Multiscale Local Community Detection in Social Networks

Luo, Wenjian; Zhang, Daofu; Li, Ni; Lu, Nannan

doi:10.1109/tkde.2019.2938173

Cited by 23 publications

(10 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researchers have proposed various approaches for local community detection [18], [35]- [38]. Luo et al [7] proposed a local modularity 𝐿𝑄 and designed modularity optimization algorithms based on 𝐿𝑄. He et al [28] developed a community detection method based on the local spectral subspace, which is defined based on the Krylov subspace.…”

Section: B Local Community Detection and Community Searchmentioning

confidence: 99%

“…Prior Work. The studies on finding communities contain global community detection [4], [5], local community detection [6], [7] and community search [8], [9]. Global community detection algorithms aim to detect all communities in social networks [4], [10], [11].…”

Section: Introductionmentioning

confidence: 99%

“…To compensate for these shortcomings, local community detection has been investigated, which can quickly detect the community that contains the given node with only local information [7], [19]- [21]. Similar to the local community detection problem, community search aims to find a subgraph containing a set of given nodes.…”

Section: Introductionmentioning

confidence: 99%

“…Some community search works need global information of social networks [8], and some do not [22], [23]. These above studies consider only the link between nodes [7], [8], [19], [20], [22], ignoring the nodes' locations, so the detected communities may not be spatially cohesive and may not be suitable for some locationbased services [3], [15], [24].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Spatial-Aware Local Community Detection Guided by Dominance Relation

Li¹,

Xu²,

Zhang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

The problem of finding the spatial-aware community for a given node has been defined and investigated in geosocial networks. However, existing studies suffer from two limitations: a) the criteria of defining communities are determined by parameters, which are difficult to set; b) algorithms may require global information and are not suitable for situations where the network is incomplete. Therefore, we propose spatialaware local community detection (SLCD), which finds the spatialaware local community with only local information and defines the community based on the difference in the sparseness of edges inside and outside the community. Specifically, to address the SLCD problem, we design a novel spatial aware local community detection algorithm based on dominance relation, but this algorithm incurs high cost. To further improve the efficiency, we propose an approximate algorithm. Experimental results demonstrate that the proposed approximate algorithm outperforms the comparison algorithms.

show abstract

Section: B Local Community Detection and Community Searchmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Spatial-Aware Local Community Detection Guided by Dominance Relation

Li¹,

Xu²,

Zhang³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…Network has the ability of depicting entities and their relations. So it is widely applied to model various real world complex systems such as social platform [24,26,41], power grid [25,34] and so on [10,30]. As a basic problem in network science, network dismantling (ND) [6] aims to find a set of nodes whose removal will greatly destory the connectivity of network.…”

Section: Introductionmentioning

confidence: 99%

Betweenness Approximation for Hypernetwork Dismantling with Hypergraph Neural Network

Yan¹,

Xie²,

Zhang³

2022

Preprint

View full text Add to dashboard Cite

The purpose of Network Dismantling (ND) is to find an optimal set of nodes and removing these nodes can greatly decrease the network connectivity. However, current dismantling methods are mainly focus on traditional simple network which only consider the pairwise interaction between two nodes, while the hypernetwork, which can model higher order groupwise relation among arbitrary nodes, is more suitable for modeling real world. Due to the structural difference between simple network and hypernetwork, current dismantling methods cannot be directly applied to hypernetwork dismantling. Although some centrality measures in hypernetwork can be used for hypernetwork dismantling, they face the problem of banlancing effect and efficiency. Therefore, in this paper, we propose a novel HyperNetwork Dismantling methods based on hypergraph neural network, called HND. Specifically, our method first generates plenty of node ranking samples with the help of synthetic hypernetwork generator. Then, a node betweenness approximation model in hypernetwork is built based on hypergraph neural network. And this model is trained on those ranking samples generated in previous step until convergence. Finally, the well-trained model is utilized to approximate the nodes' betweenness in real world hypernetworks and further used for dismantling. To confirm the effectiveness of our method, we conduct extensive experiments on five real world hypernetworks. The experimental results demostrate that the HND outperforms various baselines.

show abstract