{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,28]],"date-time":"2026-03-28T04:52:07Z","timestamp":1774673527645,"version":"3.50.1"},"reference-count":25,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2021,2,27]],"date-time":"2021-02-27T00:00:00Z","timestamp":1614384000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>In recent years, on the basis of drawing lessons from traditional neural network models, people have been paying more and more attention to the design of neural network architectures for processing graph structure data, which are called graph neural networks (GNN). GCN, namely, graph convolution networks, are neural network models in GNN. GCN extends the convolution operation from traditional data (such as images) to graph data, and it is essentially a feature extractor, which aggregates the features of neighborhood nodes into those of target nodes. In the process of aggregating features, GCN uses the Laplacian matrix to assign different importance to the nodes in the neighborhood of the target nodes. Since graph-structured data are inherently non-Euclidean, we seek to use a non-Euclidean mathematical tool, namely, Riemannian geometry, to analyze graphs (networks). In this paper, we present a novel model for semi-supervised learning called the Ricci curvature-based graph convolutional neural network, i.e., RCGCN. The aggregation pattern of RCGCN is inspired by that of GCN. We regard the network as a discrete manifold, and then use Ricci curvature to assign different importance to the nodes within the neighborhood of the target nodes. Ricci curvature is related to the optimal transport distance, which can well reflect the geometric structure of the underlying space of the network. The node importance given by Ricci curvature can better reflect the relationships between the target node and the nodes in the neighborhood. The proposed model scales linearly with the number of edges in the network. Experiments demonstrated that RCGCN achieves a significant performance gain over baseline methods on benchmark datasets.<\/jats:p>","DOI":"10.3390\/e23030292","type":"journal-article","created":{"date-parts":[[2021,2,27]],"date-time":"2021-02-27T03:44:31Z","timestamp":1614397471000},"page":"292","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":13,"title":["Ricci Curvature-Based Semi-Supervised Learning on an Attributed Network"],"prefix":"10.3390","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5938-9004","authenticated-orcid":false,"given":"Wei","family":"Wu","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangmin","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fucai","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,2,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Tang, J., Aggarwal, C., and Liu, H. (2016, January 5\u20137). Node classification in signed social networks. Proceedings of the 2016 SIAM International Conference on Data Mining, Miami, FL, USA.","DOI":"10.1137\/1.9781611974348.7"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Gao, S., Denoyer, L., and Gallinari, P. (2011). Temporal link prediction by integrating content and structure information. Proceedings of the 20th ACM International Conference on Information and Knowledge Management, ACM.","DOI":"10.1145\/2063576.2063744"},{"key":"ref_3","unstructured":"Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013). Efficient estimation of word representations in vector space. arXiv."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Perozzi, B., Al-Rfou, R., and Skiena, S. (2014, January 24\u201327). Deepwalk: Online learning of social representations. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, New York, NY, USA.","DOI":"10.1145\/2623330.2623732"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Grover, A., and Leskovec, J. (2016, January 13\u201317). node2vec: Scalable feature learning for networks. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939754"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Tang, J., Qu, M., Wang, M., Zhang, M., Yan, J., and Mei, Q. (2015, January 18\u201322). Line: Large-scale information network embedding. Proceedings of the 24th International Conference on World Wide Web, Florence, Italy.","DOI":"10.1145\/2736277.2741093"},{"key":"ref_7","unstructured":"Shen, E., Cao, Z., Zou, C., and Wang, J. (2018). Flexible Attributed Network Embedding. arXiv."},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Cao, S., Lu, W., and Xu, Q. (2015, January 19\u201323). Grarep: Learning graph representations with global structural information. Proceedings of the 24th ACM International on Conference on Information and Knowledge Management, Melbourne, Australia.","DOI":"10.1145\/2806416.2806512"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Ou, M., Cui, P., Pei, J., Zhang, Z., and Zhu, W. (2016, January 13\u201317). Asymmetric transitivity preserving graph embedding. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939751"},{"key":"ref_10","first-page":"2111","article-title":"Network representation learning with rich text information","volume":"2015","author":"Yang","year":"2015","journal-title":"IJCAI"},{"key":"ref_11","first-page":"3889","article-title":"Max-margin deepwalk: Discriminative learning of network representation","volume":"2016","author":"Tu","year":"2016","journal-title":"IJCAI"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Zhang, D., Yin, J., Zhu, X., and Zhang, C. (2016, January 12\u201315). Homophily, structure, and content augmented network representation learning. Proceedings of the 2016 IEEE 16th International Conference on Data Mining (ICDM), Barcelona, Spain.","DOI":"10.1109\/ICDM.2016.0072"},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wang, D., Cui, P., and Zhu, W. (2016, January 13\u201317). Structural deep network embedding. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, San Francisco, CA, USA.","DOI":"10.1145\/2939672.2939753"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"2257","DOI":"10.1109\/TKDE.2018.2819980","article-title":"Attributed social network embedding","volume":"30","author":"Liao","year":"2018","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_15","unstructured":"Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv."},{"key":"ref_16","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Lio, P., and Bengio, Y. (2017). Graph attention networks. arXiv."},{"key":"ref_17","unstructured":"Petersen, P., Axler, S., and Ribet, K. (2006). Riemannian Geometry, Springer."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"923","DOI":"10.1002\/cpa.20060","article-title":"Transport inequalities, gradient estimates, entropy and Ricci curvature","volume":"58","author":"Sturm","year":"2005","journal-title":"Commun. Pure Appl. Math."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"810","DOI":"10.1016\/j.jfa.2008.11.001","article-title":"Ricci curvature of Markov chains on metric spaces","volume":"256","author":"Ollivier","year":"2009","journal-title":"J. Funct. Anal."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"916","DOI":"10.1016\/j.ejc.2013.01.004","article-title":"Ollivier\u2019s Ricci curvature and the coloring of graphs","volume":"34","author":"Cho","year":"2013","journal-title":"Eur. J. Comb."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Bauer, F., Jost, J., and Liu, S. (2011). Ollivier-Ricci curvature and the spectrum of the normalized graph Laplace operator. arXiv.","DOI":"10.4310\/MRL.2012.v19.n6.a2"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"605","DOI":"10.2748\/tmj\/1325886283","article-title":"Ricci curvature of graphs","volume":"63","author":"Lin","year":"2011","journal-title":"Tohoku Math. J."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"300","DOI":"10.1007\/s00454-013-9558-1","article-title":"Ollivier\u2019s Ricci curvature, local clustering and curvature-dimension inequalities on graphs","volume":"51","author":"Jost","year":"2014","journal-title":"Discret. Comput. Geom."},{"key":"ref_24","unstructured":"Pouryahya, M., Mathews, J., and Tannenbaum, A. (2017). Comparing three notions of discrete ricci curvature on biological networks. arXiv."},{"key":"ref_25","unstructured":"Yang, Z., Cohen, W., and Salakhudinov, R. (2016, January 19\u201324). Revisiting semi-supervised learning with graph embeddings. Proceedings of the International Conference on Machine Learning, New York, NY, USA."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/3\/292\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:29:48Z","timestamp":1760160588000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/3\/292"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,27]]},"references-count":25,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2021,3]]}},"alternative-id":["e23030292"],"URL":"https:\/\/doi.org\/10.3390\/e23030292","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,2,27]]}}}