Entropy of Spatial Network Ensembles

Abstract

We analyze complexity in spatial network ensembles through the lens of graph entropy. Mathematically, we model a spatial network as a soft random geometric graph, i.e., a graph with two sources of randomness, namely nodes located randomly in space and links formed independently between pairs of nodes with probability given by a specified function (the "pair connection function") of their mutual distance. We consider the general case where randomness arises in node positions as well as pairwise connections (i.e., for a given pair distance, the corresponding edge state is a random variable). Classical random geometric graph and exponential graph models can be recovered in certain limits. We derive a simple bound for the entropy of a spatial network ensemble and calculate the conditional entropy of an ensemble given the node location distribution for hard and soft (probabilistic) pair connection functions. Under this formalism, we derive the connection function that yields maximum entropy under general constraints. Finally, we apply our analytical framework to study two practical examples: ad hoc wireless networks and the US flight network. Through the study of these examples, we illustrate that both exhibit properties that are indicative of nearly maximally entropic ensembles.

7 pages, 4 figures

References in corpus (2)

• Understanding the spreading patterns of mobile phone viruses
• Geographical dispersal of mobile communication networks

Cited by in corpus (7)

• Small worlds and clustering in spatial networks
• What is the Entropy of a Social Organization?
• Spatial networks with wireless applications
• Entropy of labeled versus unlabeled networks
• Large algebraic connectivity fluctuations in spatial network ensembles imply a predictive advantage from node location information
• Entropy of Random Geometric Graphs in High and Low Dimensions
• Graph model selection by edge probability sequential inference