8 Hits in 2.7 sec

vGraph: A Generative Model for Joint Community Detection and Node Representation Learning [article]

Fan-Yun Sun, Meng Qu, Jordan Hoffmann, Chin-Wei Huang, Jian Tang
2019 arXiv   pre-print
We propose a probabilistic generative model called vGraph to learn community membership and node representation collaboratively.  ...  Experimental results on multiple real-world graphs show that vGraph is very effective in both community detection and node representation learning, outperforming many competitive baselines in both tasks  ...  In this paper, we propose a novel probabilistic generative model called vGraph for joint community detection and node representation learning. vGraph assumes that each node v can be represented as a mixture  ... 
arXiv:1906.07159v2 fatcat:emvhbxiuf5gvdcg6y77dhnqf4a

Variational Embeddings for Community Detection and Node Representation [article]

Rayyan Ahmad Khan, Muhammad Umer Anwaar, Omran Kaddah, Martin Kleinsteuber
2021 arXiv   pre-print
We propose an efficient generative model called VECoDeR for jointly learning Variational Embeddings for Community Detection and node Representation.  ...  A joint learning framework leverages community-aware node embeddings for better community detection.  ...  Our main contributions are summarized below: • We propose an efficient generative model called VE-CODER for joint community detection and node representation learning. • We adopt a novel approach and argue  ... 
arXiv:2101.03885v1 fatcat:lxu5zjpdgzh6xp5rw2ceylju44

Deep Graph Clustering via Mutual Information Maximization and Mixture Model [article]

Maedeh Ahmadi, Mehran Safayani, Abdolreza Mirzaei
2022 arXiv   pre-print
Attributed graph clustering or community detection which learns to cluster the nodes of a graph is a challenging task in graph analysis.  ...  In this paper, we introduce a contrastive learning framework for learning clustering-friendly node embedding.  ...  The authors are with the Department of Electrical and Computer Engineering, Isfahan University of Technology, Isfahan 84156-83111, Iran (e-mail:  ... 
arXiv:2205.05168v1 fatcat:o6xb72h5fvhp7kp5wbwqwcmeqy

Community Detection in Partially Observable Social Networks [article]

Cong Tran, Won-Yong Shin, Andreas Spitz
2021 arXiv   pre-print
To solve this problem, we introduce KroMFac, a new framework that conducts community detection via regularized nonnegative matrix factorization (NMF) based on the Kronecker graph model.  ...  In this paper, we address a new problem of detecting overlapping community structures in the context of such an incomplete network, where communities in the network are allowed to overlap since nodes belong  ...  presents a generative model for joint community detection and node representation learning. 4 In this case, we first recover the matrix A ( ) via the function GraphRecv and then obtain via alternative  ... 
arXiv:1801.00132v8 fatcat:lcylh3shrzdgfn3i6bnei5fd5i

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

Di Jin, Zhizhi Yu, Pengfei Jiao, Shirui Pan, Dongxiao He, Jia Wu, Philip S. Yu, Weixiong Zhang
2021 arXiv   pre-print
model and deep learning.  ...  utilize deep learning and convert networked data into low dimensional representation.  ...  [117] propose a probabilistic generative model, i.e., vGraph, to jointly detect overlapping (and nonoverlapping) communities and learn node (and community) representation. vGraph represents each node  ... 
arXiv:2101.01669v3 fatcat:p2lkjuslmzd6hc6kpum3sz5xwq

Network Representation Learning Enhanced by Partial Community Information That Is Found Using Game Theory

Hanlin Sun, Wei Jie, Jonathan Loo, Liang Chen, Zhongmin Wang, Sugang Ma, Gang Li, Shuai Zhang
2021 Information  
We also implement the framework and propose two node embedding methods that use game theory for detecting partial community information.  ...  Network representation learning, also called network embedding, provides a practical and promising way to solve these issues.  ...  Data Availability Statement: The data and code presented in this study are available on request from the corresponding author. The data are not publicly available due to privacy reasons.  ... 
doi:10.3390/info12050186 doaj:bfe1626a2ca24dde9dc9137dbcb4ba4f fatcat:vo32hudvmrg3pl4tomm6gwptyy

Network Representation Learning: From Preprocessing, Feature Extraction to Node Embedding [article]

Jingya Zhou, Ling Liu, Wenqi Wei, Jianxi Fan
2021 arXiv   pre-print
steps, node feature extraction steps and node embedding model training for a NRL task such as link prediction and node clustering.  ...  developing the next generation of network representation learning algorithms and systems.  ...  Specifically, for each node v, vGraph first draws a community assignment from ( |v) and then generates an edge e vu by drawing another node u according to distribution ( |C).  ... 
arXiv:2110.07582v1 fatcat:gbjn3evwwzf4xkeobrsfo6hope

Self-supervised Learning: Generative or Contrastive [article]

Xiao Liu, Fanjin Zhang, Zhenyu Hou, Zhaoyu Wang, Li Mian, Jing Zhang, Jie Tang
2021 arXiv   pre-print
In this survey, we take a look into new self-supervised learning methods for representation in computer vision, natural language processing, and graph learning.  ...  As an alternative, self-supervised learning attracts many researchers for its soaring performance on representation learning in the last several years.  ...  ACKNOWLEDGMENTS The work is supported by the National Key R&D Program of China (2018YFB1402600), NSFC for Distinguished Young Scholar (61825602), and NSFC (61836013).  ... 
arXiv:2006.08218v5 fatcat:t324amt3lzaehfa262xbn5hkqe