pith. sign in

arxiv: 1605.06593 · v3 · pith:EMDMEV3Ynew · submitted 2016-05-21 · 💻 cs.LG · cs.AI· cs.SI· math.OC· stat.ML

Online Influence Maximization under Independent Cascade Model with Semi-Bandit Feedback

classification 💻 cs.LG cs.AIcs.SImath.OCstat.ML
keywords imlinucbonlinefeedbackinfluencemaximizationnetworknumberregret
0
0 comments X
read the original 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.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Bandits on graphs and structures

    cs.LG 2026-05 unverdicted novelty 2.0

    The thesis compiles work on graph bandits (spectral smoothness, side observations, influence maximization) and structured bandits (kernel, polymatroid, function optimization with unknown smoothness, infinite arms) to ...