{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T15:12:05Z","timestamp":1761664325970,"version":"3.41.0"},"reference-count":80,"publisher":"Association for Computing Machinery (ACM)","issue":"3","license":[{"start":{"date-parts":[[2021,10,22]],"date-time":"2021-10-22T00:00:00Z","timestamp":1634860800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Knowl. Discov. Data"],"published-print":{"date-parts":[[2022,6,30]]},"abstract":"<jats:p>Network embedding is a technique that aims at inferring the low-dimensional representations of nodes in a semantic space. In this article, we study the problem of inferring the low-dimensional representations of both nodes and attributes for attributed networks in the same semantic space such that the affinity between a node and an attribute can be effectively measured. Intuitively, this problem can be addressed by simply utilizing existing variational auto-encoder (VAE) based network embedding algorithms. However, the variational posterior distribution in previous VAE based network embedding algorithms is often assumed and restricted to be a mean-field Gaussian distribution or other simple distribution families, which results in poor inference of the embeddings. To alleviate the above defect, we propose a novel VAE-based co-embedding method for attributed network, F-CAN, where posterior distributions are flexible, complex, and scalable distributions constructed through the normalizing flow. We evaluate our proposed models on a number of network tasks with several benchmark datasets. Experimental results demonstrate that there are clear improvements in the qualities of embeddings generated by our model to the state-of-the-art attributed network embedding methods.<\/jats:p>","DOI":"10.1145\/3477049","type":"journal-article","created":{"date-parts":[[2021,10,23]],"date-time":"2021-10-23T04:28:40Z","timestamp":1634963320000},"page":"1-31","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["A Normalizing Flow-Based Co-Embedding Model for Attributed Networks"],"prefix":"10.1145","volume":"16","author":[{"given":"Shangsong","family":"Liang","sequence":"first","affiliation":[{"name":"Sun Yat-sen University and Mohamed bin Zayed University of Artificial Intelligence, Abu Dhabi, UAE"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4600-6171","authenticated-orcid":false,"given":"Zhuo","family":"Ouyang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zaiqiao","family":"Meng","sequence":"additional","affiliation":[{"name":"University of Cambridge, Cambridge, UK"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,10,22]]},"reference":[{"doi-asserted-by":"publisher","key":"e_1_3_3_2_2","DOI":"10.5555\/3026877.3026899"},{"doi-asserted-by":"publisher","key":"e_1_3_3_3_2","DOI":"10.1016\/S0378-8733(03)00009-1"},{"doi-asserted-by":"publisher","key":"e_1_3_3_4_2","DOI":"10.1145\/2488388.2488393"},{"doi-asserted-by":"publisher","key":"e_1_3_3_5_2","DOI":"10.1109\/TIT.2020.3033985"},{"unstructured":"Mislav Balunovi\u0107 Anian Ruoss and Martin Vechev. 2021. Fair normalizing flows. arXiv:2106.05937. Retrieved from https:\/\/arxiv.org\/abs\/2106.05937.","key":"e_1_3_3_6_2"},{"key":"e_1_3_3_7_2","volume-title":"Proceedings of the 6th International Conference on Learning Representations","author":"Bojchevski Aleksandar","year":"2018","unstructured":"Aleksandar Bojchevski and Stephan G\u00fcnnemann. 2018. Deep Gaussian embedding of graphs: Unsupervised inductive learning via ranking. In Proceedings of the 6th International Conference on Learning Representations."},{"key":"e_1_3_3_8_2","volume-title":"Proceedings of the 4th International Conference on Learning Representations","author":"Burda Yuri","year":"2016","unstructured":"Yuri Burda, Roger B. Grosse, and Ruslan Salakhutdinov. 2016. Importance weighted autoencoders. In Proceedings of the 4th International Conference on Learning Representations."},{"doi-asserted-by":"publisher","key":"e_1_3_3_9_2","DOI":"10.1145\/2806416.2806512"},{"doi-asserted-by":"publisher","key":"e_1_3_3_10_2","DOI":"10.5555\/3044805.3044990"},{"key":"e_1_3_3_11_2","first-page":"856","volume-title":"Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence","author":"Davidson Tim R.","year":"2018","unstructured":"Tim R. Davidson, Luca Falorsi, Nicola De Cao, Thomas Kipf, and Jakub M. Tomczak. 2018. Hyperspherical variational auto-encoders. In Proceedings of the 34th Conference on Uncertainty in Artificial Intelligence. 856\u2013865."},{"key":"e_1_3_3_12_2","volume-title":"Proceedings of the 3rd International Conference on Learning Representations","author":"Dinh Laurent","year":"2015","unstructured":"Laurent Dinh, David Krueger, and Yoshua Bengio. 2015. NICE: Non-linear independent components estimation. In Proceedings of the 3rd International Conference on Learning Representations."},{"key":"e_1_3_3_13_2","volume-title":"Proceedings of the 5th International Conference on Learning Representations","author":"Dinh Laurent","year":"2017","unstructured":"Laurent Dinh, Jascha Sohl-Dickstein, and Samy Bengio. 2017. Density estimation using real NVP. In Proceedings of the 5th International Conference on Learning Representations."},{"doi-asserted-by":"publisher","key":"e_1_3_3_14_2","DOI":"10.1088\/1751-8121\/ab7f65"},{"doi-asserted-by":"publisher","key":"e_1_3_3_15_2","DOI":"10.5555\/3326943.3327111"},{"doi-asserted-by":"publisher","key":"e_1_3_3_16_2","DOI":"10.1103\/PhysRevD.101.076002"},{"doi-asserted-by":"publisher","key":"e_1_3_3_17_2","DOI":"10.1088\/2632-2153\/abab62"},{"doi-asserted-by":"publisher","key":"e_1_3_3_18_2","DOI":"10.5555\/3304222.3304235"},{"doi-asserted-by":"publisher","key":"e_1_3_3_19_2","DOI":"10.5555\/3045118.3045213"},{"doi-asserted-by":"publisher","key":"e_1_3_3_20_2","DOI":"10.1145\/2594455"},{"doi-asserted-by":"publisher","key":"e_1_3_3_21_2","DOI":"10.5555\/3045118.3045274"},{"doi-asserted-by":"publisher","key":"e_1_3_3_22_2","DOI":"10.1145\/2939672.2939754"},{"doi-asserted-by":"publisher","key":"e_1_3_3_23_2","DOI":"10.5555\/3294771.3294869"},{"key":"e_1_3_3_24_2","volume-title":"Proceedings of the 5th International Conference on Learning Representations","author":"Higgins Irina","year":"2017","unstructured":"Irina Higgins, Loic Matthey, Arka Pal, Christopher Burgess, Xavier Glorot, Matthew Botvinick, Shakir Mohamed, and Alexander Lerchner. 2017. beta-VAE: Learning basic visual concepts with a constrained variational framework. In Proceedings of the 5th International Conference on Learning Representations."},{"doi-asserted-by":"publisher","key":"e_1_3_3_25_2","DOI":"10.1137\/1.9781611974973.71"},{"doi-asserted-by":"publisher","key":"e_1_3_3_26_2","DOI":"10.1145\/3018661.3018667"},{"doi-asserted-by":"publisher","key":"e_1_3_3_27_2","DOI":"10.1145\/3159652.3159655"},{"key":"e_1_3_3_28_2","volume-title":"3rd International Conference on Learning Representations","author":"Kingma Diederik P.","year":"2015","unstructured":"Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations."},{"doi-asserted-by":"publisher","key":"e_1_3_3_29_2","DOI":"10.5555\/3327546.3327685"},{"doi-asserted-by":"publisher","key":"e_1_3_3_30_2","DOI":"10.5555\/2969033.2969226"},{"doi-asserted-by":"publisher","key":"e_1_3_3_31_2","DOI":"10.5555\/3157382.3157627"},{"key":"e_1_3_3_32_2","volume-title":"Proceedings of the 2nd International Conference on Learning Representations","author":"Kingma Diederik P.","year":"2014","unstructured":"Diederik P. Kingma and Max Welling. 2014. Auto-encoding variational bayes. In Proceedings of the 2nd International Conference on Learning Representations."},{"unstructured":"Thomas N. Kipf and Max Welling. 2016. Variational graph auto-encoders. stat 1050 (2016) 21 pages.","key":"e_1_3_3_33_2"},{"key":"e_1_3_3_34_2","volume-title":"Proceedings of the 5th International Conference on Learning Representations","author":"Kipf Thomas N.","year":"2017","unstructured":"Thomas N. Kipf and Max Welling. 2017. Semi-supervised classification with graph convolutional networks. In Proceedings of the 5th International Conference on Learning Representations."},{"doi-asserted-by":"publisher","key":"e_1_3_3_35_2","DOI":"10.5555\/3044805.3045025"},{"doi-asserted-by":"publisher","key":"e_1_3_3_36_2","DOI":"10.1145\/3159652.3159674"},{"doi-asserted-by":"publisher","key":"e_1_3_3_37_2","DOI":"10.1145\/3132847.3132919"},{"doi-asserted-by":"publisher","key":"e_1_3_3_38_2","DOI":"10.5555\/3504035.3504077"},{"doi-asserted-by":"publisher","key":"e_1_3_3_39_2","DOI":"10.1137\/1.9781611975321.18"},{"doi-asserted-by":"publisher","key":"e_1_3_3_40_2","DOI":"10.5555\/3504035.3504754"},{"doi-asserted-by":"publisher","key":"e_1_3_3_41_2","DOI":"10.1609\/aaai.v33i01.33014269"},{"doi-asserted-by":"publisher","key":"e_1_3_3_42_2","DOI":"10.1109\/TKDE.2018.2832211"},{"doi-asserted-by":"publisher","key":"e_1_3_3_43_2","DOI":"10.1145\/3219819.3220043"},{"doi-asserted-by":"publisher","key":"e_1_3_3_44_2","DOI":"10.1145\/3437963.3441741"},{"doi-asserted-by":"publisher","key":"e_1_3_3_45_2","DOI":"10.5555\/3454287.3455503"},{"doi-asserted-by":"publisher","key":"e_1_3_3_46_2","DOI":"10.1145\/3357384.3358155"},{"doi-asserted-by":"publisher","key":"e_1_3_3_47_2","DOI":"10.1609\/aaai.v34i04.5936"},{"doi-asserted-by":"publisher","key":"e_1_3_3_48_2","DOI":"10.1145\/3357384.3358056"},{"doi-asserted-by":"publisher","key":"e_1_3_3_49_2","DOI":"10.5555\/2999134.2999195"},{"doi-asserted-by":"publisher","key":"e_1_3_3_50_2","DOI":"10.1145\/3289600.3291015"},{"doi-asserted-by":"publisher","key":"e_1_3_3_51_2","DOI":"10.5555\/3454287.3454871"},{"doi-asserted-by":"publisher","key":"e_1_3_3_52_2","DOI":"10.1145\/3377850"},{"doi-asserted-by":"publisher","key":"e_1_3_3_53_2","DOI":"10.5555\/2999792.2999959"},{"doi-asserted-by":"publisher","key":"e_1_3_3_54_2","DOI":"10.5555\/3044805.3045092"},{"doi-asserted-by":"publisher","key":"e_1_3_3_55_2","DOI":"10.1145\/2939672.2939751"},{"doi-asserted-by":"crossref","unstructured":"Gaurav Pandey and Ambedkar Dukkipati. 2016. Variational methods for conditional multimodal learning: Generating human faces from attributes. arXiv:1603.01801. Retrieved from https:\/\/arxiv.org\/abs\/1603.01801.","key":"e_1_3_3_56_2","DOI":"10.1109\/IJCNN.2017.7965870"},{"doi-asserted-by":"publisher","key":"e_1_3_3_57_2","DOI":"10.5555\/3294771.3294994"},{"doi-asserted-by":"publisher","key":"e_1_3_3_58_2","DOI":"10.1145\/2623330.2623732"},{"doi-asserted-by":"publisher","key":"e_1_3_3_59_2","DOI":"10.5555\/3157096.3157360"},{"doi-asserted-by":"publisher","key":"e_1_3_3_60_2","DOI":"10.5555\/3045118.3045281"},{"doi-asserted-by":"publisher","key":"e_1_3_3_61_2","DOI":"10.5555\/3044805.3045035"},{"doi-asserted-by":"publisher","key":"e_1_3_3_62_2","DOI":"10.1609\/aimag.v29i3.2157"},{"doi-asserted-by":"publisher","key":"e_1_3_3_63_2","DOI":"10.1007\/978-3-030-01418-6_41"},{"doi-asserted-by":"publisher","key":"e_1_3_3_64_2","DOI":"10.5555\/2969442.2969628"},{"doi-asserted-by":"publisher","key":"e_1_3_3_65_2","DOI":"10.5555\/3157382.3157516"},{"doi-asserted-by":"publisher","key":"e_1_3_3_66_2","DOI":"10.1145\/3385415"},{"doi-asserted-by":"publisher","key":"e_1_3_3_67_2","DOI":"10.1145\/2736277.2741093"},{"doi-asserted-by":"publisher","key":"e_1_3_3_68_2","DOI":"10.1145\/1557019.1557109"},{"key":"e_1_3_3_69_2","first-page":"109","volume-title":"Bayesian Time Series Models.","author":"Turner Richard","year":"2011","unstructured":"Richard Turner, M. Sahani. 2011. Two problems with variational expectation maximisation for time-series models. In Bayesian Time Series Models. D. Barber, T. Cemgil, and S. Chiappa (Eds.), Cambridge University Press, 109\u2013130."},{"doi-asserted-by":"publisher","key":"e_1_3_3_70_2","DOI":"10.1109\/ICDM.2018.00071"},{"doi-asserted-by":"publisher","key":"e_1_3_3_71_2","DOI":"10.1145\/3132847.3132905"},{"doi-asserted-by":"publisher","key":"e_1_3_3_72_2","DOI":"10.5555\/3298239.3298270"},{"unstructured":"Hao Wu Jonas K\u00f6hler and Frank No\u00e9. 2020. Stochastic normalizing flows. arXiv:2002.06707. Retrieved from https:\/\/arxiv.org\/abs\/2002.06707.","key":"e_1_3_3_73_2"},{"doi-asserted-by":"publisher","key":"e_1_3_3_74_2","DOI":"10.5555\/3304889.3305058"},{"doi-asserted-by":"publisher","key":"e_1_3_3_75_2","DOI":"10.1145\/3041021.3054181"},{"doi-asserted-by":"publisher","key":"e_1_3_3_76_2","DOI":"10.1109\/ICDM.2018.8626170"},{"doi-asserted-by":"crossref","unstructured":"Andrei Zanfir Eduard Gabriel Bazavan Hongyi Xu Bill Freeman Rahul Sukthankar and Cristian Sminchisescu. 2020. Weakly supervised 3d human pose and shape reconstruction with normalizing flows. In Proceedings of the European Conference on Computer Vision . Springer 465\u2013481.","key":"e_1_3_3_77_2","DOI":"10.1007\/978-3-030-58539-6_28"},{"doi-asserted-by":"publisher","key":"e_1_3_3_78_2","DOI":"10.1145\/3394486.3403104"},{"doi-asserted-by":"publisher","key":"e_1_3_3_79_2","DOI":"10.5555\/3304889.3305099"},{"doi-asserted-by":"publisher","key":"e_1_3_3_80_2","DOI":"10.1145\/3219819.3219968"},{"doi-asserted-by":"publisher","key":"e_1_3_3_81_2","DOI":"10.1145\/3219819.3220052"}],"container-title":["ACM Transactions on Knowledge Discovery from Data"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477049","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3477049","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:30:47Z","timestamp":1750188647000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3477049"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10,22]]},"references-count":80,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,6,30]]}},"alternative-id":["10.1145\/3477049"],"URL":"https:\/\/doi.org\/10.1145\/3477049","relation":{},"ISSN":["1556-4681","1556-472X"],"issn-type":[{"type":"print","value":"1556-4681"},{"type":"electronic","value":"1556-472X"}],"subject":[],"published":{"date-parts":[[2021,10,22]]},"assertion":[{"value":"2020-05-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-07-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-10-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}