Effective link prediction in multiplex networks: A TOPSIS method

Bai, Shenshen; Zhang, Yakun; Li, Longjie; Shan, Na; Chen, Xiaoyun

doi:10.1016/j.eswa.2021.114973

Cited by 37 publications

(9 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) This paper mainly studies the small-scale group decision-making problem in the 2TLNNs environment. Extending the GDM method of large groups and social networks to the 2TLNNs environment is a problem worthy of further research [53,54]. (3) The operator proposed in this paper is improved to consider the expression of decision evaluation information based on language preference relationship, such as group decision method based on probabilistic linguistic decision information [55,56] and probabilistic uncertain linguistic decision information [57,58], which is also a topic worthy of future research.…”

Section: Discussionmentioning

confidence: 99%

Grey relational analysis method for typhoon vulnerability assessment of civil engineering structures based on the 2-tuple linguistic neutrosophic number

Chen

Wang³

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

As one of the severe natural disasters, typhoon hazard brings tremendous tragedy to human beings. The foreland in the southeast of China is one of the most typhoon prone areas in the world. There are amount of damage of civil engineering structures induced by typhoon every year. Especially for the spacious villages, the low-rise buildings are vulnerable to typhoon so that many of them are destroyed regionally. The typhoon vulnerability assessment of civil engineering structures is a classical multiple attribute group decision making (MAGDM) issues. In this paper, the 2-tuple linguistic neutrosophic number grey relational analysis (2TLNN-GRA) method is built based on the grey relational analysis (GRA) and 2-tuple linguistic neutrosophic sets (2TLNSs) with incomplete weight information. For deriving the weight information of the attribute, an optimization model is built on the basis of the GRA, by which the attribute weights can be decided. Then, the optimal alternative is chosen through calculating largest relative relational degree from the 2-tuple linguistic neutrosophic number positive ideal solution (2TLNNPIS) which considers both the largest grey relational coefficient (GRC) from the 2TLNNPIS and the smallest GRC form 2-tuple linguistic neutrosophic number negative ideal solution (2TLNN NIS). Then, combine the traditional fuzzy GRA model with 2TLNNSs information, the 2TLNN-GRA method is established and the computing steps for MAGDM are built. Finally, a numerical example for typhoon vulnerability assessment of civil engineering structures has been given and some comparisons is used to illustrate advantages of 2TLNN-GRA method.

show abstract

Section: Discussionmentioning

confidence: 99%

Grey relational analysis method for typhoon vulnerability assessment of civil engineering structures based on the 2-tuple linguistic neutrosophic number

Chen

Wang³

et al. 2022

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…Node and layer level diversity/similarity is discussed in [5,22]. Recent literature shows the application of similarity measure for link prediction in multiplex network [23][24][25][26], where the objective is to predict the unknown/missing links of the target layer from the information of other layers. Hence, effective approach of similarity measure is essential.…”

Section: Related Workmentioning

confidence: 99%

“…The computation of layer similarity can be applicable in the task of link prediction. In link prediction [23][24][25][26], from different layers of multiplex network, one layer is chosen as target layer. The links of the target layer are categorized into train links and test links.…”

Section: Application Of the Layer Similaritymentioning

confidence: 99%

Core-based Approach to Measure Pairwise Layer Similarity in Multiplex Network

Mohapatra¹,

Bhoi²,

Jena³

et al. 2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Most of the recent works on network science are focused on investigating various interactions among a set of entities present in a system that can be represented by multiplex network. Each type of relationship is treated as a layer of multiplex network. Some of the recent works on multiplex networks are focused on deriving layer similarity from node similarity where node similarity is evaluated using neighborhood similarity measures like cosine similarity and Jaccard similarity. But this type of analysis lacks in finding the set of nodes having the same influence in both the network. The discovery of influence similarity between the layers of multiplex networks helps in strategizing cascade effect, influence maximization, network controllability, etc. Towards this end, this paper proposes a pairwise similarity evaluation of layers based on a set of common core nodes of the layers. It considers the number of nodes present in the common core set, the average clustering coefficient of the common core set, and fractional influence capacity of the common core set to quantify layer similarity. The experiment is carried out on three real multiplex networks. As the proposed notion of similarity uses a different aspect of layer similarity than the existing one, a low positive correlation (close to non-correlation) is found between the proposed and existing approach of layer similarity. The result demonstrates that the degree of coreness difference is less for the datasets in the proposed method than the existing one. The existing method reports the coreness difference to be 40% and 18.4% for the datasets CS-AARHUS and EU-AIR TRANSPORTATION MULTIPLEX respectively whereas it is found to be 20% and 8.1% using proposed approach.

show abstract

“…Li et al [14] combined the four similarity indexes, including Common Neighbors, Leicht-Holme-Newman, Cosine based on the Laplacian matrix, and Matrix Forest based on the Logistic regression algorithm and the Xgboost algorithm, and introduced the idea of stacking into the link prediction of complex networks. Bai et al [15] constructed a new model that regarded link prediction in multiplex networks as a multi-attribute decisionmaking problem, in which the potential links in the target layer are alternatives, the layers are viewed as attributes, and the similarity score of a potential link in each layer are an attribute value.…”

Section: Literature Reviewmentioning

confidence: 99%

A Link Prediction Method Based on Neural Networks

Yan

2021

Applied Sciences

View full text Add to dashboard Cite

Link prediction to optimize network performance is of great significance in network evolution. Because of the complexity of network systems and the uncertainty of network evolution, it faces many challenges. This paper proposes a new link prediction method based on neural networks trained on scale-free networks as input data, and optimized networks trained by link prediction models as output data. In order to solve the influence of the generalization of the neural network on the experiments, a greedy link pruning strategy is applied. We consider network efficiency and the proposed global network structure reliability as objectives to comprehensively evaluate link prediction performance and the advantages of the neural network method. The experimental results demonstrate that the neural network method generates the optimized networks with better network efficiency and global network structure reliability than the traditional link prediction models.

show abstract

Effective link prediction in multiplex networks: A TOPSIS method

Cited by 37 publications

References 86 publications

Grey relational analysis method for typhoon vulnerability assessment of civil engineering structures based on the 2-tuple linguistic neutrosophic number

Grey relational analysis method for typhoon vulnerability assessment of civil engineering structures based on the 2-tuple linguistic neutrosophic number

Core-based Approach to Measure Pairwise Layer Similarity in Multiplex Network

A Link Prediction Method Based on Neural Networks

Contact Info

Product

Resources

About