Global ETD Search
Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.
Results
Showing 1 to 20 of 35 for “"Spectral Embedding"”.
-
Foundations of Adjacency Spectral Embedding
… in finite dimensional Euclidean space. This embedding allows the full arsenal of statistical and machine learning methodology for multivariate Euclidean data to be deployed for graph inference. Our work analyzes this embedding, a graph version of principal component analysis, in the context …
-
Adjacency spectral embedding beyond unweighted, undirected networks
… considers the statistical analysis of adjacency spectral embedding beyond these standard networks. By embedding the nodes of these networks into low dimensional space in a consistent and meaningful manner, it is possible to make better inferences from the embedded data. This thesis extends the …
-
Spectral embedding of large graphs and dynamic networks
… dependencies between entities, often begins with embedding: the process of mapping these entities into a low-dimensional vector space in a way which preserves salient information present in the data. Spectral embedding is a family of embedding algorithms in which representations are obtained using …
-
Joint spectral embeddings of random dot product graphs
… only permits a single relationship type. Joint spectral embedding methods facilitate analysis of multiplex network data by simultaneously mapping vertices in each network to points in Euclidean space, entitled node embeddings, where statistical inference is then performed. This mapping is …
-
Spectral embeddings through nonstandard samplings
The Spectral Embedding Theorem, one of the formulations of the Spectral Theorem, states that any densely-defined symmetric operator A on a separable Hilbert space H can be extended by a multiplication operator through an isometric embedding of H in an L_2-space. In this research project, the goal …
-
Robust and scalable unsupervised learning via landmark diffusion, from theory to medical application
… by such challenging task, we proposed a novel spectral embedding algorithm, which we coined Robust and Scalable Embedding via Landmark Diffusion (ROSELAND). The solution is a generic and not limited to analyze physiological waveforms. In short, we measure the affinity between two points via a …
-
NETWORK ALIGNMENT AND STRUCTURED SIGNALS IN RANDOM GRAPHS
… structure detection, and multi-graph analysis. Spectral embedding has become a central tool for statistical network analysis due to its efficiency and versatility in tasks such as com- munity detection, anomaly detection, and graph comparison. However, challenges such as vertex misalignment …
-
Graph-Based Acoustic Clustering and Classification
… processing and problems on networks, we apply a spectral embedding to project the high-dimensional graph data onto a low-dimensional subspace. We show how the Nyström extension can accelerate the calculation of the eigenvectors of the graph Laplacian, and how to adapt the method to accommodate …
-
STATISTICAL INFERENCE ON STRUCTURED HIGH-DIMENSIONAL MODELS USING LIKELIHOOD-BASED METHODS
… structured high-dimensional models is based on spectral methods, such as spectral clustering for stochastic block models, or penalized spectral methods, such as sparse principal component analysis. In contrast, likelihood- based methods for such non-classical statistical models are relatively …
-
Robust Path-based Image Segmentation Using Superpixel Denoising
… similar characteristics, with one category being spectral clustering where data points are represented as vertices of a graph connected by weighted edges signifying similarity based on distance. The longest leg path distance (LLPD) has shown promise when used in spectral clustering, but is …
-
Vertex Classification on Weighted Networks
… of classification techniques using the spectral embedding of the unweighted adjacency matrix. In this paper we look at two settings for the edge weight distributions and propose classification procedures in both settings. We show the effectiveness of the proposed classifiers by comparing …
-
Two-Sample Hypothesis Testing for Random Graphs
… inference. Currently, methods such as adjacency spectral embedding (ASE) are used to create test statistics for random graphs. The first chapter of our study presents non-metric multidimensional scaling as an alternative to ASE. We show our procedure is functional for both simulated data and for …
-
Learning strictly orthogonal p-order nonnegative Laplacian embedding via smoothed iterative reweighted method
Laplacian embedding is a powerful graph based method with its ability in spectral clustering to reveal the intrinsic geometry of data in the high dimensional space. Imposing the orthogonality and the nonnegativity constraints can avoid degenerate and negative solutions, respectively. These two …
-
Statistical Analysis and Spectral Methods for Signal-Plus-Noise Matrix Models
… investigate the asymptotic relationship between spectral embedding performance and underlying network structure for stochastic block model graphs.
-
Learning with Multiple Similarities
… In particular, I propose two models for learning spectral embedding from multiple similarity graphs using ideas from co-training and co-regularization. Further, I propose a novel approach to the problem of multiple kernel learning (MKL), converting it to a more familiar problem of binary …
-
Graph Representation Learning with Motif Structures
… along three directions: (1) a method to learn a spectral embedding space with both edge-based and triangle-based structures for clustering nodes; (2) a graph transformer by unifying homophily and heterophily representation for role classification and motif structure completion; (3) a method to …
-
Dynamics and Uncertainty in Networks and Web Data
… this thesis uses Unfolded Adjacency Spectral Embedding, a novel method that enables comparisons of network embeddings across both space and time, to analyse directed, weighted yearly networks of commercial website hyperlink connections between geographic areas. A robust and scalable …
-
Simultaneous Dimensionality and Complexity Model Selection for Spectral Graph Clustering
… Among various vertex clustering approaches, spectral clustering is one of the most popular clustering methods because it is easy to implement while it often outperforms traditional clustering algorithms. However, there are two inherent model selection problems in spectral clustering, namely …
-
Spectral Techniques for Heterogeneous Social Networks
… connecting the layers to produce a consistent spectral embedding. This embedding can be used to compute social network properties of graphs of different types, to predict edges, edge types, and edge direction, as well as to track the change of role over time. I illustrate the approaches using …
Page 1 of 2