Filters








502 Hits in 6.3 sec

Compressive Spectral Clustering [article]

Nicolas Tremblay, Gilles Puy, Remi Gribonval, Pierre Vandergheynst
2016 arXiv   pre-print
It comprises three main steps: create a similarity graph between N objects to cluster, compute the first k eigenvectors of its Laplacian matrix to define a feature vector for each object, and run k-means  ...  We propose to speed up the last two steps based on recent results in the emerging field of graph signal processing: graph filtering of random signals, and random sampling of bandlimited graph signals.  ...  to cluster j, useful for fuzzy partitioning.  ... 
arXiv:1602.02018v2 fatcat:ssosu6vnubcllesebycayxfxfe

RGCNN: Regularized Graph CNN for Point Cloud Segmentation [article]

Gusi Te, Wei Hu, Zongming Guo, Amin Zheng
2018 arXiv   pre-print
In particular, we update the graph Laplacian matrix that describes the connectivity of features in each layer according to the corresponding learned features, which adaptively captures the structure of  ...  Further, we deploy a graph-signal smoothness prior in the loss function, thus regularizing the learning process.  ...  Features of high quality can greatly improve the learning efficiency. • Segmentation based on clustering: Clustering groups (3D) points into clusters based on attributes or features.  ... 
arXiv:1806.02952v1 fatcat:fdxhxw3eivcdrlgg2c74a425ua

Novel modelling of clustering for enhanced classification performance on gene expression data

Sudha V., Girijamma H. A.
2020 International Journal of Electrical and Computer Engineering (IJECE)  
The study outcome shows that proposed system offers comparatively better accuracy and reduced computational complexity with the existing clustering approaches.  ...  Therefore, the proposed manuscript introduces a novel and simplified model capable using Graph Fourier Transform, Eigen Value and vector for offering better classification performance considering case  ...  [22] has used Laplacian regularization process in order to optimize the clustering performance.  ... 
doi:10.11591/ijece.v10i2.pp2060-2068 fatcat:2f4eugmnnnctlhtkfp6wrpbk6y

Feature selection and feature learning for high-dimensional batch reinforcement learning: A survey

De-Rong Liu, Hong-Liang Li, Ding Wang
2015 International Journal of Automation and Computing  
The batch RL algorithms with handcrafted feature representations work well for low-dimensional MDPs.  ...  To cope with high-dimensional RL problems, the desire to obtain data-driven features has led to a lot of works in incorporating feature selection and feature learning into traditional batch RL algorithms  ...  [75] presented a clustering-based (K-means clustering or fuzzy C-means clustering) graph Laplacian framework for automatic learning of features in MDPs with continuous state spaces.  ... 
doi:10.1007/s11633-015-0893-y fatcat:53wepnwplfgtjkqlt2j4q2dtuy

Clustering on Multiple Incomplete Datasets via Collective Kernel Learning [article]

Weixiang Shao University of Illinois at Chicago)
2016 arXiv   pre-print
Furthermore, a clustering algorithm is proposed based on the kernel matrix. The experiments on both synthetic and real datasets demonstrate the effectiveness of the proposed approach.  ...  Multiple datasets containing different types of features may be available for a given task. For instance, users' profiles can be used to group users for recommendation systems.  ...  The following feature spaces (datasets) with different vector-based features is available for the numbers: (1) 76 Fourier coefficients of the character shapes, (2) 216 profile correlations, (3) 240 pixel  ... 
arXiv:1310.1177v2 fatcat:3o4ytcr5tbhmdagegi3dy43kwm

Trends in extreme learning machines: A review

Gao Huang, Guang-Bin Huang, Shiji Song, Keyou You
2015 Neural Networks  
Apart from classification and regression, ELM has recently been extended for clustering, feature selection, representational learning and many other learning tasks.  ...  In this review, we try to provide a comprehensive view of these advances in ELM together with its future perspectives.  ...  Recht (2007, 2008a ) provided a theoretical analysis on random Fourier features-one of ELM random feature mappings, and show that the inner product of transformed data can uniformly approximate those of  ... 
doi:10.1016/j.neunet.2014.10.001 pmid:25462632 fatcat:q3omxuofbfbtbfdq2ls324fddy

Hybrid Approach of Relation Network and Localized Graph Convolutional Filtering for Breast Cancer Subtype Classification [article]

Sungmin Rhee, Seokjun Seo, Sun Kim
2018 arXiv   pre-print
Recently, graph based deep learning techniques have emerged, which becomes an opportunity to leverage analyses in network biology.  ...  On the other hand, network biology requires in-depth knowledge to construct disease-specific networks, but our current knowledge is very limited even with the recent advances in human cancer biology.  ...  We clustered the patients into two groups based on raw gene expression values and feature map data at the last graph convolution layer with dimensions reduced.  ... 
arXiv:1711.05859v3 fatcat:xclwqibjn5bpdp4sujzksa7ssu

Network Representation Learning: From Traditional Feature Learning to Deep Learning

Ke Sun, Lei Wang, Bo Xu, Wenhong Zhao, Shyh Wei Teng, Feng Xia
2020 IEEE Access  
Actually, the unbiased random walk strategy of DeepWalk is a special case of node2vec with p = 1 and q = 1.  ...  In general, graph-Laplacian [45] is often combined with PCA methods [46] - [48] for feature extraction in the area of bioinformatics.  ... 
doi:10.1109/access.2020.3037118 fatcat:kca6htfarjdjpmtwcvbsppfzui

Deep Learning on Graphs: A Survey [article]

Ziwei Zhang, Peng Cui, Wenwu Zhu
2020 arXiv   pre-print
We divide the existing methods into five categories based on their model architectures and training strategies: graph recurrent neural networks, graph convolutional networks, graph autoencoders, graph  ...  In this way, the raw features can be associated with some random walk probability of the graph [109] .  ...  [70] first analyzed the performance of GCNs by using a special form of Laplacian smoothing, which makes the features of nodes in the same cluster similar.  ... 
arXiv:1812.04202v3 fatcat:uefgy4gnrnhztbbsgrio7dvdqu

LFGCN: Levitating over Graphs with Levy Flights

Yuzhou Chen, Yulia R. Gel, Konstantin Avrachenkov
2020 2020 IEEE International Conference on Data Mining (ICDM)  
Furthermore, we propose a new preferential P-DropEdge method based on the Girvan-Newman argument.  ...  Our experimental results on semi-supervised node classification tasks demonstrate that the LFGCN coupled with P-DropEdge accelerates the training task, increases stability and further improves predictive  ...  of feature maps with neurons.  ... 
doi:10.1109/icdm50108.2020.00109 fatcat:w3a5hjigs5cdjio37bdo6phx7m

Study on a Novel Data Classification Method Based on Improved GA and SVM Model

Jing Huo, Yuxiang Zhao
2016 International Journal of Smart Home  
Li et al.[21] proposed a novel SVM classification approach based on the random selection and de-clustering technique for large data sets.  ...  The first proposed algorithm is based on modifying the OC-SVM kernel by modeling the data marginal distribution with the graph Laplacian built with both labeled and unlabeled samples.  ...  The program for the study, initialization, training, and simulation of the proposed algorithm in this article was written with the tool-box of MATLAB 2010b produced by the Math-Works.  ... 
doi:10.14257/ijsh.2016.10.5.12 fatcat:syos6hsgyfhwjjy22okuutn4mq

LFGCN: Levitating over Graphs with Levy Flights [article]

Yuzhou Chen, Yulia R. Gel, Konstantin Avrachenkov
2020 arXiv   pre-print
Furthermore, we propose a new preferential P-DropEdge method based on the Girvan-Newman argument.  ...  Our experimental results on semi-supervised node classification tasks demonstrate that the LFGCN coupled with P-DropEdge accelerates the training task, increases stability and further improves predictive  ...  of feature maps with neurons.  ... 
arXiv:2009.02365v1 fatcat:6c36zbf3pzaz3aywc3udq557ma

A survey and evaluation of promising approaches for automatic image-based defect detection of bridge structures

Mohammad R. Jahanshahi, Jonathan S. Kelly, Sami F. Masri, Gaurav S. Sukhatme
2009 Structure and Infrastructure Engineering  
., Masri, Sami F. and Sukhatme, Gaurav S. (2009) 'A survey and evaluation of promising approaches for automatic image-based defect detection of bridge structures',Structure and Infrastructure Engineering  ...  Area-based methodsArea-based methods emphasise feature matching, and are less concerned with feature detection.  ...  Within-clustering distance D k can be defined, as indicated by Equation (9) , where d(m i ,X j ) represents the distance between the mean vector of the i th cluster and feature vector X j : D k ¼ 1 P  ... 
doi:10.1080/15732470801945930 fatcat:r3ue7bsj65cnhhu2wu7hsypp74

Locality-Sensitive Hashing Techniques for Nearest Neighbor Search

Keon Myung Lee
2012 International Journal of Fuzzy Logic and Intelligent Systems  
It categories them based on several criteria, presents their characteristics, and compares their performance.  ...  It uses the random Fourier features and thresholds the values to get binary codes for data.  ...  It efficiently performs spectral clustering to get hash codes because it enables to compute the graph Laplacian eigenvectors of the original data set from the graph Laplacian eigenvectors of the anchar  ... 
doi:10.5391/ijfis.2012.12.4.300 fatcat:qwkw27hpd5ht5jhzwfgcajyfs4

A Survey on Image Analysis based on Texture

Suresha M, Harisha Naik T
2017 International Journal of Advanced Research in Computer Science and Software Engineering  
Texture description methods are categorized in to statistical, geometrical, model based, region based and transform based methods.  ...  For the datasets, Brodatz and SIPI texture dataset is the most popularly used dataset despite it being old and with limited samples, other datasets are less used.  ...  A pair wise affinity function [35] for spectral clustering based on a measure of texture features represented by Gaussian Markov Random Field (GMRF) model.  ... 
doi:10.23956/ijarcsse/v7i6/0324 fatcat:632gxfogojejrhuhwvl27rjwc4
« Previous Showing results 1 — 15 out of 502 results