FastCover: An Unsupervised Learning Framework for Multi-Hop Influence Maximization in Social Networks
This addresses the problem of efficiently identifying influential users in social networks for applications like marketing, with incremental improvements in speed and scalability.
The paper tackles the influence maximization problem in social networks by reducing it to a budget-constrained d-hop dominating set problem and proposes FastCover, an unsupervised learning framework that uses a novel GNN architecture to compute node scores in one forward pass, achieving solutions with comparable or better quality and a speedup of over 1000x compared to concurrent algorithms.
Finding influential users in social networks is a fundamental problem with many possible useful applications. Viewing the social network as a graph, the influence of a set of users can be measured by the number of neighbors located within a given number of hops in the network, where each hop marks a step of influence diffusion. In this paper, we reduce the problem of IM to a budget-constrained d-hop dominating set problem (kdDSP). We propose a unified machine learning (ML) framework, FastCover, to solve kdDSP by learning an efficient greedy strategy in an unsupervised way. As one critical component of the framework, we devise a novel graph neural network (GNN) architecture, graph reversed attention network (GRAT), that captures the diffusion process among neighbors. Unlike most heuristic algorithms and concurrent ML frameworks for combinatorial optimization problems, FastCover determines the entire seed set from the nodes' scores computed with only one forward propagation of the GNN and has a time complexity quasi-linear in the graph size. Experiments on synthetic graphs and real-world social networks demonstrate that FastCover finds solutions with better or comparable quality rendered by the concurrent algorithms while achieving a speedup of over 1000x.