A Non-negative Symmetric Encoder-Decoder Approach for Community Detection

Sun, Bingjie; Shen, Huawei; Gao, Jinhua; Ouyang, Wentao; Cheng, Xueqi

doi:10.1145/3132847.3132902

Cited by 65 publications

(27 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Shi et al [75] present a novel pairwise constrained non-negative symmetric matrix factorization (PCSNMF) method, which imposes pairwise constraints generated from ground-truth community information, to improve the performance of community detection. Sun et al [76] design a non-negative symmetric encoder-decoder approach to derive a better latent representation to improve community detection. Unlike other NMF-based methods that merely pay attention to the loss of the decoder, they combine the loss of the decoder and encoder to construct a unified loss function, so that the community membership of each node obtained is clearer and more explanatory.…”

Section: Matrix Factorization-based Methodsmentioning

confidence: 99%

A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning

Jin

Jiao

et al. 2021

Preprint

View full text Add to dashboard Cite

Community detection, a fundamental task for network analysis, aims to partition a network into multiple sub-structures to help reveal their latent functions. Community detection has been extensively studied in and broadly applied to many real-world network problems. Classical approaches to community detection typically utilize probabilistic graphical models and adopt a variety of prior knowledge to infer community structures. As the problems that network methods try to solve and the network data to be analyzed become increasingly more sophisticated, new approaches have also been proposed and developed, particularly those that utilize deep learning and convert networked data into low dimensional representation. Despite all the recent advancement, there is still a lack of insightful understanding of the theoretical and methodological underpinning of community detection, which will be critically important for future development of the area of network analysis. In this paper, we develop and present a unified architecture of network communityfinding methods to characterize the state-of-the-art of the field of community detection. Specifically, we provide a comprehensive review of the existing community detection methods and introduce a new taxonomy that divides the existing methods into two categories, namely probabilistic graphical model and deep learning. We then discuss in detail the main idea behind each method in the two categories. Furthermore, to promote future development of community detection, we release several benchmark datasets from several problem domains and highlight their applications to various network analysis tasks. We conclude with discussions of the challenges of the field and suggestions of possible directions for future research.

show abstract

Section: Matrix Factorization-based Methodsmentioning

confidence: 99%

A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning

Jin

Jiao

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…where • F denotes the Frobenius norm, L represents the graph Laplacian matrix, and graph regularization [124] focuses on the network topological similarity to cluster neighboring nodes. A further work [125] adds a sparsity constraint into the above deep NMF-based community detection.…”

Section: Deep Nonnegative Matrix Factorization-based Community Detectionmentioning

confidence: 99%

A Comprehensive Survey on Community Detection With Deep Learning

Xue

Liu

et al. 2024

IEEE Trans. Neural Netw. Learning Syst.

191

View full text Add to dashboard Cite

A community reveals the features and connections of its members that are different from those in other communities in a network. Detecting communities is of great significance in network analysis. Despite the classical spectral clustering and statistical inference methods, we notice a significant development of deep learning techniques for community detection in recent years with their advantages in handling high dimensional network data. Hence, a comprehensive overview of community detection's latest progress through deep learning is timely to both academics and practitioners. This survey devises and proposes a new taxonomy covering different categories of the state-of-theart methods, including deep learning-based models upon deep neural networks, deep nonnegative matrix factorization and deep sparse filtering. The main category, i.e., deep neural networks, is further divided into convolutional networks, graph attention networks, generative adversarial networks and autoencoders. The survey also summarizes the popular benchmark data sets, model evaluation metrics, and open-source implementations to address experimentation settings. We then discuss the practical applications of community detection in various domains and point to implementation scenarios. Finally, we outline future directions by suggesting challenging topics in this fast-growing deep learning field.

show abstract

“…Non-overlapping community detection is analogous to clustering, and assumes that a node can only belong to a single group; see, for example, [18,26,28,31]. While overlapping community detection is analogous to fuzzy clustering as nodes have an affiliation with multiple clusters; look for example [16,36,43,49,51].…”

Section: Community Detectionmentioning

confidence: 99%

“…We would also like to emphasize that the use of graph kernels would not be feasible on graph datasets which are this numerous. [11,16,36,43,49,51] we assigned each node to the cluster that has the strongest affiliation score with the node (ties were broken randomly). The metric used for the clustering performance measurement is the average normalized mutual information (henceforth NMI) score calculated between the cluster membership vector and the factual class memberships.…”

Section: Datasetsmentioning

confidence: 99%

“…We report in Table 3 the NMI averages with the standard errors calculated from 100 experimental runs. Looking at Table 3 first we notice that the non-overlapping community detection techniques [11,18,26,28,31] materially outperform the overlapping models which create latent spaces [16,36,43,49,51] on every dataset in terms of NMI. Second, those algorithms which create clusters based on the presence of closed triangles (SCD [26], Ego-Splitting [11]) have a general strong performance.…”

Section: Datasetsmentioning

confidence: 99%

See 1 more Smart Citation

Karate Club

Rózemberczki

Kiss²,

Sarkar

2020

Proceedings of the 29th ACM International Conference on Information &Amp; Knowledge Management

View full text Add to dashboard Cite

Graphs encode important structural properties of complex systems. Machine learning on graphs has therefore emerged as an important technique in research and applications. We present Karate Club-a Python framework combining more than 30 state-of-the-art graph mining algorithms. These unsupervised techniques make it easy to identify and represent common graph features. The primary goal of the package is to make community detection, node and whole graph embedding available to a wide audience of machine learning researchers and practitioners. Karate Club is designed with an emphasis on a consistent application interface, scalability, ease of use, sensible out of the box model behaviour, standardized dataset ingestion, and output generation. This paper discusses the design principles behind the framework with practical examples. We show Karate Club's efficiency in learning performance on a wide range of real world clustering problems and classification tasks along with supporting evidence of its competitive speed.

show abstract

A Non-negative Symmetric Encoder-Decoder Approach for Community Detection

Cited by 65 publications

References 43 publications

A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning

A Survey of Community Detection Approaches: From Statistical Modeling to Deep Learning

A Comprehensive Survey on Community Detection With Deep Learning

Karate Club

Contact Info

Product

Resources

About