Abstract
Complex networks can model a wide range of complex systems in nature and society, and many algorithms (network generators) capable of synthesizing networks with few and very specific structural characteristics (degree distribution, average path length, etc.) have been developed. However, there remains a significant lack of generators capable of synthesizing networks with strong resemblance to those observed in the real-world, which can subsequently be used as a null model, or to perform tasks such as extrapolation, compression and control. In this paper, a robust new approach we term Action-based Modeling is presented that creates a compact probabilistic model of a given target network, which can then be used to synthesize networks of arbitrary size. Statistical comparison to existing network generators is performed and results show that the performance of our approach is comparable to the current state-of-the-art methods on a variety of network measures, while also yielding easily interpretable generators. Additionally, the action-based approach described herein allows the user to consider an arbitrarily large set of structural characteristics during the generator design process.
Highlights
Lines closer to the origin imply a lower dissimilarity between target and synthesized networks and are more desirable. These results suggest that the synthesis algorithm action-based network generators (ABNG)-PA(1) is capable of modeling the actual network generator using only one target network observation
Action-based network generators provide a flexible framework for reproducing complex structure of networks exhibiting different global/structural statistics by formulating network generation as an optimization problem
The approach consists of three distinct parts: (i) network synthesis using algorithm f( · ), (ii) computation of dissimilarity using a user-defined set of measures Y, and (iii) an optimization technique to learn parameters M for a given target network
Summary
Our goal is to devise a robust algorithmic framework for learning a compressed model of a given target network, and to show that the resulting generator is capable of synthesizing, with high probability, statistically similar networks to the given network
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
