{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,3]],"date-time":"2025-12-03T18:06:50Z","timestamp":1764785210940,"version":"build-2065373602"},"reference-count":21,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T00:00:00Z","timestamp":1693872000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Research Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["BDCC"],"abstract":"<jats:p>Social networks have become important objects of study in recent years. Social media marketing has, for example, greatly benefited from the vast literature developed in the past two decades. The study of social networks has taken advantage of recent advances in machine learning to process these immense amounts of data. Automatic emotional labeling of content on social media has, for example, been made possible by the recent progress in natural language processing. In this work, we are interested in the influence maximization problem, which consists of finding the most influential nodes in the social network. The problem is classically carried out using classical performance metrics such as accuracy or recall, which is not the end goal of the influence maximization problem. Our work presents an end-to-end learning model, SGREEDYNN, for the selection of the most influential nodes in a social network, given a history of information diffusion. In addition, this work proposes data visualization techniques to interpret the augmenting performances of our method compared to classical training. The results of this method are confirmed by visualizing the final influence of the selected nodes on network instances with edge bundling techniques. Edge bundling is a visual aggregation technique that makes patterns emerge. It has been shown to be an interesting asset for decision-making. By using edge bundling, we observe that our method chooses more diverse and high-degree nodes compared to the classical training.<\/jats:p>","DOI":"10.3390\/bdcc7030149","type":"journal-article","created":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T09:46:20Z","timestamp":1693907180000},"page":"149","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Visual Explanations of Differentiable Greedy Model Predictions on the Influence Maximization Problem"],"prefix":"10.3390","volume":"7","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-1489-6161","authenticated-orcid":false,"given":"Mario","family":"Michelessa","sequence":"first","affiliation":[{"name":"Department of Statistics and Data Science, Faculty of Science, National University of Singapore, Singapore 117546, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4318-6717","authenticated-orcid":false,"given":"Christophe","family":"Hurter","sequence":"additional","affiliation":[{"name":"ENAC, Universit\u00e9 de Toulouse, 31400 Toulouse, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brian Y.","family":"Lim","sequence":"additional","affiliation":[{"name":"Department of Statistics and Data Science, Faculty of Science, National University of Singapore, Singapore 117546, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jamie Ng Suat","family":"Ling","sequence":"additional","affiliation":[{"name":"Institute for Infocomm Research, A*STAR, Singapore 138632, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bogdan","family":"Cautis","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Paris-Sud, 91405 Orsay, France"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5522-4058","authenticated-orcid":false,"given":"Carol Anne","family":"Hargreaves","sequence":"additional","affiliation":[{"name":"Department of Statistics and Data Science, Faculty of Science, National University of Singapore, Singapore 117546, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,9,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Chen, W., Wang, C., and Wang, Y. (2010, January 25\u201328). Scalable Influence Maximization for Prevalent Viral Marketing in Large-Scale Social Networks. Proceedings of the 16th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD \u201910, Washington, DC, USA.","DOI":"10.1145\/1835804.1835934"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1038\/nature11421","article-title":"A 61-Million-Person Experiment in Social Influence and Political Mobilization","volume":"489","author":"Bond","year":"2012","journal-title":"Nature"},{"key":"ref_3","first-page":"1809","article-title":"Social networks, government surveillance, and the Fourth Amendment Mosaic Theory","volume":"94","author":"Bedi","year":"2014","journal-title":"BUL Rev."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Kempe, D., Kleinberg, J., and Tardos, E. (2003, January 24\u201327). Maximizing the Spread of Influence through a Social Network. Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD \u201903, Washington, DC, USA.","DOI":"10.1145\/956750.956769"},{"key":"ref_5","first-page":"28","article-title":"Differentiable Greedy Algorithm for Monotone Submodular Maximization: Guarantees, Gradient Estimators, and Applications","volume":"Volume 130","author":"Banerjee","year":"2021","journal-title":"Proceedings of the 24th International Conference on Artificial Intelligence and Statistics"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1080\/00031305.1973.10478966","article-title":"Graphs in Statistical Analysis","volume":"27","author":"Anscombe","year":"1973","journal-title":"Am. Stat."},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Leskovec, J., Krause, A., Guestrin, C., Faloutsos, C., VanBriesen, J., and Glance, N. (2007, January 12\u201315). Cost-Effective Outbreak Detection in Networks. Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, KDD \u201907, New York, NY, USA.","DOI":"10.1145\/1281192.1281239"},{"key":"ref_8","unstructured":"Goyal, A., Lu, W., and Lakshmanan, L.V. (April, January 28). CELF++: Optimizing the Greedy Algorithm for Influence Maximization in Social Networks. Proceedings of the 20th International Conference Companion on World Wide Web, WWW \u201911, Hyderabad, India."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Li, C., Ma, J., Guo, X., and Mei, Q. (2017, January 3\u20137). DeepCas: An End-to-End Predictor of Information Cascades, Republic and Canton of Geneva, CHE. Proceedings of the 26th International Conference on World Wide Web, WWW \u201917, Perth, Australia.","DOI":"10.1145\/3038912.3052643"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"2135","DOI":"10.1109\/TMM.2016.2614220","article-title":"A survey on visual analytics of social media data","volume":"18","author":"Wu","year":"2016","journal-title":"IEEE Trans. Multimed."},{"key":"ref_11","first-page":"811","article-title":"OD Morphing: Balancing simplicity with faithfulness for OD bundling","volume":"26","author":"Lyu","year":"2019","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Gansner, E.R., Hu, Y., North, S.C., and Scheidegger, C.E. (2011, January 1\u20134). Multilevel agglomerative edge bundling for visualizing large graphs. Proceedings of the IEEE Pacific Visualization Symposium, Hong Kong, China.","DOI":"10.1109\/PACIFICVIS.2011.5742389"},{"key":"ref_13","unstructured":"Qu, H., Zhou, H., and Wu, Y. (2006, January 18\u201320). Controllable and progressive edge clustering for large networks. Proceedings of the International Symposium on Graph Drawing, Karlsruhe, Germany."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"741","DOI":"10.1109\/TVCG.2006.147","article-title":"Hierarchical edge bundles: Visualization of adjacency relations in hierarchical data","volume":"12","author":"Holten","year":"2006","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1111\/cgf.13213","article-title":"State of the Art in Edge and Trail Bundling Techniques","volume":"36","author":"Lhuillier","year":"2017","journal-title":"Comput. Graph. Forum"},{"key":"ref_16","unstructured":"Zhang, J., Liu, B., Tang, J., Chen, T., and Li, J. (2013, January 3\u20139). Social Influence Locality for Modeling Retweeting Behaviors. Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence, IJCAI \u201913, Beijing, China."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Goyal, A., Bonchi, F., and Lakshmanan, L.V. (2010, January 3\u20136). Learning influence probabilities in social networks. Proceedings of the Third ACM International Conference on Web Search and Data Mining, New York, NY, USA.","DOI":"10.1145\/1718487.1718518"},{"key":"ref_18","unstructured":"Falkner, S., Klein, A., and Hutter, F. (2018, January 10\u201315). BOHB: Robust and efficient hyperparameter optimization at scale. Proceedings of the International Conference on Machine Learning, PMLR, Stockholm, Sweden."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"865","DOI":"10.1111\/j.1467-8659.2012.03079.x","article-title":"Graph Bundling by Kernel Density Estimation","volume":"31","author":"Hurter","year":"2012","journal-title":"Comput. Graph. Forum"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1129","DOI":"10.1002\/spe.4380211102","article-title":"Graph drawing by force-directed placement","volume":"21","author":"Fruchterman","year":"1991","journal-title":"Softw. Pract. Exp."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"109","DOI":"10.1109\/TSMC.1981.4308636","article-title":"Methods for visual understanding of hierarchical system structures","volume":"11","author":"Sugiyama","year":"1981","journal-title":"IEEE Trans. Syst. Man Cybern."}],"container-title":["Big Data and Cognitive Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-2289\/7\/3\/149\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T20:46:33Z","timestamp":1760129193000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-2289\/7\/3\/149"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,5]]},"references-count":21,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2023,9]]}},"alternative-id":["bdcc7030149"],"URL":"https:\/\/doi.org\/10.3390\/bdcc7030149","relation":{},"ISSN":["2504-2289"],"issn-type":[{"type":"electronic","value":"2504-2289"}],"subject":[],"published":{"date-parts":[[2023,9,5]]}}}