Influence Prediction for Continuous-Time Information Propagation on Networks

TL;DR

This paper introduces a differential equation-based framework for predicting influence spread over time in large-scale networks, offering scalable and accurate solutions for complex propagation dynamics.

Contribution

It develops a novel differential equation model for influence prediction that is scalable to large, dense networks, improving computational efficiency and accuracy.

Findings

High prediction accuracy demonstrated

Effective for large-scale, dense networks

Scalable algorithms outperform existing methods

Abstract

We consider the problem of predicting the time evolution of influence, the expected number of activated nodes, given a set of initially active nodes on a propagation network. To address the significant computational challenges of this problem on large-scale heterogeneous networks, we establish a system of differential equations governing the dynamics of probability mass functions on the state graph where the nodes each lumps a number of activation states of the network, which can be considered as an analogue to the Fokker-Planck equation in continuous space. We provides several methods to estimate the system parameters which depend on the identities of the initially active nodes, network topology, and activation rates etc. The influence is then estimated by the solution of such a system of differential equations. This approach gives rise to a class of novel and scalable algorithms that work effectively for large-scale and dense networks. Numerical results are provided to show the very promising performance in terms of prediction accuracy and computational efficiency of this approach.