Revealing graph bandits for maximizing local influence - Archive ouverte HAL Access content directly
Conference Papers Year :

Revealing graph bandits for maximizing local influence

(1) , (2)
Michal Valko


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.
Fichier principal
Vignette du fichier
carpentier2016revealing.pdf (1.65 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-01304020 , version 1 (18-04-2016)
hal-01304020 , version 2 (23-04-2016)
hal-01304020 , version 3 (29-04-2016)


  • 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⟩
168 View
136 Download


Gmail Facebook Twitter LinkedIn More