A Fast Parallel Genetic Algorithm Based Approach for Community Detection in Large Networks

Ghoshal, Arnab; Das, Nabanita; Bhattacharjee, S.; Chakraborty, Goutam

doi:10.1109/comsnets.2019.8711127

Cited by 17 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are several techniques that have been developed for detecting communities in networks. A number of them are based on modularity-optimization, hierarchical clustering, label propagation, region density, core clustering [33], game theory, information theory (infomap) [34,35,36,37,38], and biological evolution (genetics) [39,40,41]. Metrics such as the modularity score [20,42,40], Normalized Mutual Information index (NMI) [43,44], and Jaccard Index [43] are used to compare the quality of communities obtained with different approaches.…”

Section: Literature Surveymentioning

confidence: 99%

Selecting a suitable Parallel Label-propagation based algorithm for Disjoint Community Detection

Sahu¹

2023

Preprint

View full text Add to dashboard Cite

Community detection is an essential task in network analysis as it helps identify groups and patterns within a network. High-speed community detection algorithms are necessary to analyze large-scale networks in a reasonable amount of time. Researchers have made significant contributions in the development of high-speed community detection algorithms, particularly in the area of label-propagation based disjoint community detection. These algorithms have been proven to be highly effective in analyzing large-scale networks in a reasonable amount of time. However, it is important to evaluate the performance and accuracy of these existing methods to determine which algorithm is best suited for a particular type of network and specific research problem. In this report, we investigate the RAK, COPRA, and SLPA, three label-propagation-based static community discovery techniques. We pay close attention to each algorithm's minute details as we implement both its single-threaded and multi-threaded OpenMP-based variants, making any necessary adjustments or optimizations and obtaining the right parameter values. The RAK algorithm is found to perform well with a tolerance of 0.05 and OpenMP-based strict RAK with 12 threads was 6.75x faster than the sequential non-strict RAK. The COPRA algorithm works well with a single label for road networks and max labels of 4-16 for other classes of graphs. The SLPA algorithm performs well with increasing memory size, but overall doesn't offer a favourable return on investment. The RAK algorithm is recommended for label-propagation based disjoint community detection.

show abstract

Section: Literature Surveymentioning

confidence: 99%

Selecting a suitable Parallel Label-propagation based algorithm for Disjoint Community Detection

Sahu¹

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Most traditional methods [10][11][12][13] used a heuristic method to generate a linguistic rule for each cell of the pattern space which generates a large number of rules and need another algorithm like a genetic algorithm approach (Genetic Algorithm -Based Rule Selection) to select a small number of significant rules from them to reduce those large number of candidate fuzzy rules. This means that if we have K fuzzy sets for each of n attributes, then the number of linguistic rule = K rules.…”

Section: Phase Three: Fuzzy Rules Extraction Via Sql Statementmentioning

confidence: 99%

“…To solve this problem, a rough sets model based on database systems has been introduced for this problem to redefine a core and reducts by using relational algebra such as Cardinality and Projection. Most traditional methods [10][11][12][13] used a heuristic method to generate a linguistic rule which generates a large number of rules and need other technique like (Genetic Algorithm -Based Rule Selection) to select a small number of significant rules to reduce the large number of candidate fuzzy rules. For this problem we use the algorithm for extracting fuzzy rules using SQL statements which generates efficient smaller number of fuzzy rules immediately without needing to run a genetic algorithm approach to do this step.…”

Section: Introductionmentioning

confidence: 99%

A Fuzzy Rough Model Using Genetic Algorithm for Accuracy Enhancement

2021

IJIES

View full text Add to dashboard Cite

“…Evolutionary computational strategies are abstractions from biological evolutionary theory used to create optimization procedures or methods. This strategy combines the concept of biological evolution with computer technology such as genetic algorithm 14 and particle swarm optimization 15 .…”

Section: Introductionmentioning

confidence: 99%

Community detection with greedy modularity disassembly strategy

Rustamaji¹,

Kusuma²,

Nurdiati³

et al. 2023

Preprint

View full text Add to dashboard Cite

One of the problems in networking is community detection, the process of identifying groups of nodes in a network that are more densely connected than the rest of the network. To measure the quality of community detection in the network using modularity. Greedy modularity is one of the community detection algorithms. It optimizes the modularity score locally at each step rather than globally optimizing over all possible network partitions. However, because the algorithm makes local improvements, it can be trapped in a suboptimal network partition. In this research, we developed the Greedy Modularity algorithm by adding an exploration method: a disassembly node and disassembly community formed to increase modularity. There are four strategies for disassembly nodes: disassembly random nodes, weak nodes, nodes with low embeddedness values, and releasing nodes that do not form triads. The disassembly community strategy includes random communities, weak communities, communities with low internal edge density, communities with low triad participation ratio, and communities with low conductance. The results show increased modularity in various real-world and synthetic network datasets. We also compared the results with various community detection algorithms, and the modularity ranking of these algorithms were in positions 1-8 across various datasets.

show abstract

A Fast Parallel Genetic Algorithm Based Approach for Community Detection in Large Networks

Cited by 17 publications

References 29 publications

Selecting a suitable Parallel Label-propagation based algorithm for Disjoint Community Detection

Selecting a suitable Parallel Label-propagation based algorithm for Disjoint Community Detection

A Fuzzy Rough Model Using Genetic Algorithm for Accuracy Enhancement

Community detection with greedy modularity disassembly strategy

Contact Info

Product

Resources

About