Online Influence Maximization under the Independent Cascade Model with Node-Level Feedback

TL;DR

This paper develops an online influence maximization algorithm under the independent cascade model using realistic node-level feedback, achieving near-optimal regret bounds in social networks.

Contribution

It introduces the first $ ilde{O}( ootO{ ext{T}})$-regret algorithm for influence maximization under the IC model with node-level feedback.

Findings

Achieves near-optimal regret bounds for IC model with node feedback

Extends previous results from LT to IC diffusion models

Provides a practical approach for influence maximization with realistic feedback

Abstract

We study the online influence maximization (OIM) problem in social networks, where the learner repeatedly chooses seed nodes to generate cascades, observes the cascade feedback, and gradually learns the best seeds that generate the largest cascade in multiple rounds. In the demand of the real world, we work with node-level feedback instead of the common edge-level feedback in the literature. The edge-level feedback reveals all edges that pass through information in a cascade, whereas the node-level feedback only reveals the activated nodes with timestamps. The node-level feedback is arguably more realistic since in practice it is relatively easy to observe who is influenced but very difficult to observe from which relationship (edge) the influence comes. Previously, there is a nearly optimal $\tilde{O}(\sqrt{T})$-regret algorithm for OIM problem under the linear threshold (LT) diffusion model with node-level feedback. It remains unknown whether the same algorithm exists for the independent cascade (IC) diffusion model. In this paper, we resolve this open problem by presenting an $\tilde{O}(\sqrt{T})$-regret algorithm for OIM problem under the IC model with node-level feedback.