Use of Rapid Probabilistic Argumentation for Ranking on Large Complex Networks

TL;DR

This paper introduces ERank, a fast probabilistic argumentation-based ranking algorithm for large networks, outperforming traditional methods like PageRank in accuracy and efficiency.

Contribution

The paper presents ERank, a novel linear-time ranking algorithm based on Probabilistic Argumentation Systems, applicable to large complex networks, with a new statistical performance comparison method.

Findings

ERank outperforms PageRank, closeness, and betweenness in experiments.

ERank operates in linear/near linear time, suitable for large networks.

A new statistical test effectively compares ranking algorithms.

Abstract

We introduce a family of novel ranking algorithms called ERank which run in linear/near linear time and build on explicitly modeling a network as uncertain evidence. The model uses Probabilistic Argumentation Systems (PAS) which are a combination of probability theory and propositional logic, and also a special case of Dempster-Shafer Theory of Evidence. ERank rapidly generates approximate results for the NP-complete problem involved enabling the use of the technique in large networks. We use a previously introduced PAS model for citation networks generalizing it for all networks. We propose a statistical test to be used for comparing the performances of different ranking algorithms based on a clustering validity test. Our experimentation using this test on a real-world network shows ERank to have the best performance in comparison to well-known algorithms including PageRank, closeness, and betweenness.