{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T01:51:08Z","timestamp":1760233868528,"version":"build-2065373602"},"reference-count":34,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2021,2,18]],"date-time":"2021-02-18T00:00:00Z","timestamp":1613606400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Future Internet"],"abstract":"<jats:p>Variational graph autoencoder, which can encode structural information and attribute information in the graph into low-dimensional representations, has become a powerful method for studying graph-structured data. However, most existing methods based on variational (graph) autoencoder assume that the prior of latent variables obeys the standard normal distribution which encourages all nodes to gather around 0. That leads to the inability to fully utilize the latent space. Therefore, it becomes a challenge on how to choose a suitable prior without incorporating additional expert knowledge. Given this, we propose a novel noninformative prior-based interpretable variational graph autoencoder (NPIVGAE). Specifically, we exploit the noninformative prior as the prior distribution of latent variables. This prior enables the posterior distribution parameters to be almost learned from the sample data. Furthermore, we regard each dimension of a latent variable as the probability that the node belongs to each block, thereby improving the interpretability of the model. The correlation within and between blocks is described by a block\u2013block correlation matrix. We compare our model with state-of-the-art methods on three real datasets, verifying its effectiveness and superiority.<\/jats:p>","DOI":"10.3390\/fi13020051","type":"journal-article","created":{"date-parts":[[2021,2,18]],"date-time":"2021-02-18T20:56:21Z","timestamp":1613681781000},"page":"51","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Interpretable Variational Graph Autoencoder with Noninformative Prior"],"prefix":"10.3390","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8541-8139","authenticated-orcid":false,"given":"Lili","family":"Sun","sequence":"first","affiliation":[{"name":"College of Software, Jilin University, Changchun 130012, China"},{"name":"Key Laboratory of Symbolic Computation and Knowledge Engineer (Jilin University), Ministry of Education, Changchun 130012, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1790-3751","authenticated-orcid":false,"given":"Xueyan","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Symbolic Computation and Knowledge Engineer (Jilin University), Ministry of Education, Changchun 130012, China"},{"name":"College of Computer Science and Technology, Jilin University, Changchun 130012, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Min","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Jilin University, Changchun 130012, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Symbolic Computation and Knowledge Engineer (Jilin University), Ministry of Education, Changchun 130012, China"},{"name":"College of Computer Science and Technology, Jilin University, Changchun 130012, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2021,2,18]]},"reference":[{"key":"ref_1","unstructured":"Kipf, T.N., and Welling, M. (2016). Variational Graph Auto-Encoders. arXiv."},{"key":"ref_2","unstructured":"Kingma, D.P., and Welling, M. (2014, January 14\u201316). Auto-encoding variational bayes. Proceedings of the 2nd International Conference on Learning Representations, Banff, AB, Canada."},{"key":"ref_3","unstructured":"Kipf, T.N., and Welling, M. (2016). Semi-supervised classification with graph convolutional networks. arXiv."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Im, D.J., Ahn, S., Memisevic, R., and Bengio, Y. (2017, January 4\u20139). Denoising criterion for variational auto-encoding framework. Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, San Francisco, CA, USA.","DOI":"10.1609\/aaai.v31i1.10777"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Pan, W., Li, J., and Li, X. (2020). Portfolio Learning Based on Deep Learning. Future Internet, 12.","DOI":"10.3390\/fi12110202"},{"key":"ref_6","unstructured":"Salha, G., Hennequin, R., and Vazirgiannis, M. (2019). Keep it simple: Graph autoencoders without graph convolutional networks. arXiv."},{"key":"ref_7","unstructured":"Jing, B., Chi, E.A., and Tang, J. (2019). Sgvae: Sequential Graph Variational Autoencoder. arXiv."},{"key":"ref_8","unstructured":"Lucas, J., Tucker, G., Grosse, R., and Norouzi, M. (2019, January 6). Understanding posterior collapse in generative latent variable models. Proceedings of the Deep Generative Models for Highly Structured Data, ICLR 2019 Workshop, New Orleans, LA, USA."},{"key":"ref_9","unstructured":"Yeung, S., Kannan, A., Dauphin, Y., and Fei-Fei, L. (2020, November 10). Epitomic Variational Autoencoders. Available online: http:\/\/ai.stanford.edu\/~syyeung\/resources\/YeuKanDauLi16.pdf."},{"key":"ref_10","unstructured":"Khan, R.A., and Kleinsteuber, M. (2020). Epitomic Variational Graph Autoencoder. arXiv."},{"key":"ref_11","unstructured":"Dieng, A.B., Kim, Y., Rush, A.M., and Blei, D.M. (2019, January 16\u201318). Avoiding latent variable collapse with generative skip models. Proceedings of the 22nd International Conference on Artificial Intelligence and Statistics, AISTATS 2019, Naha, Okinawa, Japan."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Fu, H., Li, C., Liu, X., Gao, J., Celikyilmaz, A., and Carin, L. (2019). Cyclical Annealing Schedule: A simple Approach to Mitigating KL Vanishing. arXiv.","DOI":"10.18653\/v1\/N19-1021"},{"key":"ref_13","unstructured":"Abiri, N., and Ohlsson, M. (2019, January 24\u201326). Variational auto-encoders with Student\u2019s t-prior. Proceedings of the 27th European Symposium on Artificial Neural Networks, ESANN 2019, Bruges, Belgium."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"107514","DOI":"10.1016\/j.patcog.2020.107514","article-title":"Dirichlet variational autoencoder","volume":"107","author":"Joo","year":"2020","journal-title":"Pattern Recognit."},{"key":"ref_15","unstructured":"Li, J., Yu, J., Li, J., Zhang, H., Zhao, K., Rong, Y., Cheng, H., and Huang, J. (2020, January 6\u201312). Dirichlet graph variational autoencoder. Proceedings of the Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, Vancouver, BC, Canada."},{"key":"ref_16","unstructured":"Tomczak, J.M., and Welling, M. (2018, January 9\u201311). VAE with a Vampprior. Proceedings of the International Conference on Artificial Intelligence and Statistics, AISTATS 2018, Lanzarote, Spain."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"43992","DOI":"10.1109\/ACCESS.2020.2977671","article-title":"Variational Autoencoder With Optimizing Gaussian Mixture Model Priors","volume":"8","author":"Guo","year":"2020","journal-title":"IEEE Access"},{"key":"ref_18","unstructured":"Ying, Z., Bourgeois, D., You, J., Zitnik, M., and Leskovec, J. (2019, January 8\u201314). Gnnexplainer: Generating explanations for graph neural networks. Proceedings of the Advances in Neural Information Processing Systems 32: Annual Conference on Neural Information Processing Systems 2019, NeurIPS 2019, Vancouver, BC, Canada."},{"key":"ref_19","unstructured":"Ma, J., Cui, P., Kuang, K., Wang, X., and Zhu, W. (2019, January 9\u201315). Disentangled graph convolutional networks. Proceedings of the 36th International Conference on Machine Learning, ICML 2019, Long Beach, CA, USA."},{"key":"ref_20","unstructured":"Bishop, C.M. (2006). Probability distributions. Pattern Recognition and Machine Learning, Springer."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"197","DOI":"10.1023\/A:1020258113913","article-title":"A Noninformative Prior for Neural Networks","volume":"50","author":"Lee","year":"2003","journal-title":"Mach. Learn."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Choong, J.J., Liu, X., and Murata, T. (2019, January 9\u201312). Optimizing Variational Graph Autoencoder for Community Detection. Proceedings of the 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA.","DOI":"10.1109\/BigData47090.2019.9006123"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Choong, J.J., Liu, X., and Murata, T. (2018, January 17\u201320). Learning community structure with variational autoencoder. Proceedings of the IEEE International Conference on Data Mining, ICDM 2018, Singapore.","DOI":"10.1109\/ICDM.2018.00022"},{"key":"ref_24","unstructured":"Mehta, N., Carin, L., and Rai, P. (2019). Stochastic blockmodels meet graph neural networks. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"105714","DOI":"10.1016\/j.knosys.2020.105714","article-title":"Semi-supervised stochastic blockmodel for structure analysis of signed networks","volume":"195","author":"Liu","year":"2020","journal-title":"Knowl. Based Syst."},{"key":"ref_26","unstructured":"Jeffreys, H. (2020, November 20). An Invariant Form for the Prior Probability in Estimation Problems. Available online: https:\/\/royalsocietypublishing.org\/doi\/abs\/10.1098\/rspa.1946.0056."},{"key":"ref_27","first-page":"1","article-title":"Noninformative bayesian priors. Interpretation and problems with construction and applications","volume":"3","author":"Syversveen","year":"1998","journal-title":"Prepr. Stat."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Pal, S., Coates, M., and Ustebay, D. (February, January 27). Bayesian graph convolutional neural networks for semi-supervised classification. Proceedings of the 33rd AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.","DOI":"10.1609\/aaai.v33i01.33015829"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Pan, S., Hu, R., Long, G., Jiang, J., Yao, L., and Zhang, C. (2018, January 13\u201319). Adversarially regularized graph autoencoder for graph embedding. Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence, IJCAI 2018, Stockholm, Sweden.","DOI":"10.24963\/ijcai.2018\/362"},{"key":"ref_30","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, WWW 2015, Florence, Italy.","DOI":"10.1145\/2736277.2741093"},{"key":"ref_31","unstructured":"Yang, C., Liu, Z., Zhao, D., Sun, M., and Chang, E.Y. (2015, January 25\u201331). Network representation learning with rich text information. Proceedings of the Twenty-Fourth International Joint Conference on Artificial Intelligence, IJCAI 2015, Buenos Aires, Argentina."},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Shen, X., Zhu, X., Jiang, X., Gao, L., He, T., and Hu, X. (2017, January 11\u201314). Visualization of non-metric relationships by adaptive learning multiple maps t-SNE regularization. Proceedings of the 2017 IEEE International Conference on Big Data (Big Data), Boston, MA, USA.","DOI":"10.1109\/BigData.2017.8258393"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1044","DOI":"10.1016\/j.physa.2018.08.135","article-title":"Identifying influential nodes in complex networks based on the inverse-square law","volume":"512","author":"Fei","year":"2018","journal-title":"Phys. A Stat. Mech. Its Appl."},{"key":"ref_34","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"}],"container-title":["Future Internet"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1999-5903\/13\/2\/51\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T05:25:54Z","timestamp":1760160354000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1999-5903\/13\/2\/51"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,2,18]]},"references-count":34,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,2]]}},"alternative-id":["fi13020051"],"URL":"https:\/\/doi.org\/10.3390\/fi13020051","relation":{},"ISSN":["1999-5903"],"issn-type":[{"type":"electronic","value":"1999-5903"}],"subject":[],"published":{"date-parts":[[2021,2,18]]}}}