MONSTOR: An Inductive Approach for Estimating and Maximizing Influence over Unseen Networks

TL;DR

This paper introduces MONSTOR, an inductive machine learning approach that accurately estimates influence spread in unseen social networks, significantly speeding up influence maximization algorithms while maintaining high accuracy.

Contribution

MONSTOR is the first inductive method for influence estimation, enabling faster influence maximization in unseen networks with high accuracy.

Findings

Achieved Pearson and Spearman correlations of 0.998+ in unseen networks.

IM algorithms with MONSTOR outperform state-of-the-art in 63% of cases.

Significantly reduces computational time compared to Monte Carlo simulations.

Abstract

Influence maximization (IM) is one of the most important problems in social network analysis. Its objective is to find a given number of seed nodes that maximize the spread of information through a social network. Since it is an NP-hard problem, many approximate/heuristic methods have been developed, and a number of them repeat Monte Carlo (MC) simulations over and over to reliably estimate the influence (i.e., the number of infected nodes) of a seed set. In this work, we present an inductive machine learning method, called Monte Carlo Simulator (MONSTOR), for estimating the influence of given seed nodes in social networks unseen during training. To the best of our knowledge, MONSTOR is the first inductive method for this purpose. MONSTOR can greatly accelerate existing IM algorithms by replacing repeated MC simulations. In our experiments, MONSTOR provided highly accurate estimates, achieving 0.998 or higher Pearson and Spearman correlation coefficients in unseen real-world social networks. Moreover, IM algorithms equipped with MONSTOR are more accurate than state-of-the-art competitors in 63% of IM use cases.