Filters








19,697 Hits in 5.1 sec

Graph Random Neural Network for Semi-Supervised Learning on Graphs [article]

Wenzheng Feng, Jie Zhang, Yuxiao Dong, Yu Han, Huanbo Luan, Qian Xu, Qiang Yang, Evgeny Kharlamov, Jie Tang
2021 arXiv   pre-print
We study the problem of semi-supervised learning on graphs, for which graph neural networks (GNNs) have been extensively explored.  ...  In this paper, we propose a simple yet effective framework -- GRAPH RANDOM NEURAL NETWORKS (GRAND) -- to address these issues.  ...  GRAPH RANDOM NEURAL NETWORKS We present the GRAPH RANDOM NEURAL NETWORKS (GRAND) for semi-supervised learning on graphs, as illustrated in Figure 1 .  ... 
arXiv:2005.11079v4 fatcat:jvxmfcpvsfcadniu3kfqt6jgia

Directed hypergraph neural network [article]

Loc Hoang Tran, Linh Hoang Tran
2022 arXiv   pre-print
Among the classic directed graph based semi-supervised learning method, the novel directed hypergraph based semi-supervised learning method, the novel directed hypergraph neural network method that are  ...  However, data scientists just have concentrated primarily on developing deep neural network method for un-directed graph.  ...  based semi-supervised learning Directed graph neural network F-directed hypergraph neural network B-directed hypergraph neural network  ... 
arXiv:2008.03626v2 fatcat:uyk2zndaqvarbbrbldny2t7vee

Semi-Supervised Classification with Graph Convolutional Networks [article]

Thomas N. Kipf, Max Welling
2017 arXiv   pre-print
We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs.  ...  In a number of experiments on citation networks and on a knowledge graph dataset we demonstrate that our approach outperforms related methods by a significant margin.  ...  ACKNOWLEDGMENTS We would like to thank Christos Louizos, Taco Cohen, Joan Bruna, Zhilin Yang, Dave Herman, Pramod Sinha and Abdul-Saboor Sheikh for helpful discussions.  ... 
arXiv:1609.02907v4 fatcat:pt7vcc7b5vecflnsu4xdigvceq

Application of three graph Laplacian based semisupervised learning methods to protein function prediction problem

Loc Tran
2013 International Journal on Bioinformatics & Biosciences  
In this paper, the un-normalized, symmetric normalized, and random walk graph Laplacian based semi-supervised learning methods will be applied to the integrated network combined from multiple networks  ...  Moreover, the accuracy performance measures of these three semi-supervised learning methods for integrated network are much better than the best accuracy performance measures of these three methods for  ...  the published) and normalized graph Laplacian based semi-supervised learning methods slightly perform better than the random walk graph Laplacian based semi-supervised learning method using network ( )  ... 
doi:10.5121/ijbb.2013.3202 fatcat:pta7isryl5asnh6lboeoq44y7a

A Flexible Generative Framework for Graph-based Semi-supervised Learning [article]

Jiaqi Ma, Weijing Tang, Ji Zhu, Qiaozhu Mei
2019 arXiv   pre-print
Relational information among the data samples, often encoded in the graph/network structure, is shown to be helpful for these semi-supervised learning tasks.  ...  We conduct thorough experiments on benchmark datasets for graph-based semi-supervised learning. Results show that the proposed methods outperform the state-of-the-art models in most settings.  ...  Graph Neural Networks for Semi-supervised Learning Another class of methods that have gained great attention recently are the graph neural networks [10, 5, 21] .  ... 
arXiv:1905.10769v2 fatcat:mtooywzivfevricftsdcjr56ke

Hypergraph based semi-supervised learning algorithms applied to speech recognition problem: a novel approach [article]

Loc Hoang Tran, Trang Hoang, Bui Hoang Nam Huynh
2018 arXiv   pre-print
Hidden Markov Model method (the current state of the art method applied to speech recognition problem) and graph based semi-supervised learning methods (i.e. the current state of the art network-based  ...  Thus, in this paper, the three un-normalized, random walk, and symmetric normalized hypergraph Laplacian based semi-supervised learning methods applied to hypergraph constructed from the feature data of  ...  This work is funded by the Ministry of Science and Technology, State-level key program, Research for application and development of information technology and communications, code KC.01.23/11-15.  ... 
arXiv:1810.12743v1 fatcat:whavzea7fjgtfknja4ctzhuism

Noise-robust classification with hypergraph neural network

Nguyen Trinh Vu Dang, Loc Tran, Linh Tran
2021 Indonesian Journal of Electrical Engineering and Computer Science  
Then, the classic graph based semisupervised learning method, the classic hypergraph based semi-supervised learning method, the graph neural network, the hypergraph neural network, and our proposed hypergraph  ...  Moreover, the hypergraph neural network methods are at least as good as the graph neural network.</p>  ...  . c) Compare the accuracy performance measures of the classic graph based semi-supervised learning problem, the classic hypergraph based semi-supervised learning problem, the graph neural network method  ... 
doi:10.11591/ijeecs.v21.i3.pp1465-1473 fatcat:iz7g63by3vgofnrj6gocz5b4zy

Hypergraph and protein function prediction with gene expression data [article]

Loc Tran
2012 arXiv   pre-print
Thus, in this paper, the three un-normalized, random walk, and symmetric normalized hypergraph Laplacian based semi-supervised learning methods applied to hypergraph constructed from the gene expression  ...  However, their average accuracy performance measures of these three methods are much greater than the average accuracy performance measures of un-normalized graph Laplacian based semi-supervised learning  ...  full topology of the network, the Artificial Neural Networks, Support Vector Machine, unnormalized, symmetric normalized and random walk graph Laplacian based semi-supervised learning method utilizes  ... 
arXiv:1212.0388v1 fatcat:sf2aopcbpbcptdfughqvbyqnei

Convolutional Neural Networks On Graphs With Fast Localized Spectral Filtering (Smld'16)

Michaël Defferrard
2016 Zenodo  
Presentation given at the Swiss Machine Learning Day (SMLD) (https://www.idiap.ch/workshop/smld2016).  ...  ConvNets & Graphs ConvNets on Graphs Numerical Experiments MNIST 20NEWS Application: Semi-supervised learning Application: Recurrent Neural Nets Table: Accuracies of the proposed graph CNN  ...  64.64 FC2500-FC500 65.76 GC32 68.26 ConvNets & Graphs ConvNets on Graphs Numerical Experiments MNIST 20NEWS Application: Semi-supervised learning Application: Recurrent Neural Nets Graph  ... 
doi:10.5281/zenodo.1318411 fatcat:vgrdipopw5h5zcmngwjxzhhv2q

A Generative Bayesian Graph Attention Network for Semi-Supervised Classification on Scarce Data

Zhongtian Sun, Anoushka Harit, Jialin Yu, Alexandra I. Cristea, Noura Al Moubayed
2021 2021 International Joint Conference on Neural Networks (IJCNN)  
This research focuses on semi-supervised classification tasks, specifically for graph-structured data under datascarce situations.  ...  The proposed method is comprehensively evaluated on three graph-based deep learning benchmark data sets.  ...  Extensive graph neural network (GNN) based models, including graph convolution networks (GCNs) [3] and graph attention networks (GATs) [4] have been developed for unsupervised, semi-supervised and  ... 
doi:10.1109/ijcnn52387.2021.9533981 fatcat:r7bssnui4vgkpnt2jqzvcuspiy

Few-Shot Learning with Graph Neural Networks [article]

Victor Garcia, Joan Bruna
2018 arXiv   pre-print
Besides providing improved numerical performance, our framework is easily extended to variants of few-shot learning, such as semi-supervised or active learning, demonstrating the ability of graph-based  ...  By assimilating generic message-passing inference algorithms with their neural-network counterparts, we define a graph neural network architecture that generalizes several of the recently proposed few-shot  ...  ACKNOWLEDGMENTS This work was partly supported by Samsung Electronics (Improving Deep Learning using Latent Structure).  ... 
arXiv:1711.04043v3 fatcat:3fd7knhjorhrncf4h3dwuwwoby

SLGAT: Soft Labels Guided Graph Attention Networks [chapter]

Yubin Wang, Zhenyu Zhang, Tingwen Liu, Li Guo
2020 Lecture Notes in Computer Science  
Graph convolutional neural networks have been widely studied for semi-supervised classification on graph-structured data in recent years.  ...  Experimental results on semi-supervised node classification show that SLGAT achieves state-of-the-art performance.  ...  Related Work Graph-Based Semi-supervised Learning.  ... 
doi:10.1007/978-3-030-47426-3_40 fatcat:627gi5flknavfjs5tucadoxf3y

Non-iterative approaches in training feed-forward neural networks and their applications

Xizhao Wang, Weipeng Cao
2018 Soft Computing - A Fusion of Foundations, Methodologies and Applications  
Keywords Non-iterative approaches · Feed-forward neural networks · Neural networks with random weights · Deep learning  ...  Focusing on non-iterative approaches in training feed-forward neural networks, this special issue includes 12 papers to share the latest progress, current challenges, and potential applications of this  ...  Antonio Di Nola, the Editor-in-Chief of Soft Computing, for his support to edit this special issue.  ... 
doi:10.1007/s00500-018-3203-0 fatcat:snmmbo3ys5a2plmpsyxowzye6a

Semi-Supervised Node Classification by Graph Convolutional Networks and Extracted Side Information [article]

Mohammad Esmaeili, Aria Nosratinia
2020 arXiv   pre-print
From this perspective, this paper revisits the node classification task in a semi-supervised scenario by graph convolutional networks (GCNs).  ...  For both cases, the experiments on synthetic and real-world datasets demonstrate that the proposed model achieves a higher prediction accuracy in comparison to the existing state-of-the-art methods for  ...  ] , graph attention networks [2] , a variant of attention-based graph neural network for semi-supervised learning [17] , and dual graph convolutional networks [18] .  ... 
arXiv:2009.13734v2 fatcat:tqk3kcb2abhc3igulyavifxuvi

Semisupervised Learning on Heterogeneous Graphs and its Applications to Facebook News Feed [article]

Cheng Ju, James Li, Bram Wasti, Shengbo Guo
2018 arXiv   pre-print
Graph-based semi-supervised learning is a fundamental machine learning problem, and has been well studied. Most studies focus on homogeneous networks (e.g. citation network, friend network).  ...  In the present paper, we propose the Heterogeneous Embedding Label Propagation (HELP) algorithm, a graph-based semi-supervised deep learning algorithm, for graphs that are characterized by heterogeneous  ...  Graph-based Semi-supervised Learning Graph-based semi-supervised learning is widely used in network analysis, for prediction/clustering tasks over nodes and edges.  ... 
arXiv:1805.07479v2 fatcat:a6fcag6nszft7d2hpmash2b2ni
« Previous Showing results 1 — 15 out of 19,697 results