{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T18:15:45Z","timestamp":1770401745504,"version":"3.49.0"},"reference-count":40,"publisher":"American Association for the Advancement of Science (AAAS)","funder":[{"DOI":"10.13039\/501100013096","name":"Science and Technology Project of State Grid","doi-asserted-by":"publisher","award":["SGSJ0000HGJS2500038"],"award-info":[{"award-number":["SGSJ0000HGJS2500038"]}],"id":[{"id":"10.13039\/501100013096","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["spj.science.org"],"crossmark-restriction":true},"short-container-title":["Intell Comput"],"published-print":{"date-parts":[[2026,1]]},"abstract":"<jats:p>Graph simulation has emerged as a practical route to release realistic yet privacy-preserving network data, especially for temporal graphs that evolve through node and edge arrivals. However, prevailing approaches rely on temporal random walks that introduce sampling bias and become prohibitively costly at scale and impose Gaussian variational priors that fail to capture the heavy-tailed dynamics of real systems. We present a semi-implicit temporal variational graph autoencoder (SIT-VGAE) for high-fidelity temporal graph generation. SIT-VGAE samples localized ego-graphs and encodes them with a temporal graph attention network (TGAT) augmented with learnable time embeddings, capturing structural and temporal dependencies without random walk preprocessing. To overcome restrictive priors, we adopt semi-implicit variational inference in which a neural mixer defines an expressive, reparameterizable posterior family that better fits non-Gaussian dynamics. A lightweight decoder maps latent codes to timestamped edge distributions, whose assembled snapshots form generated temporal graphs. The model is trained to maximize a variational lower bound coupling a likelihood over edges with a Kullback\u2013Leibler regularizer. Across multiple real temporal graph datasets, SIT-VGAE achieves superior simulation fidelity on structural statistics, while reducing training and generation time compared with random-walk-based and Gaussian prior baselines. The resulting framework scales to large graphs via TGAT encoding and amortized inference, offering a practical, efficient, and expressive solution for realistic temporal network synthesis.<\/jats:p>","DOI":"10.34133\/icomputing.0293","type":"journal-article","created":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T03:38:43Z","timestamp":1767929923000},"update-policy":"https:\/\/doi.org\/10.34133\/aaas_crossmark_01","source":"Crossref","is-referenced-by-count":0,"title":["Semi-Implicit Temporal Variational Graph Autoencoder for Dynamic Graph Generation"],"prefix":"10.34133","volume":"5","author":[{"given":"Shenglong","family":"Liu","sequence":"first","affiliation":[{"name":"Big Data Center, State Grid Corporation of China","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yixin","family":"Li","sequence":"additional","affiliation":[{"name":"Big Data Center, State Grid Corporation of China","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Peng","sequence":"additional","affiliation":[{"name":"Big Data Center, State Grid Corporation of China","place":["China"]}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-4643-5708","authenticated-orcid":false,"given":"Xu","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, \rTongji University, Shanghai, China."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-9321-7374","authenticated-orcid":true,"given":"Zicai","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, \rTongji University, Shanghai, China."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5877-7387","authenticated-orcid":false,"given":"Dawei","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, \rTongji University, Shanghai, China."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"221","published-online":{"date-parts":[[2026,2,6]]},"reference":[{"key":"e_1_3_3_2_2","doi-asserted-by":"crossref","first-page":"897","DOI":"10.1007\/s00778-021-00701-5","article-title":"General graph generators: Experiments, analyses, and improvements","volume":"31","author":"Xiang S","year":"2022","unstructured":"Xiang S, Wen D, Cheng D, Zhang Y, Qin L, Qian Z, Lin X. General graph generators: Experiments, analyses, and improvements. VLDB J. 2022;31:897\u2013925.","journal-title":"VLDB J"},{"key":"e_1_3_3_3_2","doi-asserted-by":"crossref","unstructured":"Hines P Blumsack S Sanchez EC Barrows C. The topological and electrical structure of power grids. In: 2010 43rd Hawaii international conference on system sciences. Honolulu (HI): IEEE; 2010. p. 1\u201310.","DOI":"10.1109\/HICSS.2010.398"},{"key":"e_1_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3648470"},{"key":"e_1_3_3_5_2","doi-asserted-by":"crossref","first-page":"40","DOI":"10.1016\/j.comcom.2021.12.015","article-title":"Graph-based deep learning for communication networks: A survey","volume":"185","author":"Jiang W","year":"2022","unstructured":"Jiang W. Graph-based deep learning for communication networks: A survey. Comput Commun. 2022;185:40\u201354.","journal-title":"Comput Commun"},{"key":"e_1_3_3_6_2","doi-asserted-by":"crossref","DOI":"10.1007\/s11704-024-40474-y","article-title":"Graph neural networks for financial fraud detection: A review","volume":"19","author":"Cheng D","year":"2025","unstructured":"Cheng D, Zou Y, Xiang S, Jiang C. Graph neural networks for financial fraud detection: A review. Front Comput Sci. 2025;19: Article 199609.","journal-title":"Front Comput Sci"},{"issue":"4","key":"e_1_3_3_7_2","doi-asserted-by":"crossref","first-page":"565","DOI":"10.1142\/S1793351X20300022","article-title":"Graph computing for financial crime and fraud detection: Trends, challenges and outlook","volume":"14","author":"Kurshan E","year":"2020","unstructured":"Kurshan E, Shen H. Graph computing for financial crime and fraud detection: Trends, challenges and outlook. Int J Semant Comput. 2020;14(4):565\u2013589.","journal-title":"Int J Semant Comput"},{"issue":"2","key":"e_1_3_3_8_2","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1016\/0378-8733(83)90021-7","article-title":"Stochastic blockmodels: First steps","volume":"5","author":"Holland PW","year":"1983","unstructured":"Holland PW, Laskey KB, Leinhardt S. Stochastic blockmodels: First steps. Soc Netw. 1983;5(2):109\u2013137.","journal-title":"Soc Netw"},{"key":"e_1_3_3_9_2","unstructured":"You J Ying R Ren X Hamilton W Leskovec J. GraphRNN: Generating realistic graphs with deep auto-regressive models. In: Proceedings of the 35th international conference on machine learning. Stockholm (Sweden): PMLR; 2018. p. 5708\u20135717."},{"key":"e_1_3_3_10_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3447772","article-title":"Knowledge graphs","volume":"54","author":"Hogan A","year":"2021","unstructured":"Hogan A, Blomqvist E, Cochez M, Damato C, De Melo G, Gutierrez C, Kirrane S, Gayo JS, Navigli R, Neumaier S, et al. Knowledge graphs. ACM Comput Surv. 2021;54:1\u201337.","journal-title":"ACM Comput Surv"},{"key":"e_1_3_3_11_2","doi-asserted-by":"crossref","unstructured":"Byrd D Polychroniadou A. Differentially private secure multi-party computation for federated learning in financial applications. In: Proceedings of the first ACM international conference on AI in finance. New York (NY): Association for Computing Machinery; 2021. p. 1\u20139.","DOI":"10.1145\/3383455.3422562"},{"key":"e_1_3_3_12_2","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1090\/S0002-9947-1984-0756039-5","article-title":"On the evolution of random graphs","volume":"286","author":"Erdos PL","year":"1984","unstructured":"Erdos PL, Renyi A. On the evolution of random graphs. Trans Am Math Soc. 1984;286:257\u2013257.","journal-title":"Trans Am Math Soc"},{"key":"e_1_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.286.5439.509"},{"key":"e_1_3_3_14_2","unstructured":"Bojchevski A Shchur O Zugner D Gunnemann S. NetGAN: Generating graphs via random walks. In: Proceedings of the 35th international conference on machine learning. Stockholm (Sweden): PMLR; 2018. p. 610\u2013619."},{"key":"e_1_3_3_15_2","unstructured":"Kipf TN Welling M. Variational graph auto-encoders. In: Proceedings of the bayesian deep learning workshop at NIPS 2016. Barcelona (Spain): Curran Associates Inc.; 2016. p. 1\u20133."},{"key":"e_1_3_3_16_2","doi-asserted-by":"crossref","unstructured":"Leskovec J Kleinberg J Faloutsos C. Graphs over time: Densification laws shrinking diameters and possible explanations. In: Proceedings of the eleventh ACM SIGKDD international conference on knowledge discovery and data mining. Chicago (IL): Association for Computing Machinery; 2005. p. 177\u2013187.","DOI":"10.1145\/1081870.1081893"},{"key":"e_1_3_3_17_2","doi-asserted-by":"crossref","unstructured":"Zeno G La Fond T Neville J. DYMOND: DYnamic MOtif-NoDes network generative model. In: Proceedings of the web conference 2021. Ljubljana (Slovenia): Association for Computing Machinery; 2021. p. 718\u2013729.","DOI":"10.1145\/3442381.3450102"},{"key":"e_1_3_3_18_2","doi-asserted-by":"crossref","unstructured":"Li F Wang X Cheng D Chen C Zhang Y Lin X. Efficient dynamic attributed graph generation. In: 2025 IEEE 41st international conference on data engineering. Hong Kong (China): IEEE; 2025. p. 1101\u20131114.","DOI":"10.1109\/ICDE65448.2025.00110"},{"key":"e_1_3_3_19_2","doi-asserted-by":"crossref","unstructured":"Xiang S Xu C Cheng D Wang X Zhang Y. Efficient learning-based graph simulation for temporal graphs. In: 2025 IEEE 41st international conference on data engineering. Hong Kong (China): IEEE; 2025. p. 251\u2013264.","DOI":"10.1109\/ICDE65448.2025.00026"},{"key":"e_1_3_3_20_2","doi-asserted-by":"crossref","unstructured":"Zhou D Zheng L Han J He J. A data-driven graph generative model for temporal interaction networks. In: Proceedings of the 26th ACM SIGKDD conference on knowledge discovery & data mining. Virtual Event [originally San Diego (CA)]: Association for Computing Machinery; 2020. p. 401\u2013411.","DOI":"10.1145\/3394486.3403082"},{"key":"e_1_3_3_21_2","doi-asserted-by":"crossref","unstructured":"Gupta S Manchanda S Bedathur SJ and Ranu S. TIGGER: Scalable generative modelling for temporal interaction graphs. In: Proceedings of the 36th AAAI conference on artificial intelligence. Virtual Event [originally Vancouver (BC)]: AAAI Press; 2022. vol. 366. p. 819\u2013828.","DOI":"10.1609\/aaai.v36i6.20638"},{"key":"e_1_3_3_22_2","unstructured":"Hajiramezanali E Hasanzadeh A Duffield N Narayanan K Zhou M Qian X. Semi-implicit graph variational auto-encoders. In: Proceeding of the 33rd international conference on neural information processing systems. Vancouver (BC): Curran Associates Inc.; 2019. p. 10712\u201310723."},{"key":"e_1_3_3_23_2","unstructured":"Xu D Ruan C Korpeoglu E Kumar S Achan K. Inductive representation learning on temporal graphs. ArXiv. 2020. https:\/\/doi.org\/10.48550\/arXiv.2022.07962"},{"key":"e_1_3_3_24_2","unstructured":"Yin M Zhou M. Semi-implicit variational inference. In: Proceedings of the 35th international conference on machine learning. Stockholm (Sweden): PMLR; 2018. p. 5660\u20135569."},{"issue":"373","key":"e_1_3_3_25_2","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1080\/01621459.1981.10477598","article-title":"An exponential family of probability distributions for directed graphs","volume":"76","author":"Holland PW","year":"1981","unstructured":"Holland PW, Leinhardt S. An exponential family of probability distributions for directed graphs. J Am Stat Assoc. 1981;76(373):33\u201350.","journal-title":"J Am Stat Assoc"},{"key":"e_1_3_3_26_2","unstructured":"Kipf TN Welling M. Semi-supervised classification with graph convolutional networks. ArXiv. 2017. https:\/\/doi.org\/10.48550\/arXiv.1609.02907"},{"key":"e_1_3_3_27_2","unstructured":"Grover A Zweig A Ermon S. Graphite: Iterative generative modeling of graphs. In: Proceedings of the 36th international conference on machine learning. Long Beach (CA): PMLR; 2019. vol. 97. p. 2434\u20132444."},{"key":"e_1_3_3_28_2","unstructured":"Goodfellow IJ Pouget-Abadie J Mirza M Xu B Warde-Farley D Ozair S Courville A Bengio Y. Generative adversarial nets. In: Proceedings of the 28th international conference on neural information processing systems - volume 2. Montreal (QC): Curran Associates Inc.; 2014. p. 2672\u20132680."},{"key":"e_1_3_3_29_2","doi-asserted-by":"crossref","unstructured":"Wang H Wang J Wang J Zhao M Zhang W Zhang F Xie X Guo M. GraphGAN: Graph representation learning with generative adversarial nets. In: Proceedings of the thirty-second AAAI conference on artificial intelligence. New Orleans (LA): AAAI Press; 2018. p. 2508\u20132515.","DOI":"10.1609\/aaai.v32i1.11872"},{"issue":"8","key":"e_1_3_3_30_2","doi-asserted-by":"crossref","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","article-title":"Long short-term memory","volume":"9","author":"Hochreiter S","year":"1997","unstructured":"Hochreiter S, Schmidhuber J. Long short-term memory. Neural Computation. 1997;9(8):1735\u20131780.","journal-title":"Neural Computation"},{"key":"e_1_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1038\/323533a0"},{"key":"e_1_3_3_32_2","unstructured":"Liao R Li Y Song Y Wang S Hamilton Wl Duvenaud D Urtasun R Zemel R. Efficient graph generation with graph recurrent attention networks. In: Proceedings of the 33rd international conference on neural information processing systems. Vancouver (BC): Curran Associates Inc.; 2019. p. 11108\u201311119."},{"key":"e_1_3_3_33_2","unstructured":"Vaswani A Shazeer N Parmar N Uszkoreit J Jones L Gomez AN Kaiser L Polosukhin. Attention is all you need. In: Proceedings of the 31st international conference on neural information processing systems. Long Beach (CA): Curran Associates Inc.; 2017. p. 6000\u20136010."},{"key":"e_1_3_3_34_2","unstructured":"Kazemi SM Goel R Eghbali S Ramanan J Sahota J Thakur S Wu S Smyth C Poupart P Brubaker M. Time2Vec: Learning a vector representation of time. ArXiv. 2019. https:\/\/doi.org\/10.48550\/arXiv.1907.05321"},{"key":"e_1_3_3_35_2","unstructured":"Mehta N Duke LC Rai P. Stochastic blockmodels meet graph neural networks. In: Proceedings of the 36th international conference on machine learning. Long Beach (CA): PMLR; 2019. p. 4466\u20134474."},{"key":"e_1_3_3_36_2","doi-asserted-by":"crossref","unstructured":"Rossi RA Ahmed NK. The network data repository with interactive graph analytics and visualization. In: Proceedings of the twenty-ninth AAAI conference on artificial intelligence. Austin (TX): AAAI Press; 2015. p. 4292\u20134293.","DOI":"10.1609\/aaai.v29i1.9277"},{"key":"e_1_3_3_37_2","doi-asserted-by":"crossref","unstructured":"Kumar S Spezzano F Subrahmanian V Faloutsos C. Edge weight prediction in weighted signed networks. In: 2016 IEEE 16th international conference on data mining. Barcelona (Spain): IEEE; 2016. p. 221\u2013230.","DOI":"10.1109\/ICDM.2016.0033"},{"key":"e_1_3_3_38_2","doi-asserted-by":"crossref","unstructured":"Kumar S Hooi B Makhija D Kumar M Faloutsos C Subrahmanian V. Rev2: Fraudulent user prediction in rating platforms. In: Proceedings of the eleventh ACM international conference on web search and data mining. Marina del Rey (CA): Association for Computing Machinery; 2018. p. 333\u2013341.","DOI":"10.1145\/3159652.3159729"},{"key":"e_1_3_3_39_2","doi-asserted-by":"crossref","unstructured":"Leskovec J Huttenlocher D Kleinberg J. Predicting positive and negative links in online social networks. In: Proceedings of the 19th international conference on world wide web. Raleigh (NC): Association for Computing Machinery; 2010. p. 641\u2013650.","DOI":"10.1145\/1772690.1772756"},{"key":"e_1_3_3_40_2","doi-asserted-by":"crossref","unstructured":"Viswanath B Mislove A Cha M Gummadi KP. On the evolution of user interaction in Facebook. In: Proceedings of the 2nd ACM workshop on online social networks. Barcelona (Spain): Association for Computing Machinery; 2009. p. 37\u201342.","DOI":"10.1145\/1592665.1592675"},{"key":"e_1_3_3_41_2","unstructured":"Leskovec J Krevl A. SNAP datasets: Stanford large network dataset collection. Stanford University. June 2014. http:\/\/snap.stanford.edu\/data"}],"container-title":["Intelligent Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/spj.science.org\/doi\/pdf\/10.34133\/icomputing.0293","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,6]],"date-time":"2026-02-06T08:00:43Z","timestamp":1770364843000},"score":1,"resource":{"primary":{"URL":"https:\/\/spj.science.org\/doi\/10.34133\/icomputing.0293"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":40,"alternative-id":["10.34133\/icomputing.0293"],"URL":"https:\/\/doi.org\/10.34133\/icomputing.0293","relation":{},"ISSN":["2771-5892"],"issn-type":[{"value":"2771-5892","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]},"assertion":[{"value":"2025-09-19","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-07","order":1,"name":"revised","label":"Revised","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-01-08","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-02-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"0293"}}