{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/online-influence-maximization-under","title":"Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback","arxiv_id":"1605.06593","date":"2016-05-21","proceeding":"NeurIPS 2017 12","authors":["Zheng Wen","Branislav Kveton","Michal Valko","Sharan Vaswani"],"abstract":"We study the online influence maximization problem in social networks under\nthe independent cascade model. Specifically, we aim to learn the set of \"best\ninfluencers\" in a social network online while repeatedly interacting with it.\nWe address the challenges of (i) combinatorial action space, since the number\nof feasible influencer sets grows exponentially with the maximum number of\ninfluencers, and (ii) limited feedback, since only the influenced portion of\nthe network is observed. Under a stochastic semi-bandit feedback, we propose\nand analyze IMLinUCB, a computationally efficient UCB-based algorithm. Our\nbounds on the cumulative regret are polynomial in all quantities of interest,\nachieve near-optimal dependence on the number of interactions and reflect the\ntopology of the network and the activation probabilities of its edges, thereby\ngiving insights on the problem complexity. To the best of our knowledge, these\nare the first such results. Our experiments show that in several representative\ngraph topologies, the regret of IMLinUCB scales as suggested by our upper\nbounds. IMLinUCB permits linear generalization and thus is both statistically\nand computationally suitable for large-scale problems. Our experiments also\nshow that IMLinUCB with linear generalization can lead to low regret in\nreal-world online influence maximization.","url_abs":"http://arxiv.org/abs/1605.06593v3","url_pdf":"http://arxiv.org/pdf/1605.06593v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"online-influence-maximization-under","repo_url":"https://github.com/olety/TIMLinUCB","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}