{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,13]],"date-time":"2025-12-13T06:57:09Z","timestamp":1765609029351,"version":"build-2065373602"},"reference-count":47,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2023,10,4]],"date-time":"2023-10-04T00:00:00Z","timestamp":1696377600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Alberto Leon-Garcia\u2019s University of Toronto operating grant"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>This paper addresses the problem of learning temporal graph representations, which capture the changing nature of complex evolving networks. Existing approaches mainly focus on adding new nodes and edges to capture dynamic graph structures. However, to achieve more accurate representation of graph evolution, we consider both the addition and deletion of nodes and edges as events. These events occur at irregular time scales and are modeled using temporal point processes. Our goal is to learn the conditional intensity function of the temporal point process to investigate the influence of deletion events on node representation learning for link-level prediction. We incorporate network entropy, a measure of node and edge significance, to capture the effect of node deletion and edge removal in our framework. Additionally, we leveraged the characteristics of a generalized temporal Hawkes process, which considers the inhibitory effects of events where past occurrences can reduce future intensity. This framework enables dynamic representation learning by effectively modeling both addition and deletion events in the temporal graph. To evaluate our approach, we utilize autonomous system graphs, a family of inhomogeneous sparse graphs with instances of node and edge additions and deletions, in a link prediction task. By integrating these enhancements into our framework, we improve the accuracy of dynamic link prediction and enable better understanding of the dynamic evolution of complex networks.<\/jats:p>","DOI":"10.3390\/make5040069","type":"journal-article","created":{"date-parts":[[2023,10,4]],"date-time":"2023-10-04T11:58:57Z","timestamp":1696420737000},"page":"1359-1381","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Entropy-Aware Time-Varying Graph Neural Networks with Generalized Temporal Hawkes Process: Dynamic Link Prediction in the Presence of Node Addition and Deletion"],"prefix":"10.3390","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1030-592X","authenticated-orcid":false,"given":"Bahareh","family":"Najafi","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of British Columbia, Vancouver, BC V6T 1Z2, Canada"},{"name":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON M5S 3G8, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Saeedeh","family":"Parsaeefard","sequence":"additional","affiliation":[{"name":"Apple Inc., San Francisco, CA 95014, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9888-0389","authenticated-orcid":false,"given":"Alberto","family":"Leon-Garcia","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Toronto, Toronto, ON M5S 3G8, Canada"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,10,4]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Thakur, N., and Han, C.Y. (2021). A study of fall detection in assisted living: Identifying and improving the optimal machine learning method. J. Sens. Actuator Netw., 10.","DOI":"10.3390\/jsan10030039"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Bergamaschi, S., De Nardis, S., Martoglia, R., Ruozzi, F., Sala, L., Vanzini, M., and Vigliermo, R.A. (2022). Novel perspectives for the management of multilingual and multialphabetic heritages through automatic knowledge extraction: The digitalmaktaba approach. Sensors, 22.","DOI":"10.3390\/s22113995"},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Rizoiu, M.A., Xie, L., Sanner, S., Cebrian, M., Yu, H., and Van Hentenryck, P. (2017, January 3\u20137). Expecting to be hip: Hawkes intensity processes for social media popularity. Proceedings of the 26th International Conference on World Wide Web, Perth, Australia.","DOI":"10.1145\/3038912.3052650"},{"key":"ref_4","unstructured":"Rossi, E., Chamberlain, B., Frasca, F., Eynard, D., Monti, F., and Bronstein, M. (2020). Temporal graph networks for deep learning on dynamic graphs. arXiv."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Kumar, S., Zhang, X., and Leskovec, J. (2019, January 4\u20138). Predicting dynamic embedding trajectory in temporal interaction networks. Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, Anchorage, AK, USA.","DOI":"10.1145\/3292500.3330895"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhou, H., Zheng, D., Nisa, I., Ioannidis, V., Song, X., and Karypis, G. (2022). Tgl: A general framework for temporal gnn training on billion-scale graphs. arXiv.","DOI":"10.14778\/3529337.3529342"},{"key":"ref_7","unstructured":"Lee, D., Lee, J., and Shin, K. (2023). Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs. arXiv."},{"key":"ref_8","unstructured":"Cong, W., Zhang, S., Kang, J., Yuan, B., Wu, H., Zhou, X., Tong, H., and Mahdavi, M. (2023). Do We Really Need Complicated Model Architectures For Temporal Networks?. arXiv."},{"key":"ref_9","unstructured":"Xu, D., Ruan, C., Korpeoglu, E., Kumar, S., and Achan, K. (2020). Inductive representation learning on temporal graphs. arXiv."},{"key":"ref_10","unstructured":"Trivedi, R., Farajtabar, M., Biswal, P., and Zha, H. (2019, January 6\u20139). Dyrep: Learning representations over dynamic graphs. Proceedings of the International Conference on Learning Representations, New Orleans, LA, USA."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Knyazev, B., Augusta, C., and Taylor, G.W. (2021). Learning temporal attention in dynamic graphs with bilinear interactions. PLoS ONE, 16.","DOI":"10.1371\/journal.pone.0247936"},{"key":"ref_12","unstructured":"Kipf, T., Fetaya, E., Wang, K.C., Welling, M., and Zemel, R. (2018, January 10\u201315). Neural relational inference for interacting systems. Proceedings of the International Conference on Machine Learning, Stockholm, Sweden."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Wen, Z., and Fang, Y. (2022, January 25\u201329). TREND: TempoRal Event and Node Dynamics for Graph Representation Learning. Proceedings of the ACM Web Conference 2022, Virtual.","DOI":"10.1145\/3485447.3512164"},{"key":"ref_14","unstructured":"Moallemy-Oureh, A., Beddar-Wiesing, S., Nather, R., and Thomas, J.M. (2022). FDGNN: Fully Dynamic Graph Neural Network. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1109\/TCSS.2022.3162229","article-title":"Link Prediction and Unlink Prediction on Dynamic Networks","volume":"10","author":"Muro","year":"2022","journal-title":"IEEE Trans. Comput. Soc. Syst."},{"key":"ref_16","unstructured":"Daley, D.J., and Vere-Jones, D. (2003). An Introduction to the Theory of Point Processes: Volume I: Elementary Theory and Methods, Springer."},{"key":"ref_17","first-page":"1","article-title":"Using time dependent covariates and time dependent coefficients in the cox model","volume":"2","author":"Therneau","year":"2017","journal-title":"Surviv. Vignettes"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Ai, X. (2017). Node importance ranking of complex networks with entropy variation. Entropy, 19.","DOI":"10.3390\/e19070303"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"466","DOI":"10.1016\/j.socnet.2005.11.005","article-title":"A graph-theoretic perspective on centrality","volume":"28","author":"Borgatti","year":"2006","journal-title":"Soc. Netw."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"108701","DOI":"10.1103\/PhysRevLett.88.108701","article-title":"Fluctuation-driven dynamics of the Internet topology","volume":"88","author":"Goh","year":"2002","journal-title":"Phys. Rev. Lett."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"910","DOI":"10.1126\/science.1065103","article-title":"Specificity and stability in topology of protein networks","volume":"296","author":"Maslov","year":"2002","journal-title":"Science"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"026126","DOI":"10.1103\/PhysRevE.67.026126","article-title":"Mixing patterns in networks","volume":"67","author":"Newman","year":"2003","journal-title":"Phys. Rev. E"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"208701","DOI":"10.1103\/PhysRevLett.89.208701","article-title":"Assortative mixing in networks","volume":"89","author":"Newman","year":"2002","journal-title":"Phys. Rev. Lett."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"714","DOI":"10.1016\/j.physa.2007.02.039","article-title":"Effect of node deleting on network structure","volume":"379","author":"Deng","year":"2007","journal-title":"Phys. A Stat. Mech. Its Appl."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.socnet.2007.11.001","article-title":"On variants of shortest-path betweenness centrality and their generic computation","volume":"30","author":"Brandes","year":"2008","journal-title":"Soc. Netw."},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Leskovec, J., Kleinberg, J., and Faloutsos, C. (2005, January 21\u201324). Graphs over time: Densification laws, shrinking diameters and possible explanations. Proceedings of the Eleventh ACM SIGKDD International Conference on Knowledge Discovery in Data Mining, Chicago, IL, USA.","DOI":"10.1145\/1081870.1081893"},{"key":"ref_27","unstructured":"Mei, H., and Eisner, J.M. (2017). The neural hawkes process: A neurally self-modulating multivariate point process. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"97","DOI":"10.1016\/j.physrep.2012.03.001","article-title":"Temporal networks","volume":"519","author":"Holme","year":"2012","journal-title":"Phys. Rep."},{"key":"ref_29","unstructured":"Goyal, P., Kamra, N., He, X., and Liu, Y. (2018). Dyngem: Deep embedding method for dynamic graphs. arXiv."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"29219","DOI":"10.1109\/ACCESS.2018.2839770","article-title":"Deep dynamic network embedding for link prediction","volume":"6","author":"Li","year":"2018","journal-title":"IEEE Access"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Sankar, A., Wu, Y., Gou, L., Zhang, W., and Yang, H. (2020, January 10\u201313). Dysat: Deep neural representation learning on dynamic graphs via self-attention networks. Proceedings of the 13th International Conference on Web Search and Data Mining, Virtual.","DOI":"10.1145\/3336191.3371845"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Zhou, L., Yang, Y., Ren, X., Wu, F., and Zhuang, Y. (2018, January 2\u20133). Dynamic network embedding by modeling triadic closure process. Proceedings of the AAAI Conference on Artificial Intelligence, New Orleans, LA, USA.","DOI":"10.1609\/aaai.v32i1.11257"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Nguyen, G.H., Lee, J.B., Rossi, R.A., Ahmed, N.K., Koh, E., and Kim, S. (2018, January 23\u201327). Continuous-time dynamic network embeddings. Proceedings of the Companion Proceedings of the the Web Conference 2018, Lyon, France.","DOI":"10.1145\/3184558.3191526"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Zuo, Y., Liu, G., Lin, H., Guo, J., Hu, X., and Wu, J. (2018, January 19\u201323). Embedding temporal network via neighborhood formation. Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, London, UK.","DOI":"10.1145\/3219819.3220054"},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"83","DOI":"10.1093\/biomet\/58.1.83","article-title":"Spectra of some self-exciting and mutually exciting point processes","volume":"58","author":"Hawkes","year":"1971","journal-title":"Biometrika"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Lu, Y., Wang, X., Shi, C., Yu, P.S., and Ye, Y. (2019, January 3\u20137). Temporal network embedding with micro-and macro-dynamics. Proceedings of the 28th ACM International Conference on Information and Knowledge Management, Beijing, China.","DOI":"10.1145\/3357384.3357943"},{"key":"ref_37","unstructured":"Jensen, A. (1974). Traffic Equilibrium Methods, Proceedings of the International Symposium Held at the University of Montreal, Montreal, QC, Canada, 21\u201323 November 1974, Springer."},{"key":"ref_38","doi-asserted-by":"crossref","unstructured":"You, J., Du, T., and Leskovec, J. (2022, January 14\u201318). ROLAND: Graph learning framework for dynamic graphs. Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining, Washington, DC, USA.","DOI":"10.1145\/3534678.3539300"},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"514","DOI":"10.1109\/TNET.2003.815300","article-title":"Power laws and the AS-level Internet topology","volume":"11","author":"Siganos","year":"2003","journal-title":"IEEE\/ACM Trans. Netw."},{"key":"ref_40","unstructured":"Tauro, S.L., Palmer, C., Siganos, G., and Faloutsos, M. (2001, January 25\u201329). A simple conceptual model for the internet topology. Proceedings of the GLOBECOM\u201901, IEEE Global Telecommunications Conference (Cat. No. 01CH37270), San Antonio, TX, USA."},{"key":"ref_41","unstructured":"Gaertler, M., and Patrignani, M. (2004, January 22\u201323). Dynamic analysis of the autonomous system graph. Proceedings of the IPS 2004, International Workshop on Inter-Domain Performance and Simulation, Budapest, Hungary."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"269","DOI":"10.1016\/0378-8733(83)90028-X","article-title":"Network structure and minimum degree","volume":"5","author":"Seidman","year":"1983","journal-title":"Soc. Netw."},{"key":"ref_43","doi-asserted-by":"crossref","unstructured":"Brandes, U., Gaertler, M., and Wagner, D. (2003, January 16\u201319). Experiments on graph clustering algorithms. Proceedings of the Algorithms-ESA 2003: 11th Annual European Symposium, Budapest, Hungary. Proceedings 11.","DOI":"10.1007\/978-3-540-39658-1_52"},{"key":"ref_44","unstructured":"Hamilton, W., Ying, Z., and Leskovec, J. (2017). Inductive representation learning on large graphs. Adv. Neural Inf. Process. Syst., 30."},{"key":"ref_45","unstructured":"Gastaldi, X. (2017). Shake-shake regularization. arXiv."},{"key":"ref_46","unstructured":"Gavin, D.G. (2010). K1D: Multivariate Ripley\u2019s K-Function for One-Dimensional Data, University of Oregon."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"209","DOI":"10.1111\/j.0030-1299.2004.12497.x","article-title":"Rings, circles, and null-models for point pattern analysis in ecology","volume":"104","author":"Wiegand","year":"2004","journal-title":"Oikos"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/5\/4\/69\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:05:11Z","timestamp":1760130311000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/5\/4\/69"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,4]]},"references-count":47,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["make5040069"],"URL":"https:\/\/doi.org\/10.3390\/make5040069","relation":{},"ISSN":["2504-4990"],"issn-type":[{"type":"electronic","value":"2504-4990"}],"subject":[],"published":{"date-parts":[[2023,10,4]]}}}