Deep Learning based Network Similarity for Model Selection

Tracking #: 670-1650

Responsible editor: 

Michael Maes

Submission Type: 

Research Paper


Capturing data in the form of network’s is becoming an increasingly popular approach for modeling, analyzing and visualizing complex phenomena, to understand the important properties of the underlying complex processes. Access to many large-scale network datasets is restricted due to the privacy and security concerns. Also for several applications (such as functional connectivity networks), generating large scale real data is expensive. For these reasons, there is a growing need for advanced mathematical and statistical models (also called generative models) that can account for the structure of these large scale networks, without having to materialize them in the real world. The objective is to provide a comprehensible description of the network properties and to be able to infer previously unobserved properties. Various models have been developed by researchers, which generate synthetic networks that adhere to the structural properties of real networks. However, the selection of the appropriate generative model for a given real-world network remains an important challenge. In this paper, we investigate this problem and provide a novel technique (named as TripletFit) for model selection (or network classification) and estimation of structural similarities of the complex networks. The goal of network model selection is to select a generative model that is able to generate a structurally similar synthetic network for a given real-world (target) network. We consider six outstanding generative models as the candidate models. The existing model selection methods mostly suffer from sensitivity to network perturbations, dependency on the size of the networks, and low accuracy. To overcome these limitations, we considered a broad array of network features, with the aim of representing different structural aspects of the network and employed deep learning techniques such as deep triplet network architecture and simple feed-forward network for model selection and estimation of structural similarities of the complex networks. Our proposed method, outperforms existing methods with respect to accuracy, noise-tolerance, and size independence on a number of gold standard data set used in previous studies.


Previous Version: 


  • Reviewed

Special issue (if applicable): 

Data repository URLs: 

Date of Submission: 

Monday, December 14, 2020

Date of Decision: 

Tuesday, March 23, 2021

Nanopublication URLs:



Solicited Reviews:

1 Comment

Meta-Review by Editor

We ask you to carefully address all points raised by the reviewers, focusing on the size of the studied networks and on improving Figure 4 and Table 1. I also echo Reviewer 1´s recommendation to extend the discussion section and to carefully proofread your paper.

Michael Maes (