{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T07:16:12Z","timestamp":1784186172716,"version":"3.55.0"},"reference-count":35,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100007241","name":"Universit\u00e9 Paris-Saclay","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100007241","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Data Min Knowl Disc"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Influence maximization is a fundamental problem in network analysis, focusing on identifying a subset of nodes in a social network to maximize the spread of influence. In this paper, we present an approach for tackling the Influence Maximization (IM) problem, integrating Deep Reinforcement Learning (DRL) techniques with attentive Graph Neural Networks (GATs). Our study builds upon a prior algorithm (S2V-DQN-IM) and progressively refines it towards IM-GNN, ultimately achieving competitive performance against state-of-the-art methods on classic IM. Through experiments on benchmark datasets, we empirically validate the effectiveness of graph attention mechanisms and positional encoding, using the graph magnetic Laplacian, to reach state-of-the-art performance in terms of influence spread. Building on this success, we extend our IM-GNN framework to incorporate\n                    <jats:italic>topic-awareness<\/jats:italic>\n                    in TIM-GNN, recognizing the inherent topical nature of real-world diffusions. By harnessing probabilistic techniques, we construct topic-aware social graphs using real cascades and assess the effectivenesss of TIM-GNN on them. Our extensive experimental results validate the utility of our topic-aware approach, demonstrating significant advances over existing topic-aware IM methods. Finally, in order to improve upon performance (latency) at query time, we develop a variant of TIM-GNN, called TIM-GNN\n                    <jats:inline-formula>\n                      <jats:tex-math>$$^x$$<\/jats:tex-math>\n                    <\/jats:inline-formula>\n                    , by using\n                    <jats:italic>cross<\/jats:italic>\n                    -attention mechanisms. We show it maintains comparable overall spread performance as its predecessor, while achieving a 10x-20x speed-up.\n                  <\/jats:p>","DOI":"10.1007\/s10618-025-01133-3","type":"journal-article","created":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T02:29:21Z","timestamp":1755570561000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Topic-aware influence maximization with deep reinforcement learning and graph attention networks"],"prefix":"10.1007","volume":"39","author":[{"given":"Taha","family":"Halal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bogdan","family":"Cautis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beno\u00eet","family":"Groz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruize","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,19]]},"reference":[{"key":"1133_CR1","doi-asserted-by":"publisher","unstructured":"Arora A, Galhotra S, Ranu S (2017) Debunking the myths of influence maximization: An in-depth benchmarking study. In: Salihoglu S, Zhou W, Chirkova R, Yang J, Suciu D (eds.) Proceedings of the 2017 ACM International Conference on Management of Data, SIGMOD Conference 2017, Chicago, IL, USA, May 14-19, 2017, pp. 651\u2013666. ACM. https:\/\/doi.org\/10.1145\/3035918.3035924","DOI":"10.1145\/3035918.3035924"},{"key":"1133_CR2","doi-asserted-by":"publisher","unstructured":"Aslay \u00c7, Barbieri N, Bonchi F, Baeza-Yates R (2014) Online topic-aware influence maximization queries. In: Amer-Yahia S, Christophides V, Kementsietsidis A, Garofalakis MN, Idreos S, Leroy V (eds.) Proceedings of the 17th International Conference on Extending Database Technology, EDBT 2014, Athens, Greece, March 24-28, 2014, pp. 295\u2013306. OpenProceedings.org. https:\/\/doi.org\/10.5441\/002\/edbt.2014.28","DOI":"10.5441\/002\/edbt.2014.28"},{"issue":"3","key":"1133_CR3","doi-asserted-by":"publisher","first-page":"555","DOI":"10.1007\/s10115-013-0646-6","volume":"37","author":"N Barbieri","year":"2013","unstructured":"Barbieri N, Bonchi F, Manco G (2013) Topic-aware social influence propagation models. Knowl Inf Syst 37(3):555\u2013584. https:\/\/doi.org\/10.1007\/s10115-013-0646-6","journal-title":"Knowl Inf Syst"},{"key":"1133_CR4","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1007\/978-3-319-71249-9_41","volume-title":"Machine learning and knowledge discovery in databases","author":"N Barbieri","year":"2017","unstructured":"Barbieri N, Manco G, Ritacco E (2017) Survival factorization on diffusion networks. In: Ceci M, Hollm\u00e9n J, Todorovski L, Vens C, D\u017eeroski S (eds) Machine learning and knowledge discovery in databases. Springer, Cham, pp 684\u2013700"},{"key":"1133_CR5","unstructured":"Borgs C, Brautbar M, Chayes JT, Lucier B (2012) Influence maximization in social networks: Towards an optimal algorithmic solution. CoRR arXiv:abs\/1212.0884"},{"key":"1133_CR6","unstructured":"Bradbury J, Frostig R, Hawkins P, Johnson MJ, Leary C, Maclaurin D, Necula G, Paszke A, VanderPlas J, Wanderman-Milne S, Zhang Q (2018) JAX: Composable Transformations of Python+NumPy programs. http:\/\/github.com\/google\/jax"},{"issue":"6","key":"1133_CR7","doi-asserted-by":"publisher","first-page":"666","DOI":"10.14778\/2735703.2735706","volume":"8","author":"S Chen","year":"2015","unstructured":"Chen S, Fan J, Li G, Feng J, Tan K, Tang J (2015b) Online topic-aware influence maximization. Proc VLDB Endow 8(6):666\u2013677","journal-title":"Proc VLDB Endow"},{"key":"1133_CR8","doi-asserted-by":"publisher","DOI":"10.1109\/tcss.2023.3272331","author":"T Chen","year":"2023","unstructured":"Chen T, Yan S, Guo J, Wu W (2023) ToupleGDD: a fine-designed solution of influence maximization by deep reinforcement learning. IEEE Trans Comput Soc Syst. https:\/\/doi.org\/10.1109\/tcss.2023.3272331","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"1133_CR9","doi-asserted-by":"publisher","unstructured":"Chen W, Lin T, Yang C (2015a) Real-time topic-aware influence maximization using preprocessing. In: Thai MT, Nguyen NP, Shen H (eds.) Computational Social Networks - 4th International Conference, CSoNet 2015, Beijing, China, August 4-6, 2015, Proceedings. Lecture Notes in Computer Science, vol. 9197, pp. 1\u201313. Springer. https:\/\/doi.org\/10.1007\/978-3-319-21786-4_1","DOI":"10.1007\/978-3-319-21786-4_1"},{"key":"1133_CR10","unstructured":"Chen H, Qiu W, Ou H, An B, Tambe M (2021) Contingency-aware influence maximization: a reinforcement learning approach. In: UAI"},{"key":"1133_CR11","unstructured":"Dai H, Dai B, Song L (2016) Discriminative embeddings of latent variable models for structured data. CoRR arXiv:abs\/1603.05629"},{"key":"1133_CR12","unstructured":"Dai H, Khalil EB, Zhang Y, Dilkina B, Song L (2017) Learning combinatorial optimization algorithms over graphs. CoRR arXiv:abs\/1704.01665"},{"key":"1133_CR13","first-page":"1","volume":"7","author":"J Demsar","year":"2006","unstructured":"Demsar J (2006) Statistical comparisons of classifiers over multiple data sets. J Mach Learn Res 7:1\u201330","journal-title":"J Mach Learn Res"},{"key":"1133_CR14","unstructured":"Du N, Song L, Woo H, Zha H (2013) Uncover topic-sensitive information diffusion networks. In: Proceedings of the Sixteenth International Conference on Artificial Intelligence and Statistics, AISTATS 2013, Scottsdale, AZ, USA, April 29 - May 1, 2013, pp. 229\u2013237"},{"key":"1133_CR15","unstructured":"Geisler S, Li Y, Mankowitz D, Cemgil AT, G\u00fcnnemann S, Paduraru C (2023) Transformers Meet Directed Graphs"},{"key":"1133_CR16","unstructured":"Godwin J, Keck T, Battaglia P, Bapst V, Kipf T, Li Y, Stachenfeld K, Veli\u010dkovi\u0107 P, Sanchez-Gonzalez A (2020) Jraph: a library for graph neural networks in jax. http:\/\/github.com\/deepmind\/jraph"},{"key":"1133_CR17","doi-asserted-by":"publisher","unstructured":"Goyal A, Bonchi F, Lakshmanan LVS (2010) Learning influence probabilities in social networks. In: Proceedings of the Third ACM International Conference on Web Search and Data Mining. WSDM \u201910, pp. 241\u2013250. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/1718487.1718518","DOI":"10.1145\/1718487.1718518"},{"key":"1133_CR18","unstructured":"He Y, Permultter M, Reinert G, Cucuringu M (2022) MSGNN: a spectral graph neural network based on a novel magnetic signed Laplacian"},{"key":"1133_CR19","doi-asserted-by":"publisher","unstructured":"Kempe D, Kleinberg J, Tardos E (2003) Maximizing the spread of influence through a social network. In: Proceedings of the Ninth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD \u201903, pp. 137\u2013146. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/956750.956769","DOI":"10.1145\/956750.956769"},{"key":"1133_CR20","doi-asserted-by":"publisher","unstructured":"Leskovec J, Krause A, Guestrin C, Faloutsos C, VanBriesen J, Glance N (2007) Cost-effective outbreak detection in networks. In: Proceedings of the 13th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. KDD \u201907, pp. 420\u2013429. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/1281192.1281239","DOI":"10.1145\/1281192.1281239"},{"issue":"10","key":"1133_CR21","doi-asserted-by":"publisher","first-page":"1852","DOI":"10.1109\/TKDE.2018.2807843","volume":"30","author":"Y Li","year":"2018","unstructured":"Li Y, Fan J, Wang Y, Tan K (2018) Influence maximization on social graphs: a survey. IEEE Trans Knowl Data Eng 30(10):1852\u20131872. https:\/\/doi.org\/10.1109\/TKDE.2018.2807843","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1133_CR22","doi-asserted-by":"publisher","DOI":"10.1145\/3604559","author":"Y Li","year":"2023","unstructured":"Li Y, Gao H, Gao Y, Guo J, Wu W (2023) A survey on influence maximization: from an ml-based combinatorial optimization. ACM Trans Knowl Discov Data. https:\/\/doi.org\/10.1145\/3604559","journal-title":"ACM Trans Knowl Discov Data"},{"key":"1133_CR23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3164667","author":"H Li","year":"2022","unstructured":"Li H, Xu M, Bhowmick SS, Rayhan JS, Sun C, Cui J (2022) Piano: influence maximization meets deep reinforcement learning. IEEE Trans Comput Soc Syst. https:\/\/doi.org\/10.1109\/TCSS.2022.3164667","journal-title":"IEEE Trans Comput Soc Syst"},{"key":"1133_CR24","unstructured":"Ling C, Jiang J, Wang J, Thai MT, Xue R, Song J, Qiu M, Zhao L (2023) Deep graph representation learning and optimization for influence maximization. In: Krause, A., Brunskill, E., Cho, K., Engelhardt, B., Sabato, S., Scarlett, J. (eds.) International Conference on Machine Learning, ICML 2023, 23-29 July 2023, Honolulu, Hawaii, USA. Proceedings of Machine Learning Research, vol. 202, pp. 21350\u201321361. PMLR. https:\/\/proceedings.mlr.press\/v202\/ling23b.html"},{"key":"1133_CR25","unstructured":"Manchanda S, Mittal A, Dhawan A, Medya S, Ranu S, Singh A (2020) Gcomb: learning budget-constrained combinatorial algorithms over billion-sized graphs. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 20000\u201320011. Curran Associates, Inc."},{"key":"1133_CR26","doi-asserted-by":"publisher","unstructured":"Ohsaka N (2020) The solution distribution of influence maximization: a high-level experimental study on three algorithmic approaches. In: Maier D, Pottinger R, Doan A, Tan W, Alawini A, Ngo HQ (eds.) Proceedings of the 2020 International Conference on Management of Data, SIGMOD Conference 2020, Online Conference [Portland, OR, USA], June 14-19, 2020, pp. 2151\u20132166. ACM. https:\/\/doi.org\/10.1145\/3318464.3380564","DOI":"10.1145\/3318464.3380564"},{"issue":"9","key":"1133_CR27","doi-asserted-by":"publisher","first-page":"4398","DOI":"10.1109\/TKDE.2020.3040028","volume":"34","author":"G Panagopoulos","year":"2022","unstructured":"Panagopoulos G, Malliaros FD, Vazirgiannis M (2022) Multi-task learning for influence estimation and maximization. IEEE Trans Knowl Data Eng 34(9):4398\u20134409","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"1133_CR28","doi-asserted-by":"publisher","unstructured":"Panagopoulos G, Malliaros FD, Vazirgiannis M (2018) Diffugreedy: An influence maximization algorithm based on diffusion cascades. In: Aiello LM, Cherifi C, Cherifi H, Lambiotte R, Li\u00f3 P, Rocha LM (eds.) Complex Networks and Their Applications VII - Volume 1 Proceedings The 7th International Conference on Complex Networks and Their Applications COMPLEX NETWORKS 2018, Cambridge, UK, December 11-13, 2018. Studies in Computational Intelligence, vol. 812, pp. 392\u2013404. Springer. https:\/\/doi.org\/10.1007\/978-3-030-05411-3_32","DOI":"10.1007\/978-3-030-05411-3_32"},{"key":"1133_CR29","unstructured":"Schaul T, Quan J, Antonoglou I, Silver D (2016) Prioritized Experience Replay"},{"key":"1133_CR30","doi-asserted-by":"publisher","unstructured":"Tang Y, Shi Y, Xiao X (2015) Influence maximization in near-linear time: A martingale approach. In: Proceedings of the 2015 ACM SIGMOD International Conference on Management of Data. SIGMOD \u201915, pp. 1539\u20131554. Association for Computing Machinery, New York, NY, USA. https:\/\/doi.org\/10.1145\/2723372.2723734","DOI":"10.1145\/2723372.2723734"},{"issue":"1","key":"1133_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s41019-020-00117-1","volume":"5","author":"S Tian","year":"2020","unstructured":"Tian S, Mo S, Wang L, Peng Z (2020) Deep reinforcement learning-based approach to tackle topic-aware influence maximization. Data Sci Eng 5(1):1\u201311","journal-title":"Data Sci Eng"},{"key":"1133_CR32","unstructured":"Vaswani A, Shazeer N, Parmar N, Uszkoreit J, Jones L, Gomez AN, Kaiser L, Polosukhin I (2023) Attention is all you need"},{"key":"1133_CR33","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Li\u00f2 P, Bengio Y (2018) Graph Attention Networks"},{"key":"1133_CR34","doi-asserted-by":"crossref","unstructured":"Xia W, Li Y, Wu J, Li S (2021) Deepis: Susceptibility estimation on social networks. In: WSDM \u201921, The Fourteenth ACM International Conference on Web Search and Data Mining, Virtual Event, Israel, March 8-12, 2021, pp. 761\u2013769","DOI":"10.1145\/3437963.3441829"},{"key":"1133_CR35","unstructured":"Zhang J, Liu B, Tang J, Chen T, Li J (2013) Social influence locality for modeling retweeting behaviors. In: Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence. IJCAI \u201913, pp. 2761\u20132767. AAAI Press"}],"container-title":["Data Mining and Knowledge Discovery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-025-01133-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10618-025-01133-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10618-025-01133-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T01:01:50Z","timestamp":1764982910000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10618-025-01133-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,19]]},"references-count":35,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["1133"],"URL":"https:\/\/doi.org\/10.1007\/s10618-025-01133-3","relation":{},"ISSN":["1384-5810","1573-756X"],"issn-type":[{"value":"1384-5810","type":"print"},{"value":"1573-756X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,19]]},"assertion":[{"value":"21 April 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"71"}}