Predicting Diffusion Reach Probabilities via Representation Learning on Social Networks

TL;DR

This paper introduces a method using node representation learning and machine learning to estimate diffusion reach probabilities in social networks from limited cascade data, outperforming traditional calculations especially with scarce data.

Contribution

It proposes a novel approach combining node embeddings and machine learning to predict diffusion reach probabilities with limited cascade information.

Findings

Method outperforms traditional calculations with small cascade data

Experimental results on synthetic cascades and real networks validate effectiveness

Node embeddings improve prediction accuracy in diffusion modeling

Abstract

Diffusion reach probability between two nodes on a network is defined as the probability of a cascade originating from one node reaching to another node. An infinite number of cascades would enable calculation of true diffusion reach probabilities between any two nodes. However, there exists only a finite number of cascades and one usually has access only to a small portion of all available cascades. In this work, we addressed the problem of estimating diffusion reach probabilities given only a limited number of cascades and partial information about underlying network structure. Our proposed strategy employs node representation learning to generate and feed node embeddings into machine learning algorithms to create models that predict diffusion reach probabilities. We provide experimental analysis using synthetically generated cascades on two real-world social networks. Results show that proposed method is superior to using values calculated from available cascades when the portion of cascades is small.