Going Deep: Graph Convolutional Ladder-Shape Networks

Hu, Ruiqi; Pan, Shirui; Long, Guodong; Qing-hua, Liu; Zhu, Liming; Jiang, Jing

doi:10.1609/aaai.v34i03.5673

Cited by 19 publications

(5 citation statements)

References 22 publications

(18 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these models lead to an over-smoothing problem in community detection. To reduce such negative impact, Graph Convolutional Laddershape Networks (GCLN) [75] is designed as a new GCN architecture for unsupervised community detection (k-means), which is based on the U-Net in the CNN field. A contracting path and an expanding path are symmetrically built in GCLN.…”

Section: B Gcn-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

Section: B Gcn-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

show abstract

“…The proposed strategies try to keep the number of layers to relatively small numbers (up to three, some examples are [48,49,57,60]). The ladder-shaped architecture proposed by [65] et al is another idea to overcome this issue. 5.…”

Section: Performance Degrades As Graph Convolutional Layers Are Addedmentioning

confidence: 99%

A Survey on the Recent Advances of Deep Community Detection

2021

View full text Add to dashboard Cite

In the first days of social networking, the typical view of a community was a set of user profiles of the same interests and likes, and this community kept enlarging by searching, proposing, and adding new members with the same characteristics that were likely to interfere with the existing members. Today, things have changed dramatically. Social networking platforms are not restricted to forming similar user profiles: The vast amounts of data produced every day have given opportunities to predict and suggest relationships, behaviors, and everyday activities like shopping, food, traveling destinations, etc. Every day, vast data amounts are generated by the famous social networks such as Facebook, Twitter, Instagram, and so on. For example, Facebook alone generates 4 petabytes of data per day. The analysis of such data is of high importance to many aspects like recommendation systems, businesses, health organizations, etc. The community detection problem received considerable attention a long time ago. Communities are represented as clusters of an entire network. Most of the community detection techniques are based on graph structures. In this paper, we present the recent advances of deep learning techniques for community detection. We describe the most recent strategies presented in this field, and we provide some general discussion and some future trends.

show abstract

“…To realize the convolution on graphs, there are two types of GCNs. Spectral-based GCNs [7,13,23,20] are based on the convolution theorem to perform convolution by transforming graph signals into the spectral domain via the graph Fourier transform. Spatialbased GCNs [18,19,39,31,40,44] update node representations by aggregating the message from its neighbor nodes, just like applying convolutional kernel on a local image patch.…”

Section: Related Workmentioning

confidence: 99%

A Hyperbolic-to-Hyperbolic Graph Convolutional Network

Dai¹,

Wu²,

Gao³

et al. 2021

Preprint

View full text Add to dashboard Cite

Hyperbolic graph convolutional networks (GCNs) demonstrate powerful representation ability to model graphs with hierarchical structure. Existing hyperbolic GCNs resort to tangent spaces to realize graph convolution on hyperbolic manifolds, which is inferior because tangent space is only a local approximation of a manifold. In this paper, we propose a hyperbolic-to-hyperbolic graph convolutional network (H2H-GCN) that directly works on hyperbolic manifolds. Specifically, we developed a manifoldpreserving graph convolution that consists of a hyperbolic feature transformation and a hyperbolic neighborhood aggregation. The hyperbolic feature transformation works as linear transformation on hyperbolic manifolds. It ensures the transformed node representations still lie on the hyperbolic manifold by imposing the orthogonal constraint on the transformation sub-matrix. The hyperbolic neighborhood aggregation updates each node representation via the Einstein midpoint. The H2H-GCN avoids the distortion caused by tangent space approximations and keeps the global hyperbolic structure. Extensive experiments show that the H2H-GCN achieves substantial improvements on the link prediction, node classification, and graph classification tasks.

show abstract

Going Deep: Graph Convolutional Ladder-Shape Networks

Cited by 19 publications

References 22 publications

A Comprehensive Survey on Community Detection With Deep Learning

A Comprehensive Survey on Community Detection With Deep Learning

A Survey on the Recent Advances of Deep Community Detection

A Hyperbolic-to-Hyperbolic Graph Convolutional Network

Contact Info

Product

Resources

About