Random Graph Generator for Bipartite Networks Modeling

TL;DR

This paper introduces a new iterative algorithm for generating realistic bipartite graphs with controllable features, aiding the development and testing of algorithms in areas like recommender systems.

Contribution

The paper presents a novel bipartite graph generator that models real-world network properties, adapting recent complex network modeling advances to bipartite structures.

Findings

Generator produces bipartite graphs with realistic degree distributions.

Generator allows control over local clustering coefficients.

Potential to improve testing of recommender system algorithms.

Abstract

The purpose of this article is to introduce a new iterative algorithm with properties resembling real life bipartite graphs. The algorithm enables us to generate wide range of random bigraphs, which features are determined by a set of parameters.We adapt the advances of last decade in unipartite complex networks modeling to the bigraph setting. This data structure can be observed in several situations. However, only a few datasets are freely available to test the algorithms (e.g. community detection, influential nodes identification, information retrieval) which operate on such data. Therefore, artificial datasets are needed to enhance development and testing of the algorithms. We are particularly interested in applying the generator to the analysis of recommender systems. Therefore, we focus on two characteristics that, besides simple statistics, are in our opinion responsible for the performance of neighborhood based collaborative filtering algorithms. The features are node degree distribution and local clustering coeficient.