Filters








55,248 Hits in 4.9 sec

Fuzzy multilevel graph embedding

Muhammad Muzzamil Luqman, Jean-Yves Ramel, Josep Lladós, Thierry Brouard
2013 Pattern Recognition  
Our method of explicit graph embedding bridges the gap between structural and statistical pattern recognition.  ...  Experimentation on standard public graph datasets shows that our method outperforms the state-of-the-art methods of graph embedding for richly attributed graphs. (M.M. Luqman), ramel@univ-tours.fr (J.  ...  Graph embedding Graph embedding is a natural outcome of parallel advancements in structural and statistical pattern recognition.  ... 
doi:10.1016/j.patcog.2012.07.029 fatcat:kn2i2vxjpjh6tp5mksv4inxldm

Graph Summarization [article]

Angela Bonifati, Stefania Dumbrava, Haridimos Kondylakis
2020 arXiv   pre-print
As this problem is common to several areas studying graph topologies, different approaches, such as clustering, compression, sampling, or influence detection, have been proposed, primarily based on statistical  ...  One method for condensing and simplifying such datasets is graph summarization.  ...  State of the art approaches to graph summarization through clustering roughly fall into two categories: structural and attributed-based.  ... 
arXiv:2004.14794v3 fatcat:4g4l3exin5dxpoe6pdggbtcory

Structural Adversarial Variational Auto-Encoder for Attributed Network Embedding

Junjian Zhan, Feng Li, Yang Wang, Daoyu Lin, Guangluan Xu
2021 Applied Sciences  
As most networks come with some content in each node, attributed network embedding has aroused much research interest.  ...  Most existing attributed network embedding methods aim at learning a fixed representation for each node encoding its local proximity.  ...  For the node clustering task, we employ the K-means algorithm based on the node embeddings learned from the training phase.  ... 
doi:10.3390/app11052371 fatcat:lww3aaqmgvhwdab6he4erk46wy

Pyramidal Stochastic Graphlet Embedding for Document Pattern Classification

Anjan Dutta, Pau Riba, Josep Llados, Alicia Fornes
2017 2017 14th IAPR International Conference on Document Analysis and Recognition (ICDAR)  
The consideration of pyramid of graphs rather than just a base graph extends the representational power of the graph embedding, which reduces the instability caused due to noise and distortion.  ...  Given a graph representing a document pattern, our method first computes a graph pyramid by successively reducing the base graph.  ...  Method Unlabelled Labelled Dissimilarity Embedding [5] - 95.10 Node Attribute Statistics [13] - 99.20 Fuzzy Graph Embedding [18] - 97.30 SGE [10] 92.80 99.62 Level 2 Level 3 PSGE 93.18 (  ... 
doi:10.1109/icdar.2017.15 dblp:conf/icdar/0001RLF17 fatcat:de5loabe3zgqpbibk5l7dx67xy

Estimating latent positions of actors using Neural Networks in R with GCN4R [article]

Joshua Levy, Carly A Bobak, Brock Christensen, Louis J Vaickus, A. James O'Malley
2020 bioRxiv   pre-print
Here, we introduce GCN4R, an R library for fitting graph neural networks on independent networks to aggregate actor covariate information to yield meaningful embeddings for a variety of network-based tasks  ...  While statistical and machine learning prediction models generally assume independence between actors, network-based statistical methods for social network data allow for dyadic dependence between actors  ...  GNN have emerged as powerful means from which to analyze relational data, improving the ability to represent information between actors and across entire systems through embeddings versus traditional statistical  ... 
doi:10.1101/2020.11.02.364935 fatcat:qkiyeymuxjalbhx6blekhzpg3a

Graph Embedding Framework Based on Adversarial and Random Walk Regularization

Wei Dou, Weiyu Zhang, Ziqiang Weng, Zhongxiu Xia
2020 IEEE Access  
In this paper, we propose a novel graph embedding framework, Adversarial and Random Walk Regularized Graph Embedding (ARWR-GE), which jointly preserves structural and attribute information.  ...  However, most existing graph convolutional network-based embedding algorithms not only ignore the data distribution of the latent codes but also lose the high-order proximity between nodes in a graph,  ...  NODE CLUSTERING One of the most important tasks in graph mining and graph analysis is node clustering, the goal of which is to infer the clusters in graphs based on the graph embedding.  ... 
doi:10.1109/access.2020.3047116 fatcat:t36ppblk5ffk5e6umrwsbroghm

Fairness Amidst Non-IID Graph Data: A Literature Review [article]

Wenbin Zhang, Jeremy C. Weiss, Shuigeng Zhou, Toby Walsh
2022 arXiv   pre-print
On the other hand, graphs are a ubiquitous data structure to capture connections among individual units and is non-IID by nature.  ...  In this survey, we review such recent advance in fairness amidst non-IID graph data and identify datasets and evaluation metrics available for future research.  ...  Its potential to quantify and enforce statistical based graph group clustering fairness has also been discussed therein.  ... 
arXiv:2202.07170v2 fatcat:b4ri7at2b5blncdgbpzbwhe6ea

A Comprehensive Survey on Community Detection with Deep Learning [article]

Xing Su, Shan Xue, Fanzhen Liu, Jia Wu, Jian Yang, Chuan Zhou, Wenbin Hu, Cecile Paris, Surya Nepal, Di Jin, Quan Z. Sheng, Philip S. Yu
2021 arXiv   pre-print
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  ...  Hence, a comprehensive overview of community detection's latest progress through deep learning is timely to academics and practitioners.  ...  Attentional Embedded Graph Clustering [116] Attributed graph clustering: A deep attentional embedding approach DANE Deep Attributed Network Embedding [103] Deep attributed network embedding Deep Autoencoder-like  ... 
arXiv:2105.12584v2 fatcat:matipshxnzcdloygrcrwx2sxr4

Unsupervised Deep Manifold Attributed Graph Embedding [article]

Zelin Zang, Siyuan Li, Di Wu, Jianzhu Guo, Yongjie Xu, Stan Z. Li
2021 arXiv   pre-print
To alleviate these issues, we propose a novel graph embedding framework named Deep Manifold Attributed Graph Embedding (DMAGE).  ...  Unsupervised attributed graph representation learning is challenging since both structural and feature information are required to be represented in the latent space.  ...  To solve the problems mentioned above, we propose Deep Manifold Attributed Graph Embedding (DMAGE), which is a similarity-based framework for attributed graph embedding, as shown in Fig. 2 .  ... 
arXiv:2104.13048v1 fatcat:2e2karxg4zhzdbthkect4bogvq

Confidence-based Simple Graph Convolutional Networks for Face Clustering

Dengdi Sun, Kang Yang, Zhuanlian Ding
2022 IEEE Access  
improves the efficiency of GCN-based face clustering.  ...  Recent studies use graph convolutional networks (GCNs) to learn feature embeddings from the neighborhood information between face images.  ...  Overview of the proposed CSGCN clustering framework. The original image is passed through CNN to obtain the embedded features, and then the embedded features are used to form a graph through KNN.  ... 
doi:10.1109/access.2022.3142922 fatcat:vdswuttw65dmrerjs4a3fwrdoy

Neural-Brane: Neural Bayesian Personalized Ranking for Attributed Network Embedding [article]

Vachik S. Dave, Baichuan Zhang, Pin-Yu Chen, Mohammad Al Hasan
2018 arXiv   pre-print
In this work, we present Neural-Brane, a novel Neural Bayesian Personalized Ranking based Attributed Network Embedding.  ...  We evaluate the quality of vertex embedding produced by Neural-Brane by solving the node classification and clustering tasks on four real-world datasets.  ...  CONCLUSION We present a novel neural Bayesian personalized ranking formulation for attributed network embedding, which we call Neural-Brane.  ... 
arXiv:1804.08774v2 fatcat:xkln3ks3f5a25egzx52zxxvwpm

Hierarchical Stochastic Graphlet Embedding for Graph-based Pattern Recognition [article]

Anjan Dutta, Pau Riba, Josep Lladós, Alicia Fornés
2018 arXiv   pre-print
In what follows, the coarse-to-fine structure of a graph hierarchy and the statistics fetched through the distribution of low to high order stochastic graphlets complements each other and include important  ...  The hierarchical structure is constructed by topologically clustering the graph nodes, and considering each cluster as a node in the upper hierarchical level.  ...  [9] , DE stands for the dissimilarity embedding [5] , NAS indicates the node attribute statistics [6] , GED denotes to the approximated graph edit distance [69] , SGE corresponds to the Stochastic  ... 
arXiv:1807.02839v1 fatcat:rvjmu4jdkrbh7fvd3dylexy5le

GraphFederator: Federated Visual Analysis for Multi-party Graphs [article]

Dongming Han, Wei Chen, Rusheng Pan, Yijing Liu, Jiehui Zhou, Ying Xu, Tianye Zhang, Changjie Fan, Jianrong Tao, Xiaolong Zhang
2020 arXiv   pre-print
This paper presents GraphFederator, a novel approach to construct joint representations of multi-party graphs and supports privacy-preserving visual analysis of graphs.  ...  Specifically, we propose a federated graph representation model (FGRM) that is learned from encrypted characteristics of multi-party graphs in local modules.  ...  The graph representation of each local graph is computed based on three components (R2, R3): the embedding component, the structure component, and the attribute component.  ... 
arXiv:2008.11989v1 fatcat:oolbkzck6fhsneozw44xznve5m

Improving Fuzzy Multilevel Graph Embedding through Feature Selection Technique [chapter]

Muhammad Muzzamil Luqman, Jean Yves Ramel, Josep Lladós
2012 Lecture Notes in Computer Science  
In this paper we take forward our work on explicit graph embedding and present an improvement to our earlier proposed method, named "fuzzy multilevel graph embedding -FMGE", through feature selection technique  ...  The embedding of graphs into numeric vector spaces permits them to access the state-of-the-art computational efficient statistical models and tools.  ...  i.e. an implicit clustering is achieved [12] .  ... 
doi:10.1007/978-3-642-34166-3_27 fatcat:zxl3fcf775c2hm23vurc3yfqd4

CAGNN: Cluster-Aware Graph Neural Networks for Unsupervised Graph Representation Learning [article]

Yanqiao Zhu and Yichen Xu and Feng Yu and Shu Wu and Liang Wang
2020 arXiv   pre-print
Unsupervised graph representation learning aims to learn low-dimensional node embeddings without supervision while preserving graph topological structures and node attributive features.  ...  We further refine the graph topology by strengthening intra-class edges and reducing node connections between different classes based on cluster labels, which better preserves cluster structures in the  ...  Through the topology refining procedure that is based on cluster labels, our proposed CAGNN may accidentally remove informative edges, which results in performance loss.  ... 
arXiv:2009.01674v1 fatcat:3wihohgjzrbmpba3jgnoevedii
« Previous Showing results 1 — 15 out of 55,248 results