{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T17:30:32Z","timestamp":1774546232120,"version":"3.50.1"},"reference-count":49,"publisher":"MDPI AG","issue":"6","license":[{"start":{"date-parts":[[2021,6,18]],"date-time":"2021-06-18T00:00:00Z","timestamp":1623974400000},"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>Collected network data are often incomplete, with both missing nodes and missing edges. Thus, network completion that infers the unobserved part of the network is essential for downstream tasks. Despite the emerging literature related to network recovery, the potential information has not been effectively exploited. In this paper, we propose a novel unified deep graph convolutional network that infers missing edges by leveraging node labels, features, and distances. Specifically, we first construct an estimated network topology for the unobserved part using node labels, then jointly refine the network topology and learn the edge likelihood with node labels, node features and distances. Extensive experiments using several real-world datasets show the superiority of our method compared with the state-of-the-art approaches.<\/jats:p>","DOI":"10.3390\/e23060771","type":"journal-article","created":{"date-parts":[[2021,6,18]],"date-time":"2021-06-18T11:19:20Z","timestamp":1624015160000},"page":"771","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Unifying Node Labels, Features, and Distances for Deep Network Completion"],"prefix":"10.3390","volume":"23","author":[{"given":"Qiang","family":"Wei","sequence":"first","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu 611731, China"},{"name":"National Key Laboratory of Science and Technology on Blind Signal Processing, Chengdu 610041, 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"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,18]]},"reference":[{"key":"ref_1","unstructured":"Barab\u00e1si, A.-L. (2016). Networks at the heart of complex systems. Network Science, Cambridge University Press."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1038\/nphys2162","article-title":"Communities, modules and large-scale structure in networks","volume":"8","author":"Newman","year":"2012","journal-title":"Nat. Phys."},{"key":"ref_3","first-page":"209","article-title":"Network completion and survey sampling","volume":"Volume 5","author":"Hanneke","year":"2009","journal-title":"Proceedings of the 12th International Conference on Artificial Intelligence and Statistics"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Hric, D., Peixoto, T.P., and Fortunato, S. (2016). Network structure, metadata, and the prediction of missing nodes and annotations. Phys. Rev. X, 6.","DOI":"10.1103\/PhysRevX.6.031038"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"542","DOI":"10.1038\/s41567-018-0076-1","article-title":"Network structure from rich but noisy data","volume":"14","author":"Newman","year":"2018","journal-title":"Nat. Phys."},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Huisman, M., and Krause, R.W. (2018). Imputation of missing network data. Encyclopedia of Social Network Analysis and Mining, Springer.","DOI":"10.1007\/978-1-4939-7131-2_394"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Kim, M., and Leskovec, J. (2011, January 28\u201330). The network completion problem: Inferring missing nodes and edges in networks. Proceedings of the 2011 SIAM International Conference on Data Mining, Mesa, AZ, USA.","DOI":"10.1137\/1.9781611972818.5"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"670","DOI":"10.1016\/j.comcom.2010.05.009","article-title":"Impact of sources and destinations on the observed properties of the internet topology","volume":"34","author":"Magnien","year":"2011","journal-title":"Comput. Commun."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"432","DOI":"10.1006\/jcss.2001.1785","article-title":"Distance realization problems with applications to internet tomography","volume":"63","author":"Chung","year":"2001","journal-title":"J. Comput. Syst. Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3199606","article-title":"Graph reconstruction and verification","volume":"14","author":"Kannan","year":"2018","journal-title":"ACM Trans. Algorithms"},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Erlebach, T., Hall, A., Hoffmann, M., and Miha\u013e\u00e1k, M. (2006, January 29\u201331). Network discovery and verification with distance queries. Proceedings of the 2006 Conference on Algorithms and Complexity, Rome, Italy.","DOI":"10.1007\/11758471_10"},{"key":"ref_12","first-page":"25","article-title":"An overview on user profiling in online social networks","volume":"11","author":"Vasanthakumar","year":"2017","journal-title":"Int. J. Appl. Inf. Syst."},{"key":"ref_13","first-page":"705","article-title":"A fast method for shortest-path cover identification in large complex networks","volume":"63","author":"Wei","year":"2020","journal-title":"Comput. Mater. Contin."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Eriksson, B., Barford, P., Crovella, M., and Nowak, R. (2007, January 24\u201326). Learning network structure from passive measurements. Proceedings of the 7th ACM SIGCOMM Conference on Internet Measurement, San Diego, CA, USA.","DOI":"10.1145\/1298306.1298335"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s13278-016-0405-2","article-title":"Network completion by leveraging similarity of nodes","volume":"6","author":"Forsati","year":"2016","journal-title":"Soc. Netw. Anal. Min."},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Tran, C., Shin, W.-Y., Spitz, A., and Gertz, M. (2020). DeepNC: Deep generative network completion. IEEE Trans. Pattern Anal. Mach. Intell.","DOI":"10.1109\/TPAMI.2020.3032286"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1109\/TKDE.2018.2849727","article-title":"A Survey on Network Embedding","volume":"31","author":"Cui","year":"2019","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"11433","DOI":"10.1073\/pnas.0811511106","article-title":"Assessing the relevance of node features for network structure","volume":"106","author":"Bianconia","year":"2009","journal-title":"Proc. Natl. Acad. Sci. USA."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Kim, M., and Leskovec, J. (2011, January 14\u201317). Modeling social networks with node attributes using the Multiplicative Attribute Graph model. Proceedings of the 27th Conference on Uncertainty in Artificial Intelligence, Barcelona, Spain.","DOI":"10.2172\/1124904"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Yang, L., Kang, Z., Cao, X., Jin, D., Yang, B., and Guo, Y. (2019, January 10\u201316). Topology optimization based graph convolutional network. Proceedings of the 28th International Joint Conference on Artificial Intelligence, Macao, China.","DOI":"10.24963\/ijcai.2019\/563"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1137\/S003614450342480","article-title":"The structure and function of complex networks","volume":"45","author":"Newman","year":"2003","journal-title":"SIAM Rev."},{"key":"ref_22","unstructured":"Shi, M., Tang, Y., and Zhu, X. (2020). Topology and content co-Alignment graph convolutional learning. arXiv."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Rafailidis, D., and Crestani, F. (2016, January 18\u201321). Network completion via joint node clustering and similarity learning. Proceedings of the 2016 IEEE\/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), San Francisco, CA, USA.","DOI":"10.1109\/ASONAM.2016.7752214"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Kaya, M., and Bilge, H.\u015e. (2019). Deep Metric Learning: A Survey. Symmetry, 11.","DOI":"10.3390\/sym11091066"},{"key":"ref_25","unstructured":"Zhang, Z., Cui, P., and Zhu, W. (2020). Deep learning on graphs: A Survey. IEEE Trans. Knowl. Data Eng."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"57","DOI":"10.1016\/j.aiopen.2021.01.001","article-title":"Graph neural networks: A review of methods and applications","volume":"1","author":"Zhou","year":"2020","journal-title":"AI Open"},{"key":"ref_27","unstructured":"Franceschi, L., Niepert, M., Pontil, M., and He, X. (2019, January 9\u201315). Learning discrete structures for graph neural networks. Proceedings of the The 36th International Conference on Machine Learning (PMLR), Long Beach, CA, USA."},{"key":"ref_28","unstructured":"Chen, Y., Wu, L., and Zaki, M.J. (2019). Deep Iterative and Adaptive Learning for Graph Neural Networks. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Yu, D., Zhang, R., Jiang, Z., Wu, Y., and Yang, Y. (2020). Graph-Revised Convolutional Network. arXiv.","DOI":"10.1007\/978-3-030-67664-3_23"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Hao, Y., Cao, X., Fang, Y., Xie, X., and Wang, S. (2021, January 7\u201315). Inductive link prediction for nodes having only attribute information. Proceedings of the the 29th International Joint Conference on Artificial Intelligence (IJCAI), Yokohama, Japan.","DOI":"10.24963\/ijcai.2020\/168"},{"key":"ref_31","unstructured":"You, J., Ying, R., Ren, X., Hamilton, W.L., and Leskovec, J. (2018, January 10\u201315). Graphrnn: Generating realistic graphs with deep auto-regressive models. Proceedings of the 35th International Conference on Machine Learning (ICML), Stockholm, Sweden."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1205","DOI":"10.1109\/TNET.2005.861250","article-title":"Understanding internet topology: Principles, models, and validation","volume":"13","author":"Alderson","year":"2005","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"ref_33","unstructured":"Grover, A., Zweig, A., and Ermon, S. (2019, January 10\u201315). Graphite: Iterative generative modeling of graphs. Proceedings of the 36th International Conference on Machine Learning (ICML), Long Beach, CA, USA."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Xu, D., Ruan, C., Motwani, K., Korpeoglu, E., Kumar, S., and Achan, K. (2019, January 12\u201317). Generative Graph Convolutional Network for Growing Graphs. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brighton, UK.","DOI":"10.1109\/ICASSP.2019.8682360"},{"key":"ref_35","unstructured":"Kipf, T.N., and Welling, M. (2017, January 24\u201326). Semi-Supervised Classification with Graph Convolutional Networks. Proceedings of the 5th International Conference on Learning Representations (ICLR), Palais des Congr\u00e8s Neptune, Toulon, France."},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Lin, W., He, F., Zhang, F., Cheng, X., and Cai, H. (2020, January 3\u20137). Initialization for network embedding: A graph partition approach. Proceedings of the WSDM 2020\u2014The Thirteenth ACM International Conference on Web Search and Data Mining, Houston, TX, USA.","DOI":"10.1145\/3336191.3371781"},{"key":"ref_37","unstructured":"Wang, H., and Leskovec, J. (2020). Unifying graph convolutional neural networks and label propagation. arXiv."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"Jia, J., and Benson, A.R. (2021). A unifying generative model for graph learning algorithms: Label Propagation, graph Convolutions, and combinations. arXiv.","DOI":"10.1137\/21M1395351"},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Chen, D., Lin, Y., Li, W., Li, P., Zhou, J., and Sun, X. (2019). Measuring and relieving the over-smoothing problem for graph neural networks from the topological view. arXiv.","DOI":"10.1609\/aaai.v34i04.5747"},{"key":"ref_40","unstructured":"Velickovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., and Bengio, Y. (2017, January 24\u201326). Graph attention networks. Proceedings of the 6th International Conference on Learning Representations (ICLR), Toulon, France."},{"key":"ref_41","unstructured":"Huang, Q., He, H., Singh, A., Lim, S.-N., and Benson, A.R. (2020). Combining label propagation and simple models out-performs graph neural networks. arXiv."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"016107","DOI":"10.1103\/PhysRevE.83.016107","article-title":"Stochastic blockmodels and community structure in networks","volume":"83","author":"Karrer","year":"2011","journal-title":"Phys. Rev. E"},{"key":"ref_43","first-page":"6446","article-title":"Community detection and stochastic block models: Recent developments","volume":"18","author":"Abbe","year":"2017","journal-title":"J. Mach. Learn. Res."},{"key":"ref_44","unstructured":"Agarap, A.F.M. (2018). Deep learning using rectified linear units (ReLU). arXiv."},{"key":"ref_45","unstructured":"Etworks, N. (2020). Geom-gcn: Geometric graph convolutional networks. arXiv."},{"key":"ref_46","unstructured":"Yang, Z., Cohen, W.W., and Salakhutdinov, R. (2016, January 19\u201324). Revisiting semi-supervised learning with graph embeddings. Proceedings of the 33rd International Conference on Machine Learning (ICML), New York, NY, USA."},{"key":"ref_47","unstructured":"Mernyei, P., and Cangea, C. (2020). Wiki-CS: A wikipedia-based benchmark for graph neural networks. arXiv."},{"key":"ref_48","unstructured":"Wei, Q. (2020, January 24\u201326). Network completion via deep metric learning. Proceedings of the International Conference on Big Data Mining and Information Processing (BDMIP), Qingdao, China."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/2898361","article-title":"SNAP: A general-purpose network analysis and graph-mining library","volume":"8","author":"Leskovec","year":"2016","journal-title":"ACM Trans. Intell. Syst. Technol."}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/6\/771\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:18:51Z","timestamp":1760163531000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/23\/6\/771"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,18]]},"references-count":49,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["e23060771"],"URL":"https:\/\/doi.org\/10.3390\/e23060771","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,18]]}}}