A Comprehensive Survey on Community Detection With Deep Learning (2021-05-26T00:00:00.000000Z)

TL;DR

A comprehensive review of the latest progress in community detection through deep learning through deep neural networks, including deep learning models based on deep neural networks, deep nonnegative matrix factorization, and deep sparse filtering is reviewed.

Abstract

Detecting a community in a network is a matter of discerning the distinct features and connections of a group of members that are different from those in other communities. The ability to do this is of great significance in network analysis. However, beyond the classic spectral clustering and statistical inference methods, there have been significant developments with deep learning techniques for community detection in recent years—particularly when it comes to handling high-dimensional network data. Hence, a comprehensive review of the latest progress in community detection through deep learning is timely. To frame the survey, we have devised a new taxonomy covering different state-of-the-art methods, including deep learning models based on deep neural networks (DNNs), deep nonnegative matrix factorization, and deep sparse filtering. The main category, i.e., DNNs, is further divided into convolutional networks, graph attention networks, generative adversarial networks, and autoencoders. The popular benchmark datasets, evaluation metrics, and open-source implementations to address experimentation settings are also summarized. This is followed by a discussion on the practical applications of community detection in various domains. The survey concludes with suggestions of challenging topics that would make for fruitful future research directions in this fast-growing deep learning field.

Authors

S. Nepal

2 papers

Jia Wu

2 papers

Shan Xue

2 papers

TL;DR

Abstract

Authors

References211 items

A deep learning approach for semi-supervised community detection in Online Social Networks

Unsupervised learning for community detection in attributed networks based on graph convolutional network

Detecting Communities from Heterogeneous Graphs: A Context Path-based Graph Neural Network Model

Graph Debiased Contrastive Learning with Joint Representation Clustering

Self-Supervised Graph Convolutional Network for Multi-View Clustering

A weighted network community detection algorithm based on deep learning

Self-Training Enhanced: Network Embedding and Overlapping Community Detection With Adversarial Learning

Spectral embedding network for attributed graph clustering

Self-supervised Heterogeneous Graph Neural Network with Co-contrastive Learning

Graph embedding clustering: Graph attention auto-encoder with cluster-specificity distribution

HDMI: High-order Deep Multiplex Infomax

Knowledge-Preserving Incremental Social Event Detection via Heterogeneous GNNs

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

DNC: A Deep Neural Network-based Clustering-oriented Network Embedding Algorithm

CANE: community-aware network embedding via adversarial training

CommDGI: Community Detection Oriented Deep Graph Infomax

Edge classification based on Convolutional Neural Networks for community detection in complex network

A survey of community detection methods in multilayer networks

An evolutionary autoencoder for dynamic community detection

Community Detection Based on Modularized Deep Nonnegative Matrix Factorization

SEAL: Learning Heuristics for Community Detection with Generative Adversarial Networks

Adaptive Graph Encoder for Attributed Graph Embedding

JANE: Jointly Adversarial Network Embedding

Stacked autoencoder-based community detection method via an ensemble clustering framework

Multi-View Attribute Graph Convolution Networks for Clustering

Multi-Class Imbalanced Graph Convolutional Network Learning

Efficient Community Search over Large Directed Graph: An Augmented Index-based Approach

Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs

Graph Neural Network Encoding for Community Detection in Attribute Networks

Deep Learning for Community Detection: Progress, Challenges and Opportunities

One2Multi Graph Autoencoder for Multi-view Graph Clustering

Graph Representation Learning via Ladder Gamma Variational Autoencoders

Going Deep: Graph Convolutional Ladder-Shape Networks

Structural Deep Clustering Network

MAGNN: Metapath Aggregated Graph Neural Network for Heterogeneous Graph Embedding

Deep Multi-Graph Clustering via Attentive Cross-Graph Association

Community detection in node-attributed social networks: a survey

Optimizing Variational Graph Autoencoder for Community Detection

Independence Promoted Graph Disentangled Networks

Effective Decoding in Graph Auto-Encoder using Triadic Closure

Unsupervised Attributed Multiplex Network Embedding

Hierarchical Community Structure Preserving Network Embedding: A Subspace Approach

Detecting the evolving community structure in dynamic social networks

Flexible Multi-View Representation Learning for Subspace Clustering

High-performance community detection in social networks using a deep transitive autoencoder

Variational Graph Embedding and Clustering with Laplacian Eigenmaps

Cross-domain network representations

Link Prediction with Signed Latent Factors in Signed Social Networks

ProGAN: Network Embedding via Proximity Generative Adversarial Network

Graph Convolutional Networks Meet Markov Random Fields: Semi-Supervised Community Detection in Attribute Networks

Community detection with the Label Propagation Algorithm: A survey

Evolutionary Community Detection in Dynamic Social Networks

Attributed Graph Clustering via Adaptive Graph Convolution

Attributed Graph Clustering: A Deep Attentional Embedding Approach

Stochastic Blockmodels meet Graph Neural Networks

A deep learning based community detection approach

Heterogeneous Graph Attention Network

Simplifying Graph Convolutional Networks

CommunityGAN: Community Detection with Generative Adversarial Nets

Deep Network Embedding for Graph Representation Learning in Signed Networks

Learning Community Structure with Variational Autoencoder

Deep Autoencoder-like Nonnegative Matrix Factorization for Community Detection

Hierarchical Community Detection by Recursive Partitioning

Overlapping Community Detection with Graph Neural Networks

Community discovery in networks with deep sparse filtering

Community detection in complex networks using structural similarity

Multiple Structure-View Learning for Graph Classification

Deep Attributed Network Embedding

Integrative Network Embedding via Deep Joint Reconstruction

Evolutionary Computation for Community Detection in Networks: A Review

Galaxy Network Embedding: A Hierarchical Community Structure Preserving Approach

Social Recommendation with an Essential Preference Space

Community detection in networks: A multidisciplinary review

Community Deception or: How to Stop Fearing Community Detection Algorithms

DFuzzy: a deep learning-based fuzzy clustering model for large graphs

Graph Clustering with Dynamic Embedding