Analytical maximum-likelihood method to detect patterns in real networks

@article{Squartini2011AnalyticalMM,
  title={Analytical maximum-likelihood method to detect patterns in real networks},
  author={T. Squartini and D. Garlaschelli},
  journal={arXiv: Data Analysis, Statistics and Probability},
  year={2011}
}
In order to detect patterns in real networks, randomized graph ensembles that preserve only part of the topology of an observed network are systematically used as fundamental null models. However, their generation is still problematic. The existing approaches are either computationally demanding and beyond analytic control, or analytically accessible but highly approximate. Here we propose a solution to this long-standing problem by introducing an exact and fast method that allows to obtain… Expand
Unbiased sampling of network ensembles
TLDR
A 'Maximize and Sample' ('Max & Sam' for short) method to correctly sample ensembles of networks where the constraints are 'soft', i.e. realized as ensemble averages, which is based on exact maximum-entropy distributions and is therefore unbiased by construction, even for strongly heterogeneous networks. Expand
On metrics and models for multiplex networks
TLDR
It turns out that this methodology, applicable to a specific class of multi-layer networks, can be successfully employed to reconstruct the World Trade Multiplex and is illustrated that the maximum-entropy models also allow us to find the so-called backbone of a real network, i.e. the information which is irreducible to the single-node properties and is therefore peculiar to the network itself. Expand
Irreducible network backbones: unbiased graph filtering via maximum entropy
TLDR
This work introduces a rigorous method that outputs the network backbone that is irreducible to the local properties of nodes, i.e. their degrees and strengths and employs an exact maximum-entropy formulation guaranteeing that the filtered network encodes only the links that cannot be inferred from local information. Expand
Reconstructing Topological Properties of Complex Networks Using the Fitness Model
TLDR
This paper investigates a novel method to reconstruct global topological properties of a complex network starting from limited information, using the knowledge of an intrinsic property of the nodes, and the number of connections of only a limited subset of nodes, to generate an ensemble of exponential random graphs that are representative of the real systems. Expand
Meta-validation of bipartite network projections
TLDR
A meta-validation approach is developed, which allows to identify model-specific statistical thresholds for which the signal is strongest, and at the same time to obtain results independent of the way in which the null hypothesis is formulated. Expand
Random walk patterns to identify weighted motifs
TLDR
This work proposed a novel methodology based on a random walker and a fixed maximum number of steps to study weighted motifs of limited size and found that identified similarities enable the classifications of systems according to functioning mechanisms associated with specific configurations. Expand
Fast analytical methods for finding significant labeled graph motifs
TLDR
This work proposes an analytical method (i.e. simulation-free) that extends the works of Picard et al. to identify statistically significant motifs in a given network and provides an analytical expression of the mean and variance of the count under the Expected Degree Distribution random graph model. Expand
Inferring monopartite projections of bipartite networks: an entropy-based approach
TLDR
This paper proposes an algorithm to obtain statistically-validated projections of bipartite networks, according to which any two nodes sharing a statistically-significant number of neighbors are linked, defined within the exponential random graph framework. Expand
Establish the expected number of induced motifs on unlabeled graphs through analytical models
TLDR
An analytical model is illustrated to derive the mean number of occurrences of an induced motif in an unlabeled network with respect to a random graph model and shows the effectiveness of this approach for the computation of the expected number of induced motifs up to 10 nodes. Expand
Geometric randomization of real networks with prescribed degree sequence
We introduce a model for the randomization of complex networks with geometric structure. The geometric randomization (GR) model assumes a homogeneous distribution of the nodes in an underlyingExpand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 116 REFERENCES
Maximum likelihood: extracting unbiased information from complex networks.
TLDR
This work shows that the maximum likelihood (ML) principle indicates a unique, statistically rigorous parameter choice, associated with a well-defined topological feature, and builds a class of safely unbiased models to overcome this problem. Expand
Detection of topological patterns in complex networks: correlation profile of the internet
A general scheme for detecting and analyzing topological patterns in large complex networks is presented. In this scheme the network in question is compared with its properly randomized version thatExpand
The architecture of complex weighted networks.
TLDR
This work studies the scientific collaboration network and the world-wide air-transportation network, which are representative examples of social and large infrastructure systems, respectively, and defines appropriate metrics combining weighted and topological observables that enable it to characterize the complex statistical properties and heterogeneity of the actual strength of edges and vertices. Expand
Classes of complex networks defined by role-to-role connectivity profiles.
TLDR
It is reported that networks with different functions, including the Internet, metabolic, air transportation and protein interaction networks, have distinct patterns of connections among nodes with different roles, and that, as a consequence, complex networks can be classified into two distinct functional classes on the basis of their link type frequency. Expand
Entropy of network ensembles.
  • G. Bianconi
  • Mathematics, Physics
  • Physical review. E, Statistical, nonlinear, and soft matter physics
  • 2009
TLDR
The structural entropy is defined and evaluated, i.e., the entropy of the ensembles of undirected uncorrelated simple networks with given degree sequence, and a solution to the paradox is proposed by proving that scale-free degree distributions are the most likely degree distribution with the corresponding value of the structural entropy. Expand
Detecting rich-club ordering in complex networks
Uncovering the hidden regularities and organizational principles of networks arising in physical systems ranging from the molecular level to the scale of large communication infrastructures is theExpand
Statistical mechanics of networks.
  • Juyong Park, M. Newman
  • Mathematics, Physics
  • Physical review. E, Statistical, nonlinear, and soft matter physics
  • 2004
We study the family of network models derived by requiring the expected properties of a graph ensemble to match a given set of measurements of a real-world network, while maximizing the entropy ofExpand
Random graphs with arbitrary degree distributions and their applications.
TLDR
It is demonstrated that in some cases random graphs with appropriate distributions of vertex degree predict with surprising accuracy the behavior of the real world, while in others there is a measurable discrepancy between theory and reality, perhaps indicating the presence of additional social structure in the network that is not captured by the random graph. Expand
The weighted random graph model
We introduce the weighted random graph (WRG) model, which represents the weighted counterpart of the Erdos–Renyi random graph and provides fundamental insights into more complicated weightedExpand
Analysis of weighted networks.
  • M. Newman
  • Mathematics, Physics
  • Physical review. E, Statistical, nonlinear, and soft matter physics
  • 2004
TLDR
It is pointed out that weighted networks can in many cases be analyzed using a simple mapping from a weighted network to an unweighted multigraph, allowing us to apply standard techniques for unweighting graphs to weighted ones as well. Expand
...
1
2
3
4
5
...