Revealing graph bandits for maximizing ...
Document type :
Communication dans un congrès avec actes
Title :
Revealing graph bandits for maximizing local influence
Author(s) :
Carpentier, Alexandra [Auteur]
Institut für Mathematik [Potsdam]
Valko, Michal [Auteur]
Sequential Learning [SEQUEL]
Institut für Mathematik [Potsdam]
Valko, Michal [Auteur]

Sequential Learning [SEQUEL]
Conference title :
International Conference on Artificial Intelligence and Statistics
City :
Seville
Country :
Espagne
Start date of the conference :
2016-05-09
HAL domain(s) :
Statistiques [stat]/Machine Learning [stat.ML]
English abstract : [en]
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 ...
Show more >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.Show less >
Show more >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.Show less >
Language :
Anglais
Peer reviewed article :
Oui
Audience :
Internationale
Popular science :
Non
ANR Project :
Collections :
Source :
Files
- https://hal.inria.fr/hal-01304020v3/document
- Open access
- Access the document
- https://hal.inria.fr/hal-01304020v3/document
- Open access
- Access the document
- https://hal.inria.fr/hal-01304020v3/document
- Open access
- Access the document
- document
- Open access
- Access the document
- carpentier2016revealing.pdf
- Open access
- Access the document