Results 1 - 10 of 146

Learning Convolutional Neural Networks for Graphs

by Mathias Niepert , Mohamed Ahmed , Konstantin Kutzkov , Konstantin Kutzkov@neclab , Eu
"... Abstract Numerous important problems can be framed as learning from graph data. We propose a framework for learning convolutional neural networks for arbitrary graphs. These graphs may be undirected, directed, and with both discrete and continuous node and edge attributes. Analogous to image-based ..."
Abstract - Add to MetaCart
-based convolutional networks that operate on locally connected regions of the input, we present a general approach to extracting locally connected regions from graphs. Using established benchmark data sets, we demonstrate that the learned feature representations are competitive with state of the art graph kernels

A Local Spectral Method for Graphs: With Applications to Improving Graph Partitions and Exploring Data Graphs Locally

by Michael W. Mahoney, Lorenzo Orecchia, Nisheeth K. Vishnoi, C○ Michael W. Mahoney, Lorenzo Orecchia, Nisheeth K. Vishnoi Mahoney
"... The second eigenvalue of the Laplacian matrix and its associated eigenvector are fundamental features of an undirected graph, and as such they have found widespread use in scientific computing, machine learning, and data analysis. In many applications, however, graphs that arise have several local r ..."
Abstract - Cited by 13 (5 self) - Add to MetaCart
The second eigenvalue of the Laplacian matrix and its associated eigenvector are fundamental features of an undirected graph, and as such they have found widespread use in scientific computing, machine learning, and data analysis. In many applications, however, graphs that arise have several local

Local and Global Discriminative Learning for Unsupervised Feature Selection

by unknown authors
"... Abstract—In this paper, we consider the problem of feature selection in unsupervised learning scenario. Recently, spectral feature selection methods, which leverage both the graph Laplacian and the learning mechanism, have received consid-erable attention. However, when there are lots of irrelevant ..."
Abstract - Add to MetaCart
or noisy features, such graphs may not be reliable and then mislead the selection of features. In this paper, we propose the Local and Global Discriminative learning for unsupervised Feature Selection (LGDFS), which integrates a global and a set of locally linear regression model with weighted 2-norm

Local and Global Discriminative Learning for Unsupervised Feature Selection

by unknown authors
"... Abstract—In this paper, we consider the problem of feature selection in unsupervised learning scenario. Recently, spectral feature selection methods, which leverage both the graph Laplacian and the learning mechanism, have received consid-erable attention. However, when there are lots of irrelevant ..."
Abstract - Add to MetaCart
or noisy features, such graphs may not be reliable and then mislead the selection of features. In this paper, we propose the Local and Global Discriminative learning for unsupervised Feature Selection (LGDFS), which integrates a global and a set of locally linear regression model with weighted 2-norm

Variational Graph Embedding for Globally and Locally Consistent Feature Extraction

by Shuang-hong Yang, Hongyuan Zha, S. Kevinzhou, Bao-gang Hu
"... Abstract. Existing feature extraction methods explore either global statistical or local geometric information underlying the data. In this paper, we propose a general framework to learn features that account for both types of information based on variational optimization of nonparametric learning c ..."
Abstract - Cited by 3 (2 self) - Add to MetaCart
embeds this graph by spectral analysis. The resulting feature learner has several appealing properties such as maximum discrimination, maximum-relevanceminimum-redundancy and locality-preserving. Experiments on benchmark face recognition data sets confirm the effectiveness of our proposed algorithms. 1

Non-Rigid Motion Behaviour Learning: A Spectral and Graphical Approach

by Hongfang Wang , 2007
"... In this thesis graph spectral methods and kernel methods are combined together for the tasks of rigid and non-rigid feature correspondence matching and consis-tent labelling. The thesis is divided into five chapters. In Chapter 1 we give a brief introduction and an outline of the thesis. In Chapter ..."
Abstract - Add to MetaCart
algo-rithm for rigid and articulated motion. We focus on the point features extracted from consecutive image frames. Specifically, a graph structure is used to rep-resent the data-sets, and spectral graph theory is used for the correspondence localization. The novelty is that a kernel viewpoint

Textons, contours and regions: Cue integration in image segmentation

by Jitendra Malik, Serge Belongie, Jianbo Shi, Thomas Leung - In International Conference on Computer Vision , 1999
"... This paper makes two contributions. It provides (1) an operational definition of textons, the putative elementary units of texture perception, and (2) an algorithm for partitioning the image into disjoint regions of coherent brightness and texture, where boundaries of regions are defined by peaks in ..."
Abstract - Cited by 111 (8 self) - Add to MetaCart
of oriented linear filter outputs. These can be learned using a K-means approach. By mapping each pixel to its nearest texton, the image can be analyzed into texton channels, each of which is a point set where discrete techniques such as Voronoi diagrams become applicable. Local histograms of texton

Robust Face Recognition through Local Graph Matching

by Ehsan Fazl-ersi, John S. Zelek, John K. Tsotsos - JOURNAL OF COMPUTERS , 2007
"... A novel face recognition method is proposed, in which face images are represented by a set of local labeled graphs, each containing information about the appearance and geometry of a 3-tuple of face feature points, extracted using Local Feature Analysis (LFA) technique. Our method automatically le ..."
Abstract - Cited by 4 (1 self) - Add to MetaCart
A novel face recognition method is proposed, in which face images are represented by a set of local labeled graphs, each containing information about the appearance and geometry of a 3-tuple of face feature points, extracted using Local Feature Analysis (LFA) technique. Our method automatically

Spectral Regression Subspace learning Machine learning Image classification

by Liyuan Li N, Weixun Goh, Joo Hwee Lim, Sinno Jialin Pan, Scene Recognition , 2014
"... Computer vision a b s t r a c t This paper proposes a novel method based on Spectral Regression (SR) for efficient scene recognition. First, a new SR approach, called Extended Spectral Regression (ESR), is proposed to perform manifold learning on a huge number of data samples. Then, an efficient Bag ..."
Abstract - Add to MetaCart
-level feature samples in a training set. It prohibits direct application of SR to perform manifold learning on such dataset. In ESR, we first group the samples into tiny clusters, and then devise an approach to reduce the size of the similarity matrix for graph learning. In this way, the subspace learning

Learning with Spectral Kernels and Heavy-Tailed Data

by Michael W. Mahoney
"... Heavy-tailed data, e.g., graphs in which the degree sequence decays according to a power law, are ubiquitous in applications. In many of those applications, spectral kernels, e.g., Laplacian Eigenmaps and Diffusion Maps, are commonly-used analytic tools. We establish learnability results applicable ..."
Abstract - Add to MetaCart
in both settings. Our first result is an exact learning bound for learning a classification hyperplane when the components of the feature vector decay according to a power law. Thus, although the distribution of data is infinite dimensional and unbounded, a nearly optimal linear classification hyperplane
Results 1 - 10 of 146