A Quad Motifs Index for Directed Link Prediction

Hu, Xinxin; Liu, Shuxin; Chang, Sheng; Li, Haitao

doi:10.1109/access.2019.2950539

Cited by 5 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…They proposed that the bi-directional link contains more network information, and found that a pair of nodes with bi-directional links has greater probability to connect to the common neighbours with bi-directional links. Hu et al [10] considered the effectiveness of quad motifs in calculating the similarity between nodes in the directed network, and defined closed quad, relative open quad, no-crossing closed quad and quad motifs. Li et al [11] defined a community relationship strength index (CRS) to estimate the closeness between communities, and proposed a link prediction framework based on node similarity and community information.…”

Section: A Similarity Index-based Prediction Methodsmentioning

confidence: 99%

“…where S is the number of nodes in the hidden layer, m is the input length of the model, n is the output length of the model, and a is an integer within [1], [10]. Considering the size of the sample set and reducing the time complexity of model training, this paper selects equation (8) to determine the number of nodes in the hidden layer.…”

Section: ) the Number Of Nodes In The Hidden Layermentioning

confidence: 99%

“…According to the characteristics of layer-by-layer training of the DBN, this paper uses the reconstruction error Rerror between the original data and the data obtained by reconstructing the original data to determine the number of hidden layers [28]. The Rerror is defined as shown in (10).…”

Section: ) the Number Of Hidden Layersmentioning

confidence: 99%

“…In contrast, the model will under-fit, which results in a lower accuracy of the model. Based on the above 14 (10) different lengths of time slices and 11 different lengths of input data on the ITC (MIT) dataset, we obtain the number of hidden layers of the model under different parameters according to algorithm 1. Taking the model with t = 140s and N = 210 on the ITC dataset as an example, the reconstruction error of each layer of the RBM is shown in figure 10.…”

Section: A: the Number Of Hidden Layersmentioning

confidence: 99%

See 3 more Smart Citations

A Novel Link Prediction Method for Opportunistic Networks Based on Random Walk and a Deep Belief Network

2020

View full text Add to dashboard Cite

Link prediction is to estimate the possibility of future links among nodes by utilizing known information such as network topology and node attributes. According to the characteristics of opportunistic networks (topological time-variation, node mobility and intermittent connections), this paper proposes a novel link prediction approach (IRWR-DBN) for opportunistic networks that is based on random walk and a deep belief network. First, we reconstruct the Markov probability transition matrix and define a similarity index-improved random walk with restart (IRWR). Second, we divide the opportunistic network into network snapshots. Then, the similarity matrix of each snapshot is calculated by using the IRWR index to construct a sample set. Finally, a predictive model is constructed based on a deep belief network which extracts the time-domain characteristics in the process of dynamic evolution of the opportunistic network. The experimental results on the ITC and MIT Reality datasets show that compared with methods, such as the similarity-based index (CN, AA, Katz, RA, RWR), convolutional neural network, and recurrent neural network, the proposed method is more accurate and stable. INDEX TERMS Opportunistic network, link prediction, random walk with restart, deep belief network, similarity index.

show abstract

Section: A Similarity Index-based Prediction Methodsmentioning

confidence: 99%

Section: ) the Number Of Nodes In The Hidden Layermentioning

confidence: 99%

Section: ) the Number Of Hidden Layersmentioning

confidence: 99%

Section: A: the Number Of Hidden Layersmentioning

confidence: 99%

See 2 more Smart Citations

A Novel Link Prediction Method for Opportunistic Networks Based on Random Walk and a Deep Belief Network

2020

View full text Add to dashboard Cite

show abstract

“…By counting the numbers of 4 different directed 2-paths and 8 different directed 3-paths around a pair of nodes, the paper finds out that a link has a higher probability of appearing if it could generate more bi-fan subgraphs [213]. Very similar to the idea of potential theory, the quad motifs index proposes to count particularly three types of directed open-quadriad (3-paths) subgraphs: two of them are the bases for bi-parallel subgraphs and the other one is for bi-fan [87]. Specifically, the quad motifs index of a pair of nodes 𝑖 and 𝑗 is defined as:…”

Section: -Hop Neighboursmentioning

confidence: 99%

A Network Science perspective of Graph Convolutional Networks: A survey

Jia¹,

Gabrys²,

Musiał³

2023

Preprint

View full text Add to dashboard Cite

The mining and exploitation of graph structural information have been the focal points in the study of complex networks. Traditional structural measures in Network Science focus on the analysis and modelling of complex networks from the perspective of network structure, such as the centrality measures, the clustering coefficient, and motifs and graphlets, and they have become basic tools for studying and understanding graphs. In comparison, graph neural networks, especially graph convolutional networks (GCNs), are particularly effective at integrating node features into graph structures via neighbourhood aggregation and message passing, and have been shown to significantly improve the performances in a variety of learning tasks. These two classes of methods are, however, typically treated separately with limited references to each other. In this work, aiming to establish relationships between them, we provide a network science perspective of GCNs. Our novel taxonomy classifies GCNs from three structural information angles, i.e., the layer-wise message aggregation scope, the message content, and the overall learning scope. Moreover, as a prerequisite for reviewing GCNs via a network science perspective, we also summarise traditional structural measures and propose a new taxonomy for them.Finally and most importantly, we draw connections between traditional structural approaches and graph convolutional networks, and discuss potential directions for future research.

show abstract

A Network Science Perspective of Graph Convolutional Networks: A Survey

2023

View full text Add to dashboard Cite

The mining and exploitation of graph structural information have been the focal points in the study of complex networks. Traditional structural measures in Network Science focus on the analysis and modelling of complex networks from the perspective of network structure, such as the centrality measures, the clustering coefficient, and motifs and graphlets, and they have become basic tools for studying and understanding graphs. In comparison, graph neural networks, especially graph convolutional networks (GCNs), are particularly effective at integrating node features into graph structures via neighbourhood aggregation and message passing, and have been shown to significantly improve the performances in a variety of learning tasks. These two classes of methods are, however, typically treated separately with limited references to each other. In this work, aiming to establish relationships between them, we provide a network science perspective of GCNs. Our novel taxonomy classifies GCNs from three structural information angles, i.e., the layer-wise message aggregation scope, the message content, and the overall learning scope. Moreover, as a prerequisite for reviewing GCNs via a network science perspective, we also summarise traditional structural measures and propose a new taxonomy for them. Finally and most importantly, we draw connections between traditional structural approaches and graph convolutional networks, and discuss potential directions for future research.

show abstract

A Quad Motifs Index for Directed Link Prediction

Cited by 5 publications

References 32 publications

A Novel Link Prediction Method for Opportunistic Networks Based on Random Walk and a Deep Belief Network

A Novel Link Prediction Method for Opportunistic Networks Based on Random Walk and a Deep Belief Network

A Network Science perspective of Graph Convolutional Networks: A survey

A Network Science Perspective of Graph Convolutional Networks: A Survey

Contact Info

Product

Resources

About