On approximating networks centrality measures via neural learning algorithms

Grando, Felipe; Lamb, Luís C.

doi:10.1109/ijcnn.2016.7727248

Cited by 9 publications

(29 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The power method requires an infinite number of steps (worst case) but as the number of steps increases, the precision of the measure also increases [57]. Therefore, the number of decimal places can be used to turn this measure feasible even for massive networks where a hundred steps usually grants enough precision to differentiate the vertices centrality values [57] [67].…”

Section: Spectral Centralitiesmentioning

confidence: 99%

“…Then, each community is considered an Erdős and Rényi graph where the probability of connection among vertices is equal to the desired clustering coefficient [57]. The last step generates connections proportional to the excess degree of each vertex (number of connections that a vertex needs to match its desired degree) [57]. This weighted distribution is based on Chung and Lu graphs [76] [77].…”

Section: Block Two-level Erdős and Rényi Modelmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning in Network Centrality Measures

2018

Self Cite

View full text Add to dashboard Cite

Complex networks are ubiquitous to several Computer Science domains. Centrality measures are an important analysis mechanism to uncover vital elements of complex networks. However, these metrics have high computational costs and requirements that hinder their applications in large real-world networks. In this tutorial, we explain how the use of neural network learning algorithms can render the application of the metrics in complex networks of arbitrary size. Moreover, the tutorial describes how to identify the best configuration for neural network training and learning such for tasks, besides presenting an easy way to generate and acquire training data. We do so by means of a general methodology, using complex network models adaptable to any application. We show that a regression model generated by the neural network successfully approximates the metric values and therefore are a robust, effective alternative in real-world applications. The methodology and proposed machine learning model use only a fraction of time with respect to other approximation algorithms, which is crucial in complex network applications.

show abstract

Section: Spectral Centralitiesmentioning

confidence: 99%

Section: Block Two-level Erdős and Rényi Modelmentioning

confidence: 99%

Machine Learning in Network Centrality Measures

2018

Self Cite

View full text Add to dashboard Cite

show abstract

“…Such studies have aimed at understanding networks' common characteristics and at creating models capable of generating networks stochastically with similar properties. These models became a valuable research tool for many disciplines [1] [22].…”

Section: B On Complex Network Modelsmentioning

confidence: 99%

“…Several complex network models were developed and studied over the last years. However, some of them are unable to capture and represent some properties of real networks, while others are only conceptualizations and unfortunately are not designed for generating synthetic networks [4] [22]. The Block Two-Level Erdős and Rényi (BTER) model [23] generates networks with very similar properties of real networks.…”

Section: B On Complex Network Modelsmentioning

confidence: 99%

“…Despite their attempts to find an optimal heuristic for such problem, they concluded that picking vertices uniformly at random on average is the best strategy when considering different types of network structures. Some authors [22] [37] [38] tried other kind of approximation methodologies, based mainly on machine learning and neural networks. The strength of these methodologies is their adaptability (they can be used to approximate several distinct centrality measures) and they are able to compute the centrality measures a lot faster than any other method after the model is trained.…”

Section: On Approximating Centrality Measuresmentioning

confidence: 99%

See 1 more Smart Citation

Computing Vertex Centrality Measures in Massive Real Networks with a Neural Learning Model

Grando

Lamb

2018

2018 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

Vertex centrality measures are a multi-purpose analysis tool, commonly used in many application environments to retrieve information and unveil knowledge from the graphs and network structural properties. However, the algorithms of such metrics are expensive in terms of computational resources when running real-time applications or massive real world networks. Thus, approximation techniques have been developed and used to compute the measures in such scenarios. In this paper, we demonstrate and analyze the use of neural network learning algorithms to tackle such task and compare their performance in terms of solution quality and computation time with other techniques from the literature. Our work offers several contributions. We highlight both the pros and cons of approximating centralities though neural learning. By empirical means and statistics, we then show that the regression model generated with a feedforward neural networks trained by the Levenberg-Marquardt algorithm is not only the best option considering computational resources, but also achieves the best solution quality for relevant applications and large-scale networks.

show abstract

Multitask Learning on Graph Neural Networks: Learning Multiple Graph Centrality Measures with a Unified Network

Avelar

Lemos

Prates

et al. 2019

Artificial Neural Networks and Machine Learning – ICANN 2019: Workshop and Special Sessions

View full text Add to dashboard Cite

The application of deep learning to symbolic domains remains an active research endeavour. Graph neural networks (GNN), consisting of trained neural modules which can be arranged in different topologies at run time, are sound alternatives to tackle relational problems which lend themselves to graph representations. In this paper, we show that GNNs are capable of multitask learning, which can be naturally enforced by training the model to refine a single set of multidimensional embeddings ∈ R d and decode them into multiple outputs by connecting MLPs at the end of the pipeline. We demonstrate the multitask learning capability of the model in the relevant relational problem of estimating network centrality measures, i.e. is vertex v1 more central than vertex v2 given centrality c?. We then show that a GNN can be trained to develop a lingua franca of vertex embeddings from which all relevant information about any of the trained centrality measures can be decoded. The proposed model achieves 89% accuracy on a test dataset of random instances with up to 128 vertices and is shown to generalise to larger problem sizes. The model is also shown to obtain reasonable accuracy on a dataset of real world instances with up to 4k vertices, vastly surpassing the sizes of the largest instances with which the model was trained (n = 128). Finally, we believe that our contributions attest to the potential of GNNs in symbolic domains in general and in relational learning in particular.

show abstract

On approximating networks centrality measures via neural learning algorithms

Cited by 9 publications

References 42 publications

Machine Learning in Network Centrality Measures

Machine Learning in Network Centrality Measures

Computing Vertex Centrality Measures in Massive Real Networks with a Neural Learning Model

Multitask Learning on Graph Neural Networks: Learning Multiple Graph Centrality Measures with a Unified Network

Contact Info

Product

Resources

About