{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:56:44Z","timestamp":1791392204712,"version":"4.3.3"},"reference-count":37,"publisher":"Institute of Mathematical Statistics","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Ann. Statist."],"published-print":{"date-parts":[[2025,12,1]]},"abstract":"Analysis of networks that evolve dynamically requires the joint modelling of individual snapshots and time dynamics. This paper proposes a new flexible two-way heterogeneity model towards this goal. The new model equips each node of the network with two heterogeneity parameters, one to characterize the propensity to form ties with other nodes statically and the other to differentiate the tendency to retain existing ties over time. With n observed networks each having p nodes, we develop a new asymptotic theory for the maximum likelihood estimation of 2p parameters when np\u2192\u221e. We overcome the global nonconvexity of the negative log-likelihood function by the virtue of its local convexity, and propose a novel method of moment estimator as the initial value for a simple algorithm that leads to the consistent local maximum likelihood estimator (MLE). To establish the upper bounds for the estimation error of the MLE, we derive a new uniform deviation bound, which is of independent interest. The theory of the model and its usefulness are further supported by extensive simulation and the analysis of some real network data sets.<\/jats:p>","DOI":"10.1214\/25-aos2557","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T06:17:28Z","timestamp":1766470648000},"page":"2617-2641","source":"Crossref","is-referenced-by-count":3,"title":["A two-way heterogeneity model for dynamic networks"],"prefix":"10.1214","volume":"53","author":[{"given":"Binyan","family":"Jiang","sequence":"first","affiliation":[{"name":"Department of Data Science and AI, Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenlei","family":"Leng","sequence":"additional","affiliation":[{"name":"Department of Applied Mathematics, Hong Kong Polytechnic University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ting","family":"Yan","sequence":"additional","affiliation":[{"name":"Department of Statistics, Hubei Key Laboratory of Mathematical Sciences, Key Laboratory of Nonlinear Analysis & Applications, Central China Normal University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiwei","family":"Yao","sequence":"additional","affiliation":[{"name":"Department of Statistics, London School of Economics"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyang","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Statistics, London School of Economics"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"108","reference":[{"key":"2","doi-asserted-by":"publisher","unstructured":"Chatterjee, S.<\/small>, Diaconis, P.<\/small> and Sly, A.<\/small> (2011). Random graphs with a given degree sequence. Ann. Appl. Probab.<\/i> 21<\/b> 1400\u20131435.","DOI":"10.1214\/10-AAP728"},{"key":"32","doi-asserted-by":"publisher","unstructured":"Wainwright, M. J.<\/small> (2019). High-Dimensional Statistics<\/i>: A Non-Asymptotic Viewpoint<\/i>. Cambridge Series in Statistical and Probabilistic Mathematics<\/i> 48<\/b>. Cambridge Univ. Press, Cambridge.","DOI":"10.1017\/9781108627771"},{"key":"30","doi-asserted-by":"publisher","unstructured":"van der Vaart, A. W.<\/small> (2000). Asymptotic Statistics<\/i>. Cambridge Series in Statistical and Probabilistic Mathematics<\/i> 3<\/b>. Cambridge Univ. Press, Cambridge.","DOI":"10.1017\/CBO9780511802256"},{"key":"35","doi-asserted-by":"publisher","unstructured":"YAN, T.<\/small>, LENG, C.<\/small> and ZHU, J.<\/small> (2016). Asymptotics in directed exponential random graph models with an increasing bi-degree sequence. Ann. Statist.<\/i> 44<\/b> 31\u201357.","DOI":"10.1214\/15-AOS1343"},{"key":"27","doi-asserted-by":"publisher","unstructured":"SENGUPTA, S.<\/small> and CHEN, Y.<\/small> (2018). A block model for node popularity in networks with community structure. J. R. Stat. Soc. Ser. B. Stat. Methodol.<\/i> 80<\/b> 365\u2013386.","DOI":"10.1111\/rssb.12245"},{"key":"9","doi-asserted-by":"crossref","unstructured":"HANNEKE, S.<\/small>, FU, W.<\/small> and XING, E. P.<\/small> (2010). Discrete temporal models of social networks. Electron. J. Stat.<\/i> 4<\/b> 585\u2013605.","DOI":"10.1214\/09-EJS548"},{"key":"21","doi-asserted-by":"crossref","unstructured":"KRIVITSKY, P. N.<\/small> and HANDCOCK, M. S.<\/small> (2014). A separable model for dynamic networks. J. R. Stat. Soc. Ser. B. Stat. Methodol.<\/i> 76<\/b> 29\u201346.","DOI":"10.1111\/rssb.12014"},{"key":"15","doi-asserted-by":"publisher","unstructured":"Jin, J.<\/small> (2015). Fast community detection by SCORE. Ann. Statist.<\/i> 43<\/b> 57\u201389.","DOI":"10.1214\/14-AOS1265"},{"key":"4","doi-asserted-by":"publisher","unstructured":"Durante, D.<\/small> and Dunson, D. B.<\/small> (2016). Locally adaptive dynamic networks. Ann. Appl. Stat.<\/i> 10<\/b> 2203\u20132232.","DOI":"10.1214\/16-AOAS971"},{"key":"22","doi-asserted-by":"publisher","unstructured":"Matias, C.<\/small> and Miele, V.<\/small> (2017). Statistical clustering of temporal networks through a dynamic stochastic block model. J. R. Stat. Soc. Ser. B. Stat. Methodol.<\/i> 79<\/b> 1119\u20131141.","DOI":"10.1111\/rssb.12200"},{"key":"26","doi-asserted-by":"publisher","unstructured":"Pensky, M.<\/small> (2019). Dynamic network models and graphon estimation. Ann. Statist.<\/i> 47<\/b> 2378\u20132403.","DOI":"10.1214\/18-AOS1751"},{"key":"17","doi-asserted-by":"publisher","unstructured":"KARRER, B.<\/small> and NEWMAN, M. E. J.<\/small> (2011). Stochastic blockmodels and community structure in networks. Phys. Rev. E<\/i> 83<\/b> 016107, 10.","DOI":"10.1103\/PhysRevE.83.016107"},{"key":"14","unstructured":"JIANG, B.<\/small>, LI, J.<\/small> and YAO, Q.<\/small> (2023). Autoregressive networks. J. Mach. Learn. Res.<\/i> 24<\/b> Paper No. [227], 69."},{"key":"33","doi-asserted-by":"publisher","unstructured":"YAN, T.<\/small>, JIANG, B.<\/small>, FIENBERG, S. E.<\/small> and LENG, C.<\/small> (2019). Statistical inference in a directed network model with covariates. J. Amer. Statist. Assoc.<\/i> 114<\/b> 857\u2013868.","DOI":"10.1080\/01621459.2018.1448829"},{"key":"1","unstructured":"BHATTACHARJEE, M.<\/small>, BANERJEE, M.<\/small> and MICHAILIDIS, G.<\/small> (2020). Change point estimation in a dynamic stochastic block model. J. Mach. Learn. Res.<\/i> 21<\/b> Paper No. 107, 59."},{"key":"8","doi-asserted-by":"publisher","unstructured":"HAN, R.<\/small>, XU, Y.<\/small> and CHEN, K.<\/small> (2023). A general pairwise comparison model for extremely sparse networks. J. Amer. Statist. Assoc.<\/i> 118<\/b> 2422\u20132432.","DOI":"10.1080\/01621459.2022.2053137"},{"key":"16","unstructured":"JIN, J.<\/small>, KE, Z. T.<\/small>, LUO, S.<\/small> and WANG, M.<\/small> (2023). Optimal Estimation of the Number of Network Communities. J. Amer. Statist. Assoc.<\/i> 118<\/b> 2101\u20132116."},{"key":"3","doi-asserted-by":"publisher","unstructured":"CHEN, M.<\/small>, KATO, K.<\/small> and LENG, C.<\/small> (2021). Analysis of networks via the sparse \u03b2<\/i>-model. J. R. Stat. Soc. Ser. B. Stat. Methodol.<\/i> 83<\/b> 887\u2013910.","DOI":"10.1111\/rssb.12444"},{"key":"18","doi-asserted-by":"publisher","unstructured":"KARWA, V.<\/small> and SLAVKOVI\u0106, A.<\/small> (2016). Inference using noisy degrees: Differentially private \u03b2<\/i>-model and synthetic graphs. Ann. Statist.<\/i> 44<\/b> 87\u2013112.","DOI":"10.1214\/15-AOS1358"},{"key":"37","doi-asserted-by":"publisher","unstructured":"YAN, T.<\/small> and XU, J.<\/small> (2013). A central limit theorem in the \u03b2<\/i>-model for undirected random graphs with a diverging number of vertices. Biometrika<\/i> 100<\/b> 519\u2013524.","DOI":"10.1093\/biomet\/ass084"},{"key":"12","doi-asserted-by":"crossref","unstructured":"HOLLAND, P. W.<\/small> and LEINHARDT, S.<\/small> (1981). An exponential family of probability distributions for directed graphs. J. Amer. Statist. Assoc.<\/i> 76<\/b> 33\u201350.","DOI":"10.1080\/01621459.1981.10477598"},{"key":"5","doi-asserted-by":"publisher","unstructured":"GRAGG, W. B.<\/small> and TAPIA, R. A.<\/small> (1974). Optimal error bounds for the Newton\u2013Kantorovich theorem. SIAM J. Numer. Anal.<\/i> 11<\/b> 10\u201313.","DOI":"10.1137\/0711002"},{"key":"6","doi-asserted-by":"publisher","unstructured":"GRAHAM, B. S.<\/small> (2017). An econometric model of network formation with degree heterogeneity. Econometrica<\/i> 85<\/b> 1033\u20131063.","DOI":"10.3982\/ECTA12679"},{"key":"7","doi-asserted-by":"publisher","unstructured":"HAN, R.<\/small>, CHEN, K.<\/small> and TAN, C.<\/small> (2020). Bivariate gamma model. J. Multivariate Anal.<\/i> 180<\/b> 104666, 12.","DOI":"10.1016\/j.jmva.2020.104666"},{"key":"10","unstructured":"HANNEKE, S.<\/small> and XING, E. P.<\/small> (2007). Discrete temporal models of social networks. In Statistical Network Analysis<\/i>: Models, Issues, and New Directions<\/i>: ICML<\/i> 2006 Workshop on Statistical Network Analysis, Pittsburgh, PA, USA, June<\/i> 29, 2006, Revised Selected Papers<\/i> 115\u2013125. Springer, Berlin."},{"key":"11","unstructured":"HILLAR, C. J.<\/small>, LIN, S.<\/small> and WIBISONO, A.<\/small> (2012). Inverses of symmetric, diagonally dominant positive matrices and applications. arXiv preprint. Available at arXiv:1203.6812<\/a>."},{"key":"13","doi-asserted-by":"crossref","unstructured":"JIANG, B.<\/small>, LENG, C.<\/small>, YAN, T.<\/small>, YAO, Q.<\/small> and YU, X.<\/small> (2025). Supplement to \u201cA two-way heterogeneity model for dynamic networks.\u201d https:\/\/doi.org\/10.1214\/25-AOS2557SUPP<\/a>","DOI":"10.1214\/25-AOS2557SUPP"},{"key":"19","unstructured":"KE, Z. T.<\/small> and JIN, J.<\/small> (2023). The SCORE normalization, especially for highly heterogeneous network and text data. arXiv preprint. Available at arXiv:2204.11097<\/a>."},{"key":"20","doi-asserted-by":"publisher","unstructured":"KOLACZYK, E. D.<\/small> and CS\u00c1RDI, G.<\/small> (2020). Statistical Analysis of Network Data with R<\/i>, 2nd ed. Use R!<\/i> Springer, Cham.","DOI":"10.1007\/978-3-030-44129-6_1"},{"key":"23","doi-asserted-by":"crossref","unstructured":"MERSCH, D. P.<\/small>, CRESPI, A.<\/small> and KELLER, L.<\/small> (2013). Tracking individuals shows spatial fidelity is a key regulator of ant social organization. Science<\/i> 340<\/b> 1090\u20131093.","DOI":"10.1126\/science.1234316"},{"key":"24","doi-asserted-by":"crossref","unstructured":"MINAI, A. A.<\/small> and WILLIAMS, R. D.<\/small> (1993). On the derivatives of the sigmoid. Neural Netw.<\/i> 6<\/b> 845\u2013853.","DOI":"10.1016\/S0893-6080(05)80129-7"},{"key":"25","doi-asserted-by":"publisher","unstructured":"NEWMAN, M.<\/small> (2018). Networks<\/i>, 2nd ed. Oxford Univ. Press, Oxford.","DOI":"10.1093\/oso\/9780198805090.001.0001"},{"key":"28","unstructured":"SHAO, M.<\/small>, ZHANG, Y.<\/small>, WANG, Q.<\/small>, ZHANG, Y.<\/small>, LUO, J.<\/small> and YAN, T.<\/small> (2021). L-2 Regularized maximum likelihood for \u03b2<\/i>-model in large and sparse networks. arXiv preprint. Available at arXiv:2110.11856<\/a>."},{"key":"29","doi-asserted-by":"publisher","unstructured":"STEIN, S.<\/small>, FENG, R.<\/small> and LENG, C.<\/small> (2024). A sparse beta regression model for network analysis. J. Amer. Statist. Assoc.<\/i> 120<\/b> 1281\u20131293.","DOI":"10.1080\/01621459.2024.2411073"},{"key":"31","doi-asserted-by":"publisher","unstructured":"VAN DER VAART, A. W.<\/small> and WELLNER, J. A.<\/small> (1996). Weak convergence. In Weak Convergence and Empirical Processes<\/i>: With Applications to Statistics Springer Series in Statistics<\/i> 16\u201328 Springer, New York.","DOI":"10.1007\/978-1-4757-2545-2"},{"key":"34","unstructured":"YAN, T.<\/small>, LENG, C.<\/small> and ZHU, J.<\/small> (2015). Supplement to \u201cAsymptotics in directed exponential random graph models with an increasing bi-degree sequence\u201d. Ann. Statist.<\/i>"},{"key":"36","unstructured":"YAN, T.<\/small> and XU, J.<\/small> (2012). Approximating the inverse of a balanced symmetric matrix with positive elements. arXiv preprint. Available at arXiv:1202.1058<\/a>."}],"container-title":["The Annals of Statistics"],"original-title":[],"deposited":{"date-parts":[[2026,10,7]],"date-time":"2026-10-07T16:22:48Z","timestamp":1791390168000},"score":1,"resource":{"primary":{"URL":"https:\/\/projecteuclid.org\/journals\/annals-of-statistics\/volume-53\/issue-6\/A-two-way-heterogeneity-model-for-dynamic-networks\/10.1214\/25-AOS2557.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,1]]},"references-count":37,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2025,12,1]]}},"URL":"https:\/\/doi.org\/10.1214\/25-aos2557","relation":{},"ISSN":["0090-5364","2168-8966"],"issn-type":[{"value":"0090-5364","type":"print"},{"value":"2168-8966","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,1]]}}}