Factorization Bandits for Online Influence Maximization
This work addresses the challenge of efficiently identifying optimal influencers in social networks for applications like marketing, though it is incremental by building on existing methods with a novel factorization approach.
The paper tackles the problem of online influence maximization in social networks by leveraging network assortativity to factorize activation probabilities into latent node factors, achieving significant regret reduction as demonstrated in empirical evaluations on real-world networks.
We study the problem of online influence maximization in social networks. In this problem, a learner aims to identify the set of "best influencers" in a network by interacting with it, i.e., repeatedly selecting seed nodes and observing activation feedback in the network. We capitalize on an important property of the influence maximization problem named network assortativity, which is ignored by most existing works in online influence maximization. To realize network assortativity, we factorize the activation probability on the edges into latent factors on the corresponding nodes, including influence factor on the giving nodes and susceptibility factor on the receiving nodes. We propose an upper confidence bound based online learning solution to estimate the latent factors, and therefore the activation probabilities. Considerable regret reduction is achieved by our factorization based online influence maximization algorithm. And extensive empirical evaluations on two real-world networks showed the effectiveness of our proposed solution.