Maximum entropy approach to link prediction in bipartite networks

Abstract

Within network analysis, the analytical maximum entropy framework has been very successful for different tasks as network reconstruction and filtering. In a recent paper, the same framework was used for link-prediction for monopartite networks: link probabilities for all unobserved links in a graph are provided and the most probable links are selected. Here we propose the extension of such an approach to bipartite graphs. We test our method on two real world networks with different topological characteristics. Our performances are compared to state-of-the-art methods, and the results show that our entropy-based approach has a good overall performance.

arXiv comment7 pages, 3 figures. This work is the output of the Complexity72h workshop (https://complexity72h.weebly.com/), held at IMT School for Advanced Studies in Lucca, 7-11 May 2018

References in corpus (10)

• The Building Blocks of Economic Complexity
• Topology of the World Trade Web
• The statistical mechanics of networks
• Fitness-dependent topological properties of the World Trade Web
• Emergence of structural and dynamical properties of ecological mutualistic networks
• A fitness model for the Italian Interbank Money Market
• Statistical Mechanics of Ecological Systems: Neutral Theory and Beyond
• Inferring monopartite projections of bipartite networks: an entropy-based approach
• The World-Trade Web: Topological Properties, Dynamics, and Evolution
• Entropy-based randomisation of rating networks