{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T14:48:02Z","timestamp":1767970082458,"version":"3.49.0"},"reference-count":48,"publisher":"Oxford University Press (OUP)","issue":"7","license":[{"start":{"date-parts":[[2021,6,15]],"date-time":"2021-06-15T00:00:00Z","timestamp":1623715200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/academic.oup.com\/journals\/pages\/open_access\/funder_policies\/chorus\/standard_publication_model"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2019YFB1406202"],"award-info":[{"award-number":["2019YFB1406202"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,8,24]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Since graph learning could preserve the structure information of the samples to improve the learning ability, it has been widely applied in both shallow learning and deep learning. However, the current graph learning methods still suffer from the issues such as outlier influence and model robustness. In this paper, we propose a new dynamic graph neural network (DGCN) method to conduct semi-supervised classification on multi-view data by jointly conducting the graph learning and the classification task in a unified framework. Specifically, our method investigates three strategies to improve the quality of the graph before feeding it into the GCN model: (i) employing robust statistics to consider the sample importance for reducing the outlier influence, i.e. assigning every sample with soft weights so that the important samples are with large weights and outliers are with small or even zero weights; (ii) learning the common representation across all views to improve the quality of the graph for every view; and (iii) learning the complementary information from all initial graphs on multi-view data to further improve the learning of the graph for every view. As a result, each of the strategies could improve the robustness of the DGCN model. Moreover, they are complementary for reducing outlier influence from different aspects, i.e. the sample importance reduces the weights of the outliers, both the common representation and the complementary information improve the quality of the graph for every view. Experimental result on real data sets demonstrates the effectiveness of our method, compared to the comparison methods, in terms of multi-class classification performance.<\/jats:p>","DOI":"10.1093\/comjnl\/bxab064","type":"journal-article","created":{"date-parts":[[2021,4,28]],"date-time":"2021-04-28T19:22:22Z","timestamp":1619637742000},"page":"1093-1103","source":"Crossref","is-referenced-by-count":7,"title":["Robust and Dynamic Graph Convolutional Network For Multi-view Data Classification"],"prefix":"10.1093","volume":"64","author":[{"given":"Liang","family":"Peng","sequence":"first","affiliation":[{"name":"Center for Future Media and School of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fei","family":"Kong","sequence":"additional","affiliation":[{"name":"Center for Future Media and School of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chongzhi","family":"Liu","sequence":"additional","affiliation":[{"name":"Center for Future Media and School of Computer Science and Technology, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Kuang","sequence":"additional","affiliation":[{"name":"School of Information and Software Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"286","published-online":{"date-parts":[[2021,6,15]]},"reference":[{"key":"2021103114302020400_ref1","article-title":"A comprehensive survey on graph neural networks","author":"Wu","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Sys."},{"key":"2021103114302020400_ref2","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.knosys.2018.03.022","article-title":"Graph embedding techniques, applications, and performance: A survey","volume":"151","author":"Goyal","year":"2018","journal-title":"Knowl.-Based Sys."},{"key":"2021103114302020400_ref3","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.acha.2006.03.004","article-title":"From graph to manifold laplacian: The convergence rate","volume":"21","author":"Singer","year":"2006","journal-title":"Appl. Comput. Harmon. Anal."},{"key":"2021103114302020400_ref4","doi-asserted-by":"crossref","first-page":"1969","DOI":"10.1007\/s11280-019-00731-8","article-title":"Spectral clustering via half-quadratic optimization","volume":"23","author":"Zhu","year":"2020","journal-title":"World Wide Web"},{"key":"2021103114302020400_ref5","article-title":"Representation learning on graphs: Methods and applications","volume-title":"IEEE Data(base) Engineering Bulletin.","author":"Hamilton","year":"2017"},{"key":"2021103114302020400_ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2986029","article-title":"Radial graph convolutional network for visual question generation","author":"Xu","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Sys."},{"key":"2021103114302020400_ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3004830","article-title":"Mra-net: Improving vqa via multi-modal relation attention network","author":"Peng","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2021103114302020400_ref8","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10302","article-title":"The constrained laplacian rank algorithm for graph-based clustering","volume":"30","author":"Nie","year":"2016","journal-title":"Proceedings of the AAAI conference on artificial intelligence"},{"key":"2021103114302020400_ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2020.3017250","article-title":"Unsupervised spectral feature selection with dynamic hyper-graph learning","author":"Zhu","year":"2020","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"2021103114302020400_ref10","article-title":"Deep learning on graphs: A survey","author":"Zhang","year":"2020","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"2021103114302020400_ref11","doi-asserted-by":"crossref","first-page":"1945","DOI":"10.1007\/s11280-019-00766-x","article-title":"Robust svm with adaptive graph learning","volume":"23","author":"Hu","year":"2020","journal-title":"World Wide Web"},{"key":"2021103114302020400_ref12","first-page":"2635","article-title":"Dynamic hypergraph neural networks","author":"Jiang","year":"2019","journal-title":"IJCAI"},{"key":"2021103114302020400_ref13","first-page":"1024","article-title":"Inductive representation learning on large graphs","author":"Hamilton","year":"2017","journal-title":"NIPS"},{"key":"2021103114302020400_ref14","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"2021103114302020400_ref15","first-page":"4062","article-title":"Dual self-paced graph convolutional network: Towards reducing attribute distortions induced by topology","author":"Yang","year":"2019","journal-title":"IJCAI"},{"key":"2021103114302020400_ref16","first-page":"2110","article-title":"Self-paced convolutional neural networks","author":"Li","year":"2017","journal-title":"IJCAI"},{"key":"2021103114302020400_ref17","first-page":"11313","article-title":"Semi-supervised learning with graph learning-convolutional networks","author":"Jiang","year":"2019","journal-title":"CVPR"},{"key":"2021103114302020400_ref18","article-title":"Deep iterative and adaptive learning for graph neural networks","author":"Chen","year":"2019"},{"key":"2021103114302020400_ref19","article-title":"Joint learning of graph representation and node features in graph convolutional neural networks","author":"Tang","year":"2019"},{"key":"2021103114302020400_ref20","first-page":"547","article-title":"Easy samples first: Self-paced reranking for zero-example multimedia search","author":"Jiang","year":"2014","journal-title":"ACMMM"},{"key":"2021103114302020400_ref21","doi-asserted-by":"crossref","first-page":"43","DOI":"10.1016\/j.inffus.2017.02.007","article-title":"Multi-view learning overview: Recent progress and new challenges","volume":"38","author":"Zhao","year":"2017","journal-title":"Inform. Fusion"},{"key":"2021103114302020400_ref22","doi-asserted-by":"crossref","first-page":"2494","DOI":"10.1109\/TIP.2017.2676345","article-title":"Learning discriminative binary codes for large-scale cross-modal retrieval","volume":"26","author":"Xu","year":"2017","journal-title":"IEEE Trans. Image Process."},{"key":"2021103114302020400_ref23","doi-asserted-by":"crossref","first-page":"128","DOI":"10.1016\/j.patcog.2017.02.034","article-title":"Robust discrete code modeling for supervised hashing","volume":"75","author":"Luo","year":"2018","journal-title":"Pattern Recognit."},{"key":"2021103114302020400_ref24","article-title":"Graph optimized convolutional networks","author":"Jiang","year":"2019"},{"key":"2021103114302020400_ref25","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1016\/j.inffus.2020.08.023","article-title":"Heterogeneous data fusion for predicting mild cognitive impairment conversion","volume":"66","author":"Shen","year":"2021","journal-title":"Inform. Fusion"},{"key":"2021103114302020400_ref26","doi-asserted-by":"crossref","DOI":"10.1145\/3178876.3186116","article-title":"Dual graph convolutional networks for graph-based semi-supervised classification","author":"Zhuang","year":"2018","journal-title":"Proceedings of the 2018 World Wide Web Conference"},{"key":"2021103114302020400_ref27","first-page":"3693","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Simonovsky","year":"2017"},{"key":"2021103114302020400_ref28","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1186\/1756-0381-4-10","article-title":"Using graph theory to analyze biological networks","volume":"4","author":"Pavlopoulos","year":"2011","journal-title":"BioData Mining"},{"key":"2021103114302020400_ref29","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2019.107175","article-title":"Spectral rotation for deep one-step clustering","volume":"105","author":"Zhu","year":"2020","journal-title":"Pattern Recognit."},{"key":"2021103114302020400_ref30","doi-asserted-by":"crossref","first-page":"2033","DOI":"10.1109\/TMM.2017.2703636","article-title":"Graph pca hashing for similarity search","volume":"19","author":"Zhu","year":"2017","journal-title":"IEEE Trans. Multimed."},{"key":"2021103114302020400_ref31","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1016\/j.patcog.2017.05.009","article-title":"Unsupervised manifold learning through reciprocal knn graph and connected components for image retrieval tasks","volume":"75","author":"Pedronette","year":"2018","journal-title":"Pattern Recognit."},{"key":"2021103114302020400_ref32","author":"Huber","year":"2004"},{"key":"2021103114302020400_ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3009632","article-title":"Half-quadratic minimization for unsupervised feature selection on incomplete data","author":"Shen","year":"2020","journal-title":"IEEE Trans. Neural Netw. Learn. Sys."},{"key":"2021103114302020400_ref34","doi-asserted-by":"crossref","DOI":"10.1109\/ICASSP.2007.366913","article-title":"Approximating the kullback leibler divergence between gaussian mixture models","author":"Hershey","year":"2007","journal-title":"In 2007 IEEE International Conference on Acoustics, Speech and Signal Processing-ICASSP'07"},{"key":"2021103114302020400_ref35","article-title":"A survey on multi-view learning","volume-title":"CoRR.","author":"Xu","year":"2013"},{"key":"2021103114302020400_ref36","doi-asserted-by":"crossref","first-page":"1774","DOI":"10.1109\/TPAMI.2018.2847335","article-title":"Binary multi-view clustering","volume":"41","author":"Zhang","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2021103114302020400_ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2956530","article-title":"Efficient utilization of missing data in cost-sensitive learning","author":"Zhu","year":"2019","journal-title":"IEEE Trans. Knowl. Data Eng"},{"key":"2021103114302020400_ref38","first-page":"977","article-title":"Clustering and projected clustering with adaptive neighbors","author":"Nie","year":"2014","journal-title":"SIGKDD"},{"key":"2021103114302020400_ref39","first-page":"1","article-title":"Self-paced multi-view co-training","volume":"21","author":"Ma","year":"2020","journal-title":"J. Machine Learn. Res."},{"key":"2021103114302020400_ref40","first-page":"557","article-title":"Cpm-nets: Cross partial multi-view networks","author":"Zhang","year":"2019","journal-title":"Adv. Neural Inform. Process. Sys."},{"key":"2021103114302020400_ref41","doi-asserted-by":"crossref","first-page":"1375","DOI":"10.1145\/3343031.3350860","volume-title":"Proceedings of the 27th ACM International Conference on Multimedia","author":"Jiang","year":"2019"},{"key":"2021103114302020400_ref42","article-title":"Adam: A method for stochastic optimization","volume-title":"international conference on learning representations.","author":"Kingma","year":"2015"},{"key":"2021103114302020400_ref43","volume-title":"Semi-supervised learning literature survey. Technical report","author":"Zhu","year":"2005"},{"key":"2021103114302020400_ref44","article-title":"Revisiting semi-supervised learning with graph embeddings","author":"Yang","year":"2016","journal-title":"International conference on machine learning"},{"key":"2021103114302020400_ref45","volume-title":"AAAI","author":"Xu","year":"2020"},{"key":"2021103114302020400_ref46","doi-asserted-by":"crossref","DOI":"10.1007\/978-1-349-03521-2","volume-title":"Graph theory with applications","author":"Bondy","year":"1976"},{"key":"2021103114302020400_ref47","first-page":"1025","volume-title":"NIPS","author":"Maier","year":"2008"},{"key":"2021103114302020400_ref48","volume-title":"Introduction to algorithms","author":"Cormen","year":"2009"}],"container-title":["The Computer Journal"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/academic.oup.com\/comjnl\/article-pdf\/64\/7\/1093\/40979407\/bxab064.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"http:\/\/academic.oup.com\/comjnl\/article-pdf\/64\/7\/1093\/40979407\/bxab064.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,25]],"date-time":"2022-12-25T19:10:41Z","timestamp":1671995441000},"score":1,"resource":{"primary":{"URL":"https:\/\/academic.oup.com\/comjnl\/article\/64\/7\/1093\/6299204"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,15]]},"references-count":48,"journal-issue":{"issue":"7","published-online":{"date-parts":[[2021,6,15]]},"published-print":{"date-parts":[[2021,8,24]]}},"URL":"https:\/\/doi.org\/10.1093\/comjnl\/bxab064","relation":{},"ISSN":["0010-4620","1460-2067"],"issn-type":[{"value":"0010-4620","type":"print"},{"value":"1460-2067","type":"electronic"}],"subject":[],"published-other":{"date-parts":[[2021,7]]},"published":{"date-parts":[[2021,6,15]]}}}