Skip to Main content Skip to Navigation
Conference papers

Revealing graph bandits for maximizing local influence

Alexandra Carpentier 1 Michal Valko 2
2 SEQUEL - Sequential Learning
Inria Lille - Nord Europe, CRIStAL - Centre de Recherche en Informatique, Signal et Automatique de Lille - UMR 9189
Abstract : We study a graph bandit setting where the objective of the learner is to detect the most influential node of a graph by requesting as little information from the graph as possible. One of the relevant applications for this setting is marketing in social networks, where the marketer aims at finding and taking advantage of the most influential customers. The existing approaches for bandit problems on graphs require either partial or complete knowledge of the graph. In this paper, we do not assume any knowledge of the graph, but we consider a setting where it can be gradually discovered in a sequential and active way. At each round, the learner chooses a node of the graph and the only information it receives is a stochastic set of the nodes that the chosen node is currently influencing. To address this setting, we propose BARE, a bandit strategy for which we prove a regret guarantee that scales with the detectable dimension, a problem dependent quantity that is often much smaller than the number of nodes.
Document type :
Conference papers
Complete list of metadata

Cited literature [32 references]  Display  Hide  Download
Contributor : Michal Valko Connect in order to contact the contributor
Submitted on : Friday, April 29, 2016 - 12:41:22 AM
Last modification on : Thursday, January 20, 2022 - 4:17:05 PM
Long-term archiving on: : Tuesday, November 15, 2016 - 5:53:25 PM


Files produced by the author(s)


  • HAL Id : hal-01304020, version 3



Alexandra Carpentier, Michal Valko. Revealing graph bandits for maximizing local influence. International Conference on Artificial Intelligence and Statistics, May 2016, Seville, Spain. ⟨hal-01304020v3⟩



Les métriques sont temporairement indisponibles