Recent trends on community detection algorithms: A survey

Gupta, Sumit; Singh, Dhirendra Pratap

doi:10.1142/s0217984920504084

Cited by 11 publications

(6 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Model-based methods use probabilistic, diffusion, or dynamics models to simulate the community detection problem, these models include the stochastic block model, label propagation, random walks, Potts models, etc [22]. The heuristic methods comprise the largest family of community detection algorithms, which usually apply a divisive or expanding strategy to search communities, some measurement or objective function is applied to terminate the division or expanding process [23]. In our previous work, a fast and effective expanding heuristic algorithm, namely ICDA [22] was put forward to support weighted network division.…”

Section: Community Detectionmentioning

confidence: 99%

Community-based Zigzag Piloting Algorithm for the Strong Generalized Minimum Label Spanning Tree Problem

Long

LONG

et al. 2022

Preprint

View full text Add to dashboard Cite

Edge-labeled graph (ELG) is an important abstract model of many practical applications, in which each edge is associated with one or more labels. Searching the minimum label spanning tree (MLST) of ELG is an important issue and proved NP-hard. In the last decade, researchers have put forward some algorithms, however, high computational cost and lower searching effectiveness are still the main obstacles, especially for large-size graphs. In this paper, we propose a heuristic to solve the strong generalized MLST problem (SGMLSTP). We decompose the SGMLSTP into two sub-problems, one is to search a sub-graph containing one or more spanning trees with the minimum labels from the original graph, and another is to search a spanning tree from the acquired sub-graph. As the latter sub-problem is already solved effectively, we focus on the former sub-problem and propose a community-based zigzag piloting algorithm: Firstly a weighted label graph is derived from the edge-labeled graph; then the label graph is partitioned and label communities are chosen in combination to form the initial solutions; finally, the zigzag piloting process is applied to make the initial solutions feasible and refined, of which the optimum one has the least labels. Label partition largely reduces the computation cost of searching the initial solutions, the zigzag piloting process help increase searching effectiveness, and experimental results on typical benchmark datasets fully verify this point and show better effectiveness and performance than that of the state-of-the-art algorithms.

show abstract

Section: Community Detectionmentioning

confidence: 99%

Community-based Zigzag Piloting Algorithm for the Strong Generalized Minimum Label Spanning Tree Problem

Long

LONG

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Table 1 lists the existing literature in this field. [45] 2013 Overlapping Community Discovery Methods: A Survey [46] 2014 A review on overlapping community detection methodologies [47] 2017 Overlapping Community Detection of Complex Network: A Survey [48] 2019 Recent trends on community detection algorithms: A survey [49] 2020 A Review on Community Detection algorithms and Evaluation Measures in Social Networks [50] 2021 A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning [51] 2021 A Comprehensive Survey on Community Detection with Deep Learning [52] 2021…”

Section: Community Detection Techniquesmentioning

confidence: 99%

A Community-Driven Deep Collaborative Approach for Recommender Systems

2022

View full text Add to dashboard Cite

Recommender systems (RS) are increasingly leveraging the power of graphs to enhance accuracy. However, we stipulate that existing methods don't take into consideration the inherent behavior of communities and the interaction between all the sub-groups of the network. In this work, we develop a Deep Graph-based Collaborative Filtering recommender system (DGCF), which incorporates the concept of community profiling and leverages the power of Graph Neural Networks. DGCF utilizes multiple graphs to exploit all types of information from the different user interactions. It extracts the overlapping communities from the homophily user-user graph and also integrates the high-order information from the user-item bipartite graph. We conduct experiments and evaluate the DGCF on the MovieLens datasets(ML-100K and ML-1M), and Douban dataset. Our experiments reveal significant improvements over a number of the latest deep learning models for recommender systems. Results also support that DGCF has the potential to render better recommendations as it extracts deep relationships using the community structure.

show abstract

“…Terefore, fnding these groups can provide meaningful information for experts or recommender systems to make sound decisions [1,2]. Te goal of community detection is to fnd a partition for the network that separates these densely connected parts from each other [3]. It must be noted that community detection difers from graph partitioning problems based on the predefned number of communities and their nodes.…”

Section: Introductionmentioning

confidence: 99%

Detecting Communities in Complex Networks Using an Adaptive Genetic Algorithm and Node Similarity-Based Encoding

2023

View full text Add to dashboard Cite

Detecting communities in complex networks can shed light on the essential characteristics and functions of the modeled phenomena. This topic has attracted researchers from both academia and industry. Among different community detection methods, genetic algorithms (GAs) have become popular. Considering the drawbacks of the currently used locus-based and solution-vector-based encodings to represent the individuals, in this article, we propose (1) a new node similarity-based encoding method, MST-based encoding, to represent a network partition as an individual, which can avoid the shortcomings of the previous encoding schemes. Then, we propose (2) a new adaptive genetic algorithm for the purpose of detecting communities in networks, along with (3) a new initial population generation function to improve the convergence time of the algorithm, and (4) a new sine-based adaptive mutation function which adjusts the mutations according to the improvement in the fitness value of the best individual in the population pool. The proposed method combines the similarity-based and modularity-optimization-based approaches to find communities in complex networks in an evolutionary framework. Besides the fact that the proposed encoding can avoid meaningless mutations or disconnected communities, we show that the new initial population generation function and the new adaptive mutation function can improve the convergence time of the algorithm. Several experiments and comparisons were conducted to verify the effectiveness of the proposed method using modularity and NMI measures on both real-world and synthetic datasets. The results show that the proposed method can find the communities in a significantly shorter time than other GAs while reaching a better trade-off in the different measures.

show abstract

Recent trends on community detection algorithms: A survey

Cited by 11 publications

References 52 publications

Community-based Zigzag Piloting Algorithm for the Strong Generalized Minimum Label Spanning Tree Problem

Community-based Zigzag Piloting Algorithm for the Strong Generalized Minimum Label Spanning Tree Problem

A Community-Driven Deep Collaborative Approach for Recommender Systems

Detecting Communities in Complex Networks Using an Adaptive Genetic Algorithm and Node Similarity-Based Encoding

Contact Info

Product

Resources

About