Online influence maximization under independent cascade model with semi-bandit feedback - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Year : 2017

Online influence maximization under independent cascade model with semi-bandit feedback

Zheng Wen
  • Function : Author
  • PersonId : 1023418
Branislav Kveton
  • Function : Author
Michal Valko
Sharan Vaswani
  • Function : Author
  • PersonId : 1023419

Abstract

We study the online influence maximization problem in social networks under the independent cascade model. Specifically, we aim to learn the set of " best influencers " in a social network online while repeatedly interacting with it. We address the challenges of (i) combinatorial action space, since the number of feasible influencer sets grows exponentially with the maximum number of influencers, and (ii) limited feedback, since only the influenced portion of the network is observed. Under a stochastic semi-bandit feedback, we propose and analyze IMLinUCB, a computationally efficient UCB-based algorithm. Our bounds on the cumulative regret are polynomial in all quantities of interest, achieve near-optimal dependence on the number of interactions and reflect the topology of the network and the activation probabilities of its edges, thereby giving insights on the problem complexity. To the best of our knowledge, these are the first such results. Our experiments show that in several representative graph topologies, the regret of IMLinUCB scales as suggested by our upper bounds. IMLinUCB permits linear generalization and thus is both statistically and computationally suitable for large-scale problems. Our experiments also show that IMLinUCB with linear generalization can lead to low regret in real-world online influence maximization.
Fichier principal
Vignette du fichier
wen2017online.pdf (591.12 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01643976 , version 1 (21-11-2017)

Identifiers

  • HAL Id : hal-01643976 , version 1

Cite

Zheng Wen, Branislav Kveton, Michal Valko, Sharan Vaswani. Online influence maximization under independent cascade model with semi-bandit feedback. Neural Information Processing Systems, Dec 2017, Long Beach, United States. pp.1-24. ⟨hal-01643976⟩
287 View
55 Download

Share

Gmail Facebook X LinkedIn More