Revealing Graph Bandits for Maximizing Local Influence

Alexandra Carpentier, Michal Valko
Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, PMLR 51:10-18, 2016.

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.

Cite this Paper

BibTeX
@InProceedings{pmlr-v51-carpentier16a, title = {Revealing Graph Bandits for Maximizing Local Influence}, author = {Carpentier, Alexandra and Valko, Michal}, booktitle = {Proceedings of the 19th International Conference on Artificial Intelligence and Statistics}, pages = {10--18}, year = {2016}, editor = {Gretton, Arthur and Robert, Christian C.}, volume = {51}, series = {Proceedings of Machine Learning Research}, address = {Cadiz, Spain}, month = {09--11 May}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v51/carpentier16a.pdf}, url = {https://proceedings.mlr.press/v51/carpentier16a.html}, 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.} }
Endnote
%0 Conference Paper %T Revealing Graph Bandits for Maximizing Local Influence %A Alexandra Carpentier %A Michal Valko %B Proceedings of the 19th International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2016 %E Arthur Gretton %E Christian C. Robert %F pmlr-v51-carpentier16a %I PMLR %P 10--18 %U https://proceedings.mlr.press/v51/carpentier16a.html %V 51 %X 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.
RIS
TY - CPAPER TI - Revealing Graph Bandits for Maximizing Local Influence AU - Alexandra Carpentier AU - Michal Valko BT - Proceedings of the 19th International Conference on Artificial Intelligence and Statistics DA - 2016/05/02 ED - Arthur Gretton ED - Christian C. Robert ID - pmlr-v51-carpentier16a PB - PMLR DP - Proceedings of Machine Learning Research VL - 51 SP - 10 EP - 18 L1 - http://proceedings.mlr.press/v51/carpentier16a.pdf UR - https://proceedings.mlr.press/v51/carpentier16a.html AB - 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. ER -
APA
Carpentier, A. & Valko, M.. (2016). Revealing Graph Bandits for Maximizing Local Influence. Proceedings of the 19th International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 51:10-18 Available from https://proceedings.mlr.press/v51/carpentier16a.html.

Related Material