Constrained Local Graph Clustering by Colored Random Walk

Yan, Yaowei; Bian, Yuchen; Luo, Dongsheng; Lee, Dongwon; Zhang, Xiang

doi:10.1145/3308558.3313719

Cited by 24 publications

(20 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Local clustering algorithms are designed to find community structures containing a set of seed/query nodes. There are three common types of local clustering algorithms: the RW based methods [7], [9], [10], [17], [20], [22], the target optimization methods [13], [18], [21], [25]- [28] and the spectral methods [19], [29], [30]. For target optimization methods, an optimization objective function is set, and the algorithm is trying to optimize this function during the whole clustering process.…”

Section: Related Workmentioning

confidence: 99%

“…However, getting the embedding of nodes requires many computing resources, and the accuracy for these algorithms did not show advantages compared to other algorithms. RW based local community detection algorithms have the advantage that no optimization objective function is needed, and the process of sampling random walk paths is efficient [20]. They only need to ensure the convergence of the random walk.…”

Section: Related Workmentioning

confidence: 99%

“…Given a set of seed nodes, local community detection algorithms aim to find the community containing these seed nodes. Random walk (RW) [7], [9], [10], [17], [20], [22] based algorithms are the most prevalent methods used in local community detection. In these methods, random walk paths are repeatedly sampled around the seed nodes until a converged random walker visiting probability distribution for nodes is obtained.…”

Section: Introductionmentioning

confidence: 99%

“…The boundary problem happens when the random walker object is near the boundary of the community, and then when further wandering is performed, it is easy to visit nodes belonging to other communities. For the existing random walk based algorithms for local community detection, i.e., RWR [9], VRW [7], CRW [20], etc., none of these algorithms can determine whether the random walker agent is at the community boundary position. This means that these algorithms are prone to boundary problems when the seed nodes are selected close to the community boundary or when the random walker wanders to the boundary of the community.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Density Sensitive Random Walk for Local Community Detection

Jin

et al. 2021

IEEE Access

View full text Add to dashboard Cite

Given a network, local community detection aims at finding the community that contains a set of query nodes (seed nodes). Random walk (RW) based algorithms have shown great success in various local community detection scenarios. Starting from the seed nodes, RW based algorithms continuously sample random walk paths to get the clustering result. However, current RW based algorithms for local clustering are faced with the following two problems. The random walker is insensitive to the community boundary and might have an unbalanced walk. These problems would have a negative effect on the clustering result of RW based algorithms. In this paper, we propose a density sensitive random walk algorithms (DSRW) for local community detection. By integrating the graph density information into the random walk process, the problems are resolved and the clustering result is improved. We provide the convergence proof of DSRW algorithm and perform extensive experiments on both real and synthetic datasets. Results show that our DSRW algorithm has achieved the state-of-the-art result in most scenarios.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Density Sensitive Random Walk for Local Community Detection

Jin

et al. 2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Then the local community is selected to minimize a predefined goodness function. Colored Random Walk [26] is also a typical random walk based algorithms which find node as seed with global attribute in the beginning and then detect the communities with local random walk. Liu et al [27] proposed a hierarchical method called the divide and agglomerate algorithm (i.e., DA) which detect the communities by dividing the networks into many part and then merge them refer to the modularity.…”

Section: ) the Hybrid Detection Algorithmmentioning

confidence: 99%

A Novel Community Detection Algorithm Based on Paring, Splitting and Aggregating in Internet of Things

Xia

Zhang

et al. 2020

IEEE Access

View full text Add to dashboard Cite

The explosive growth of Internet of Things (i.e., IoT) terminal equipment makes its topology more complex, which leads to the increasing cost of network research. Recently, the implicit community structure is widely used to improve the efficiency of research. However, most of the non-overlapping community detection algorithms have some weakness, such as the large number of community detected and the obvious scale gap between communities. To address these abovementioned problems, we design a novel non-overlapping community detection algorithm, named as Pairing, Splitting and Aggregating algorithm (i.e., PSA). Firstly, in order to improve the accuracy of community division, a new node similarity index is designed to transform the network into a large number of similar node pairs. Secondly, based on the connected branches composed of similar node pairs, the network is further divided into several similar node sets. Thirdly, to balance the scale gap of different communities, the Grasshopper Optimization Algorithm, (i.e., GOA) is introduced to combine the local attribute (i.e., conductance) and global attribute (i.e., modularity) together to aggregate similar node sets into potential (or final) communities. Finally, the experimental results show that PSA not only controls the difference among communities well, but also outperforms the other four popular algorithms in terms of two metrics. Moreover, we propose a community-based resource discovery method (or scheme), named as Community-assisted Short-distancequery Resource Discovery algorithm (i.e., CSRD) to further verify the efficiency of PSA. The results show that the resource discovery efficiency of CSRD using PSA is better compared with other algorithms.

show abstract