Deterministic influence maximization approach for sequential active marketing

Abstract

The influence maximization problem aims to find the best seeding set of nodes in a network to increase the influence spread, under various information diffusion models. Recent advances have shown the importance of the timing of the seeding and introduced the sequential seeding approach, determining a step-by-step cascade of activations. Our study explores a novel Deterministic Influence Maximization Approach (DIMA) for time-based sequential seeding dynamics in a threshold-based model. We examine the problem characteristics and formulate solutions optimizing a scheduled sequential seeding strategy. Based on a set of empirical simulations we demonstrate the properties of the deterministic sequential problem, incorporate three different mathematical programming formulations and provide an initial benchmark for optimization techniques.