\/1906.02319","DOI":"10.1145\/3292500.3330950"},{"key":"641_CR20","doi-asserted-by":"publisher","first-page":"31268","DOI":"10.1109\/ACCESS.2021.3060173","volume":"9","author":"X Liu","year":"2021","unstructured":"Liu X, Xia G, Lei F, Zhang Y, Chang S (2021) Higher-order graph convolutional networks with multi-scale neighborhood pooling for semi-supervised node classification. IEEE Access 9:31268\u201331275","journal-title":"IEEE Access"},{"key":"641_CR21","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1016\/j.eswa.2019.07.006","volume":"137","author":"B Li","year":"2019","unstructured":"Li B, Pi D (2019) Learning deep neural networks for node classification. Expert Syst Appl 137:324\u2013334","journal-title":"Expert Syst Appl"},{"key":"641_CR22","doi-asserted-by":"crossref","unstructured":"Molokwu BC, Shuvo SB, Kar NC, Kobti Z (2020) Node classification in complex social graphs via knowledge-graph embeddings and convolutional neural network. In: International conference on computational science\u2014ICCS 2020, vol 12142. Springer, pp. 183\u2013198","DOI":"10.1007\/978-3-030-50433-5_15"},{"issue":"10","key":"641_CR23","doi-asserted-by":"publisher","first-page":"1164","DOI":"10.3390\/e22101164","volume":"22","author":"K Madhawa","year":"2020","unstructured":"Madhawa K, Murata T (2020) Active learning for node classification: an evaluation. Entropy 22(10):1164","journal-title":"Entropy"},{"issue":"10","key":"641_CR24","doi-asserted-by":"publisher","first-page":"2222","DOI":"10.1109\/TNNLS.2014.2359471","volume":"26","author":"Y Yuan","year":"2015","unstructured":"Yuan Y, Mou L, Lu X (2015) Scene recognition by manifold regularized deep learning architecture. IEEE Trans Neural Netw Learn Syst 26(10):2222\u20132233","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"641_CR25","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/j.neunet.2020.04.016","volume":"127","author":"MT Kejani","year":"2020","unstructured":"Kejani MT, Dornaika F, Talebi H (2020) Graph convolution networks with manifold regularisation for semi-supervised learning. Neural Netw 127:160\u2013167","journal-title":"Neural Netw"},{"key":"641_CR26","doi-asserted-by":"publisher","first-page":"107425","DOI":"10.1016\/j.patcog.2020.107425","volume":"107","author":"R Zhu","year":"2020","unstructured":"Zhu R, Dornaika F, Ruichek Y (2020) Semi-supervised elastic manifold embedding with deep learning architecture. Pattern Recogn 107:107425","journal-title":"Pattern Recogn"},{"key":"641_CR27","unstructured":"George T, Konstantinos B, Stefanos Z, Schuller BW (2014) A deep semi-NMF model for learning hidden representations. In: ICML, pp 1692\u20131700"},{"key":"641_CR28","unstructured":"Ngiam J, Khosla A, Kim M, Nam J, Lee H, Ng AY (2011) Multimodal deep learning. In: ICML, pp 689\u2013696"},{"key":"641_CR29","doi-asserted-by":"publisher","first-page":"107456","DOI":"10.1016\/j.sigpro.2020.107456","volume":"170","author":"Z Liu","year":"2020","unstructured":"Liu Z, Lai Z, Ou W, Zhang K, Zheng R (2020) Structured optimal graph-based sparse feature extraction for semi-supervised learning. Signal Process 170:107456","journal-title":"Signal Process"},{"key":"641_CR30","doi-asserted-by":"publisher","first-page":"107023","DOI":"10.1016\/j.patcog.2019.107023","volume":"98","author":"X-J Shen","year":"2020","unstructured":"Shen X-J, Liu S-X, Bao B-K, Pan C-H, Zha Z-J, Fan J (2020) A generalised least-squares approach regularised with graph embedding for dimensionality reduction. Pattern Recogn 98:107023","journal-title":"Pattern Recogn"},{"key":"641_CR31","doi-asserted-by":"publisher","first-page":"113079","DOI":"10.1016\/j.eswa.2019.113079","volume":"144","author":"J Gou","year":"2020","unstructured":"Gou J, Yang Y, Yi Z, Lv J, Mao Q, Zhan Y (2020) Discriminative globality and locality preserving graph embedding for dimensionality reduction. Expert Syst Appl 144:113079","journal-title":"Expert Syst Appl"},{"key":"641_CR32","doi-asserted-by":"publisher","first-page":"113958","DOI":"10.1016\/j.eswa.2020.113958","volume":"164","author":"H Rajabzadeh","year":"2021","unstructured":"Rajabzadeh H, Jahromi MZ, Ghodsi A (2021) Supervised discriminative dimensionality reduction by learning multiple transformation operators. Expert Syst Appl 164:113958","journal-title":"Expert Syst Appl"},{"key":"641_CR33","unstructured":"Yu W, Qin Z (2020) Graph convolutional network for recommendation with low-pass collaborative filters. In: Proc. ICML, pp 1\u201313"},{"key":"641_CR34","unstructured":"Gilmer J, Schoenholz SS, Riley PF, Vinyals O, Dahl GE (2017) Neural message passing for quantum chemistry.  In International conference on machine learning, PMLR, pp. 1263\u20131272"},{"key":"641_CR35","doi-asserted-by":"crossref","unstructured":"Molokwu BC, Shuvo SB, Kar NC, Kobti Z (2020) Node classification and link prediction in social graphs using RLVECN. In: 32nd international conference on scientific and statistical database management (SSDBM 2020), Article 12, pp 1\u201310","DOI":"10.1145\/3400903.3400928"},{"key":"641_CR36","unstructured":"Yang Z, Cohen W, Salakhudinov R (2016) Revisiting semi-supervised learning with graph embeddings. In: Proceedings of the international conference on machine learning, pp 40\u201348"},{"key":"641_CR37","unstructured":"Kipf TN, Welling M (2017) Semi-supervised classification with graph convolutional networks. In: Proc. int. conf. learn. represent., pp 1\u201313"},{"issue":"1","key":"641_CR38","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1109\/TPAMI.2007.250598","volume":"29","author":"S Yan","year":"2007","unstructured":"Yan S, Xu D, Zhang B, Zhang H-J, Yang Q, Lin S (2007) Graph embedding and extensions: a general framework for dimensionality reduction. IEEE Trans Pattern Anal Mach Intell 29(1):40\u201351","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"641_CR39","first-page":"93","volume":"29","author":"P Sen","year":"2008","unstructured":"Sen P, Namata G, Bilgic M, Getoor L, Galligher B, Eliassi-Rad T (2008) Collective classification in network data\". AI Mag 29:93\u201393","journal-title":"AI Mag"},{"key":"641_CR40","doi-asserted-by":"crossref","unstructured":"B. Perozzi, R. Al-Rfou, and S. Skiena, DeepWalk: Online learning of social representations, in Proc. 20th ACM SIGKDD Int. Conf. Knowl. Discovery Data Mining (KDD), pp. 701\u2013710, 2014","DOI":"10.1145\/2623330.2623732"},{"key":"641_CR41","doi-asserted-by":"crossref","unstructured":"J. Weston, F. Ratle, and R. Collobert, Deep learning via semi-supervised embedding, in Proc. 25th Int. Conf. Mach. Learn. (ICML), pp. 1168\u20131175, 2008","DOI":"10.1145\/1390156.1390303"},{"key":"641_CR42","unstructured":"M. Defferrard, X. Bresson, and P. Vandergheynst, Convolutional neural networks on graphs with fast localised spectral filtering, in Proc. Adv. Neural Inf. Process. Syst., pp. 3844\u20133852, 2016"}],"container-title":["Complex &amp; Intelligent Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-022-00641-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s40747-022-00641-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s40747-022-00641-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,9]],"date-time":"2023-06-09T17:36:09Z","timestamp":1686332169000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s40747-022-00641-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1,18]]},"references-count":42,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["641"],"URL":"https:\/\/doi.org\/10.1007\/s40747-022-00641-9","relation":{},"ISSN":["2199-4536","2198-6053"],"issn-type":[{"type":"print","value":"2199-4536"},{"type":"electronic","value":"2198-6053"}],"subject":[],"published":{"date-parts":[[2022,1,18]]},"assertion":[{"value":"12 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 December 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 January 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}