{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T14:03:08Z","timestamp":1778853788943,"version":"3.51.4"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003451","name":"Universidad del Pa\u00eds Vasco","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100003451","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Cogn Comput"],"published-print":{"date-parts":[[2025,4]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Semi-supervised learning with a graph-based approach has gained prominence in machine learning, particularly in scenarios where labeling data involves substantial costs. Graph convolution networks (GCNs) have found widespread application in semi-supervised learning, predominantly on graph-structured data such as citation and social networks. However, a noticeable gap exists in the application of these methods to non-graph multi-view data, such as collections of images. In an effort to address this gap, we introduce two innovative deep semi-supervised multi-view classification models specifically tailored for non-graph data. Both models share a common architecture, leveraging GCNs and integrating a label smoothing constraint. The primary distinction lies in the construction of the consensus similarity graph. The first model directly reconstructs the consensus graph from different views using a specialized objective function designed for flexible graph-based semi-supervised classification. In contrast, the second model independently reconstructs individual graphs and subsequently adaptively merges them into a unified consensus graph. Our experiments encompass various multiple-view image datasets. The results consistently demonstrate the superior performance of our proposed approach compared to traditional fusion methods with GCNs. In this research, we present two approaches for tackling semi-supervised classification challenges involving multiple views. One method is named Semi-supervised Classification with a Unified Graph (SCUG), and the other is referred to as Semi-supervised Classification with a Fused Graph (SC-Fused). Both methods share a common semi-supervised classification process, utilizing the GCN framework and incorporating label smoothing. However, the key distinction lies in the construction of the similarity graph. Unlike traditional ad hoc graph construction approaches, our proposed methods, SCUG and SC-Fused, estimate the unified graph or individual graphs, respectively, alongside the labels. This results in more optimized graphs that benefit from data smoothing and the semi-supervised context.<\/jats:p>","DOI":"10.1007\/s12559-025-10428-y","type":"journal-article","created":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T10:51:25Z","timestamp":1740826285000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Leveraging Graph Convolutional Networks for Semi-supervised Learning in Multi-view Non-graph Data"],"prefix":"10.1007","volume":"17","author":[{"given":"F.","family":"Dornaika","sequence":"first","affiliation":[]},{"given":"J.","family":"Bi","sequence":"additional","affiliation":[]},{"given":"J.","family":"Charafeddine","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,3,1]]},"reference":[{"key":"10428_CR1","unstructured":"Atwood J,\u00a0Towsley D. Diffusion-convolutional neural networks. Advances in neural information processing systems, vol. 29. 2016."},{"issue":"1","key":"10428_CR2","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1016\/j.inffus.2020.09.007","volume":"66","author":"S Bahrami","year":"2021","unstructured":"Bahrami S, Dornaika F, Bosaghzadeh A. Joint auto-weighted graph fusion and scalable semi-supervised learning. Inf Fusion. 2021;66(1):213\u201328.","journal-title":"Inf Fusion"},{"key":"10428_CR3","doi-asserted-by":"crossref","unstructured":"Blum A,\u00a0Mitchell T. Combining labeled and unlabeled data with co-training. In: Proceedings of the 11th annual conference on computational learning theory. 1998.","DOI":"10.1145\/279943.279962"},{"key":"10428_CR4","unstructured":"Bruna J,\u00a0Zaremba W,\u00a0Szlam A,\u00a0LeCun Y. Spectral networks and locally connected networks on graphs. 2013. arXiv:1312.6203."},{"key":"10428_CR5","doi-asserted-by":"publisher","first-page":"296","DOI":"10.1016\/j.ins.2016.06.004","volume":"367\u2013368","author":"G Chao","year":"2016","unstructured":"Chao G, Sun S. Consensus and complementarity based maximum entropy discrimination for multi-view classification. Inf Sci. 2016;367\u2013368:296\u2013310.","journal-title":"Inf Sci"},{"key":"10428_CR6","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.inffus.2023.02.013","volume":"95","author":"Z Chen","year":"2023","unstructured":"Chen Z, Fu L, Yao J, Guo W, Plant C, Wang S. Learnable graph convolutional network and feature fusion for multi-view learning. Inf Fusion. 2023;95:109\u201319.","journal-title":"Inf Fusion"},{"key":"10428_CR7","unstructured":"Defferrard M,\u00a0Bresson X,\u00a0Vandergheynst P. Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems, vol. 29. 2016."},{"key":"10428_CR8","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1016\/j.neunet.2022.11.017","volume":"158","author":"F Dornaika","year":"2023","unstructured":"Dornaika F, Bi J, Zhang C. A unified deep semi-supervised graph learning scheme based on nodes re-weighting and manifold regularization. Neural Netw. 2023;158:188\u201396.","journal-title":"Neural Netw"},{"key":"10428_CR9","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1016\/j.neucom.2015.04.042","volume":"167","author":"Y El Traboulsi","year":"2015","unstructured":"El Traboulsi Y, Dornaika F, Assoum A. Kernel flexible manifold embedding for pattern classification. Neurocomputing. 2015;167:517\u201327.","journal-title":"Neurocomputing"},{"key":"10428_CR10","unstructured":"Federici M,\u00a0Dutta A,\u00a0Forr\u00e9 P,\u00a0Kushman N,\u00a0Akata Z. Learning robust representations via multi-view information bottleneck. 2020."},{"key":"10428_CR11","first-page":"2211","volume":"12","author":"M G\u00f6nen","year":"2011","unstructured":"G\u00f6nen M, Alpayd\u0131n E. Multiple kernel learning algorithms. J Mach Learn Res. 2011;12:2211\u201368.","journal-title":"J Mach Learn Res"},{"key":"10428_CR12","doi-asserted-by":"crossref","unstructured":"Chao G, Sun S. Alternative multiview maximum entropy discrimination. IEEE Trans Neural Netw Learn Syst. 2016.","DOI":"10.1109\/TNNLS.2015.2442256"},{"key":"10428_CR13","unstructured":"He Z,\u00a0Wan S,\u00a0Zappatore M,\u00a0Lu H. A similarity matrix low-rank approximation and inconsistency separation fusion approach for multi-view clustering. IEEE Trans Artif Intell. 2023:1\u201314."},{"issue":"3","key":"10428_CR14","doi-asserted-by":"publisher","first-page":"983","DOI":"10.1109\/TNNLS.2020.3036825","volume":"33","author":"H Huang","year":"2022","unstructured":"Huang H, Song Y, Wu Y, Shi J, Xie X, Jin H. Multitask representation learning with multiview graph convolutional networks. IEEE Trans Neural Netw Learn Syst. 2022;33(3):983\u201395.","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10428_CR15","doi-asserted-by":"publisher","first-page":"5352","DOI":"10.1109\/TIP.2021.3083072","volume":"30","author":"Z Huang","year":"2021","unstructured":"Huang Z, Zhou JT, Zhu H, Zhang C, Peng X. Deep spectral representation learning from multi-view data. IEEE Trans Image Process. 2021;30:5352\u201362.","journal-title":"IEEE Trans Image Process"},{"issue":"10","key":"10428_CR16","doi-asserted-by":"publisher","first-page":"5121","DOI":"10.1109\/TIP.2019.2912356","volume":"28","author":"K Jia","year":"2019","unstructured":"Jia K, Lin J, Tan M, Tao D. Deep multi-view learning using neuron-wise correlation-maximizing regularizers. IEEE Trans Image Process. 2019;28(10):5121\u201334.","journal-title":"IEEE Trans Image Process"},{"key":"10428_CR17","unstructured":"Jia Y,\u00a0Salzmann M,\u00a0Darrell T. Factorized latent spaces with structured sparsity. In: Advances in neural information processing systems 23: 24th annual conference on neural information processing systems 2010. Proceedings of a meeting held 6-9 December 2010, Vancouver, British Columbia, Canada. 2010."},{"key":"10428_CR18","doi-asserted-by":"crossref","unstructured":"Jiang B,\u00a0Zhang Z,\u00a0Lin D,\u00a0Tang J,\u00a0Luo B. Semi-supervised learning with graph learning-convolutional networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 11313\u201311320. 2019.","DOI":"10.1109\/CVPR.2019.01157"},{"key":"10428_CR19","unstructured":"Kipf TN,\u00a0Welling M. Semi-supervised classification with graph convolutional networks. 2016. arXiv:1609.02907."},{"key":"10428_CR20","unstructured":"Kumar A,\u00a0Rai P,\u00a0Daum\u00e9 H. Co-regularized multi-view spectral clustering. Curran Associates Inc.; 2011."},{"issue":"1","key":"10428_CR21","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1109\/TSP.2018.2879624","volume":"67","author":"R Levie","year":"2018","unstructured":"Levie R, Monti F, Bresson X, Bronstein MM. Cayleynets: graph convolutional neural networks with complex rational spectral filters. IEEE Trans Signal Process. 2018;67(1):97\u2013109.","journal-title":"IEEE Trans Signal Process"},{"key":"10428_CR22","doi-asserted-by":"crossref","unstructured":"Li R,\u00a0Wang S,\u00a0Zhu F,\u00a0Huang J. Adaptive graph convolutional neural networks. In: Proceedings of the AAAI conference on artificial intelligence, vol.\u00a032. 2018.","DOI":"10.1609\/aaai.v32i1.11691"},{"key":"10428_CR23","doi-asserted-by":"crossref","unstructured":"Li S, Li W-T, Wang W. Co-gcn for multi-view semi-supervised learning. In: Proceedings of the AAAI conference on artificial intelligence, vol. 34, pp. 4691\u20138. 2020.","DOI":"10.1609\/aaai.v34i04.5901"},{"key":"10428_CR24","unstructured":"Liang M,\u00a0Sun S. Soft margin consistency based scalable multi-view maximum entropy discrimination. AAAI Press; 2016."},{"key":"10428_CR25","unstructured":"Livescu K. Multiview clustering via canonical correlation analysis. In: International conference on machine learning; 2008."},{"key":"10428_CR26","unstructured":"Monadjemi A,\u00a0Thomas B,\u00a0Mirmehdi M. Experiments on high resolution images towards outdoor scene classification. 2002."},{"key":"10428_CR27","unstructured":"Nie F,\u00a0Jing L,\u00a0Li X. Parameter-free auto-weighted multiple graph learning: a framework for multiview clustering and semi-supervised classification. AAAI Press; 2016."},{"key":"10428_CR28","unstructured":"Ning C,\u00a0Zhu J, Xing EP. Predictive subspace learning for multi-view data: a large margin approach. In: International conference on neural information processing systems. 2010."},{"key":"10428_CR29","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1016\/j.ins.2021.07.007","volume":"578","author":"H Peng","year":"2021","unstructured":"Peng H, Du B, Liu M, Liu M, Ji S, Wang S, Zhang X, He L. Dynamic graph convolutional network for long-term traffic flow prediction with reinforcement learning. Inf Sci. 2021;578:401\u201316.","journal-title":"Inf Sci"},{"key":"10428_CR30","unstructured":"Sindhwani V. A co-regularized approach to semi-supervised learning with multiple views. In: Proc. of the 22th ICML workshop on Learning with Multiple views, 2008. 2008."},{"key":"10428_CR31","unstructured":"Sindhwani V, Rosenberg DS. An RKHS for multi-view learning and manifold co-regularization. In: Machine learning, proceedings of the twenty-fifth international conference (ICML 2008), Helsinki, Finland, June 5-9, 2008. 2008."},{"key":"10428_CR32","unstructured":"Sun S,\u00a0Chao G. Multi-view maximum entropy discrimination. In: International joint conference on artificial intelligence. 2013."},{"key":"10428_CR33","doi-asserted-by":"crossref","unstructured":"Tang X,\u00a0Luo J,\u00a0Shen C,\u00a0Lai Z. Multi-view multichannel attention graph convolutional network for mirna\u2013disease association prediction. Brief Bioinform. 2021.","DOI":"10.1093\/bib\/bbab174"},{"key":"10428_CR34","unstructured":"Thiede EH,\u00a0Zhou W,\u00a0Kondor R. Autobahn: Automorphism-based graph neural nets. 2021. arXiv:2103.01710."},{"key":"10428_CR35","unstructured":"Tolstikhin IO,\u00a0Houlsby N,\u00a0Kolesnikov A,\u00a0Beyer L,\u00a0Zhai X,\u00a0Unterthiner T,\u00a0Yung J,.\u00a0Steiner A,\u00a0Keysers D,\u00a0Uszkoreit J,\u00a0Lucic M,\u00a0Dosovitskiy A. Mlp-mixer: an all-mlp architecture for vision. 2021. arXiv:2105.01601v4."},{"key":"10428_CR36","unstructured":"Tsai Y,\u00a0Wu Y,\u00a0Salakhutdinov R, Morency LP. Self-supervised learning from a multi-view perspective. In: International conference on learning representations. 2021."},{"key":"10428_CR37","doi-asserted-by":"crossref","unstructured":"Wang M,\u00a0Lin Y,\u00a0Lin G,\u00a0Yang K, Wu XM. M2grl: a multi-task multi-view graph representation learning framework for web-scale recommender systems. ACM. 2020.","DOI":"10.1145\/3394486.3403284"},{"key":"10428_CR38","doi-asserted-by":"crossref","unstructured":"Wang S, Chen Z, Du S, Lin Z. Learning deep sparse regularizers with applications to multi-view clustering and semi-supervised classification. IEEE Trans Pattern Anal Mach Intell. 2022;44(9).","DOI":"10.1109\/TPAMI.2021.3082632"},{"key":"10428_CR39","unstructured":"Wei W, Zhou ZH. A new analysis of co-training. In: International conference on international conference on machine learning. 2010."},{"key":"10428_CR40","doi-asserted-by":"crossref","unstructured":"Wu Z,\u00a0Lin X,\u00a0Lin Z,\u00a0Chen Z,\u00a0Bai Y,\u00a0Wang S. Interpretable graph convolutional network for multi-view semi-supervised learning. IEEE Trans Multimed. 2023.","DOI":"10.1109\/TMM.2023.3260649"},{"issue":"1","key":"10428_CR41","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1109\/TNNLS.2020.2978386","volume":"32","author":"Z Wu","year":"2021","unstructured":"Wu Z, Pan S, Chen F, Long G, Zhang C, Yu PS. A comprehensive survey on graph neural networks. IEEE Trans Neural Netw Learn Syst. 2021;32(1):4\u201324.","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"10428_CR42","unstructured":"Zhang X, He L, Chen K, Luo Y, Zhou J, Wang F. Multi-view graph convolutional network and its applications on neuroimage analysis for Parkinson\u2019s disease. AMIA ... Annual Symposium proceedings. AMIA symposium. 2018."},{"key":"10428_CR43","unstructured":"Ying Y,\u00a0Campbell C. Generalization bounds for learning the kernel. In: COLT 2009 - The 22nd conference on learning theory, Montreal, Quebec, Canada, June 18-21, 2009. 2009."},{"key":"10428_CR44","doi-asserted-by":"publisher","first-page":"109694","DOI":"10.1016\/j.knosys.2022.109694","volume":"255","author":"Y Yu","year":"2022","unstructured":"Yu Y, Zhou G, Huang H, Xie S, Zhao Q. A semi-supervised label-driven auto-weighted strategy for multi-view data classification. Knowl-Based Syst. 2022;255:109694.","journal-title":"Knowl-Based Syst"},{"key":"10428_CR45","unstructured":"Zhang C,\u00a0Han Z,\u00a0Cui Y,\u00a0Fu H, Zhou JT,\u00a0Hu Q. Cpm-nets: Cross partial multi-view networks. In: Neural information processing systems. 2019."},{"key":"10428_CR46","doi-asserted-by":"crossref","unstructured":"Zhu P,\u00a0Yao X,\u00a0Wang Y,\u00a0Cao M,\u00a0Hui B,\u00a0Zhao S,\u00a0Hu Q. Latent heterogeneous graph network for incomplete multi-view learning. IEEE Trans. Multimed. 2022.","DOI":"10.1109\/TMM.2022.3154592"},{"key":"10428_CR47","doi-asserted-by":"crossref","unstructured":"Zhuang C,\u00a0Ma Q. Dual graph convolutional networks for graph-based semi-supervised classification. In: Proceedings of the 2018 world wide web conference, pp. 499\u2013508. 2018.","DOI":"10.1145\/3178876.3186116"},{"key":"10428_CR48","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1007\/s10994-019-05844-9","volume":"109","author":"W Zhuge","year":"2020","unstructured":"Zhuge W, Hou C, Peng S, Yi D. Joint consensus and diversity for multi-view semi-supervised classification. Mach Learn. 2020;109:445\u201365.","journal-title":"Mach Learn"},{"key":"10428_CR49","doi-asserted-by":"publisher","first-page":"174","DOI":"10.1016\/j.neunet.2021.11.015","volume":"146","author":"N Ziraki","year":"2021","unstructured":"Ziraki N, Dornaika F, Bosaghzadeh A. Multiple-view flexible semi-supervised classification through consistent graph construction and label propagation. Neural Netw: Off J Int Neural Netw Soc. 2021;146:174\u201380.","journal-title":"Neural Netw: Off J Int Neural Netw Soc"}],"container-title":["Cognitive Computation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-025-10428-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12559-025-10428-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12559-025-10428-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,26]],"date-time":"2025-04-26T10:38:23Z","timestamp":1745663903000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12559-025-10428-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,1]]},"references-count":49,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2025,4]]}},"alternative-id":["10428"],"URL":"https:\/\/doi.org\/10.1007\/s12559-025-10428-y","relation":{},"ISSN":["1866-9956","1866-9964"],"issn-type":[{"value":"1866-9956","type":"print"},{"value":"1866-9964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3,1]]},"assertion":[{"value":"26 January 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 February 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 March 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"73"}}