The paper analyzes the Spectral Method for clustering data points on Union of Subspaces.
problem Clustering data points on Union of Subspaces.
method Constructing a Random Geometry Graph (Subspace Clustering) and analyzing it using spectral methods.
result Established a theory to analyze the Spectral Method's efficiency on Union of Subspaces.
The aim of the present article is to give an overview of spectral theory on metric graphs guided by spectral geometry on discrete graphs and manifolds. We present the basic concept of metric graphs and natural Laplacians acting on it and explicitly allow infinite graphs. Motivated by the general form of a Laplacian on …
Root Laplacian Eigenmaps help in spectral embedding of graphs.
problem Efficient spectral embedding of graphs.
method Square root of graph-Laplacian operator.
result Improved spectral embedding techniques.
This study bridges the gap between spatial and spectral GNNs.
problem Lack of direct comparison and cross-reference of existing GNNs.
method Systematically categorizes and examines GNNs into spatial and spectral domains.
result Establishes a strong relationship between spatial and spectral GNNs.
Enhances GCNs to resist graph attacks.
problem Vulnerability of GCNs to topological attacks.
method Introduces a new robust convolution operator and training paradigm.
result Improves adversarial robustness and performance.
Developed a framework for designing filters in spectral GCNNs with improved performance.
problem Designing effective filters for spectral GCNNs with regularization properties.
method Exploring regularization properties of graph Laplacian and proposing a generalized framework for filter design.
result New filters derived from the framework outperform state-of-the-art techniques in semi-supervised node classification.
Method detects coherent structures from sparse flow data using graph theory.
problem Detecting coherent structures from sparse flow data.
method Graph coloring and spectral graph drawing algorithms applied to kinematic dissimilarity of trajectories.
result Robustly detects coherent structures using significantly less data than existing methods.
Spectral embedding improves with edge weight transformations.
problem Improving spectral embedding for weighted networks.
method Analyzed edge weight transformations for spectral embedding quality.
result Transformations like tempering or thresholding can significantly enhance spectral embedding.
The goal of this paper is to show that there exists a simple, yet universal statistical logic of spectral graph analysis by recasting it into a nonparametric function estimation problem. The prescribed viewpoint appears to be good enough to accommodate most of the existing spectral graph techniques as a consequence of …
Optimizing quantum graphs yields geodesic nets on surfaces.
problem Finding optimal quantum graphs for geodesic nets.
method Optimizing functionals from spectral theory to find geodesic nets.
result Critical metrics for eigenvalues give rise to geodesic nets.
The paper defines surface area for graphs and derives spectral estimates.
problem Understanding connectivity measures and spectral properties of graphs.
method Introducing surface area concepts related to inverse degree and deriving spectral bounds.
result An upper bound on the second eigenvalue for planar graphs.
Novel Haar-Laplacian for directed graphs enhances spectral graph applications.
problem Lack of suitable Laplacian for directed graphs in spectral graph theory.
method Inspired by Haar-like transformation, introduces a Hermitian matrix preserving direction and weight.
result HaarNet outperforms in weight prediction and denoising on directed graphs.
Unified framework for analyzing graph neural operators converging to graph limits.
problem Analyzing convergence of graph neural operators to graph limits.
method Develops a unified spectral framework for graph neural operators under various graphon assumptions.
result Unified framework enables direct comparison of convergence rates and tradeoffs.
Method reconstructs missing wind farm data using graph theory and nearest neighbors.
problem Missing data in wind farm records due to sensor failures.
method Combines spectral graph theory and k-Nearest Neighbors to estimate missing data.
result Significant improvement in data reconstruction over existing methods.
The paper improves GNN generalization theory by considering graph manifolds.
problem Improper GNN generalization bounds ignoring graph structures.
method Taking a manifold perspective, the paper establishes GNN generalization theory.
result GNN generalization bounds decrease linearly with graph size and spectral continuity.
New model learns graph spectra accurately, outperforming existing methods.
problem Graph diffusion models struggle to distinguish certain graph families and their spectra.
method Leveraged random matrix theory to analytically extract spectral properties, introducing Dyson Diffusion Model.
result Dyson Diffusion Model learns graph spectra accurately and outperforms existing models.
Researchers calculate spectral dimension of complex networks using renormalization group theory.
problem Understanding diffusion properties in complex systems.
method Renormalization group theory applied to graph Laplacians of simplicial complexes.
result Spectral dimension decreases with randomness in topological structure.
Fiedler regularization uses spectral graph theory to improve neural network performance.
problem Improving neural network performance by penalizing weights based on connectivity.
method Uses the Fiedler value of the neural network's graph as a regularization tool, providing theoretical and computational methods.
result Demonstrates Fiedler regularization's effectiveness in improving neural network performance.
Paper shows spectral filters can transfer between different graphs discretizing the same space.
problem Transferability of spectral filters between different graphs.
method Analysis of spectral filters on graphs discretizing the same space.
result Spectral filters have similar effects on graphs discretizing the same space.
This paper provides theoretical guarantees for spectral clustering using graph cuts.
problem Lack of performance guarantees for spectral clustering.
method Convex relaxation of graph cuts, spectral proximity condition, algebraic connectivity, inter-cluster connectivity.
result Deterministic bounds for successful spectral clustering are derived.
This paper refines understanding of decentralized learning by considering graph topology.
problem Current theory fails to predict performance in decentralized learning settings.
method Quantifies how graph topology influences convergence in decentralized learning.
result Graph topology significantly impacts convergence in decentralized learning, contrary to spectral gap theory.
New method computes dense partial correlations with applications in graph theory and uncertainty quantification.
problem Sparse inverse covariance matrices are popular but dense solutions are overlooked.
method Derives approach based on inverse problem theory.
result New insights and approaches for model selection and data preprocessing.
Graph-based Bayesian learning theory ensures scalable algorithms for large datasets.
problem Consistency and scalability in semi-supervised learning with graphs.
method Introduces new scaling theory for graph parameters and proves uniform spectral gaps for Markov chain Monte Carlo algorithms.
result Graph-based Markov chain Monte Carlo algorithms have a uniform spectral gap independent of unlabeled data size.
Estimates spectral density of large implicit matrices efficiently.
problem Estimating eigenvalues of large implicit matrices efficiently.
method Combines randomized estimation techniques to construct unbiased estimators.
result Validated methods on large-scale problems in graph theory and random matrix theory.
New spectral analysis improves clustering in sparse graphs.
problem Improving classical matrix perturbation results for eigenvectors.
method New perturbation bounds considering the nature of perturbations.
result Simple clustering algorithm recovers communities in sparse graphs.
A novel 3D shape registration method using spectral graph embedding and probabilistic matching.
problem Challenges in 3D shape analysis and registration, especially with large variability.
method Combining spectral graph matching with Laplacian embedding for large graphs, using commute-time embedding and PCA.
result A method to register shapes with different samplings and isometric deformations.
This paper analyzes various graph clustering methods and their applications.
problem Dividing graphs into homogeneous groups for diverse applications.
method Traditional and deep learning-based clustering methods are compared.
result Deep learning techniques improve clustering accuracy.
Developed a new homology theory for graph chromatic polynomials.
problem Categorification of chromatic polynomials.
method Introduced a new homology theory HLee(G) and developed a spectral sequence. result Spectral sequence converges to HLee(G), supporting H∗(G). Proposes a probabilistic framework for stationary topological signals on simplicial complexes.
problem Complex data structures require new models and tools.
method Generalizes stationarity to topological signals on simplicial complexes.
result Defines topological power spectral density (PSD) for stationary signals.
Spectral sparsification improves Laplacian-constrained graph learning.
problem Improving accuracy of Laplacian-constrained graph learning.
method Spectral graph sparsification as a post-estimation operation.
result Improved accuracy of Laplacian-constrained graph learning.
New method clusters evolving networks using spatio-temporal graph Laplacian.
problem Clustering communities in time-varying graphs.
method Extends spectral clustering to dynamic graphs using CCA and spatio-temporal graph Laplacian.
result The spatio-temporal graph Laplacian clearly interprets cluster evolution over time.
Study of spectral properties of graph Laplacians for data clustering.
problem Understanding the spectral gap of graph Laplacians for data clustering.
method Analysis of a three-parameter family of differential operators as the large data limit of graph Laplacians.
result The spectral gap depends on three parameters and the size of the perturbation from perfectly clustered data.
The paper introduces a quantum state system to count perfect matchings in graphs.
problem Counting perfect matchings in graphs using quantum state systems.
method Topological quantum field theory (TQFT) and spectral sequences.
result The filtered n-color vertex homology for n=2 is generated by perfect matchings. Unified framework for structured graph learning from data.
problem Lack of structural knowledge incorporation in graph learning.
method Combining Gaussian graphical models and spectral graph theory, imposing constraints via optimization.
result Provable convergence, computational efficiency, and practical applicability for various graph tasks.
The paper develops a spectral theory for hypergraphs with edge-dependent vertex weights using random walks.
problem Lack of spectral theory for hypergraphs with edge-dependent vertex weights.
method Random walks on hypergraphs with edge-dependent vertex weights, deriving a random walk-based hypergraph Laplacian.
result Random walks on hypergraphs with edge-dependent vertex weights can capture higher-order relationships in data.
Proposes autoencoding with random forests using spectral graph theory.
problem Learning low-dimensional embeddings of random forest models.
method Combines nonparametric statistics and spectral graph theory for optimization.
result Establishes a universal consistent decoder for random forest models.
We study the spectral gap of the Erdős--Rényi random graph through the connectivity threshold. In particular, we show that for any fixed δ>0 if p≥n(1/2+δ)logn, then the normalized graph Laplacian of an Erdős--Rényi graph has all of its nonzero eigenvalues tightly concentrated around 1. We est…
New nonparametric tests for high-dimensional k-sample comparisons.
problem High-dimensional k-sample comparison problems.
method Nonparametric distribution-free tests based on spectral graph theory.
result The tests are effective and have practical applications.
New centrality-based graph shift operators improve graph neural networks.
problem Improving graph neural networks by enhancing graph shift operators.
method Proposed Centrality Graph Shift Operators (CGSOs) using global centrality metrics.
result CGSOs lead to improved performance in graph neural networks on real-world datasets.
Paper explores embedding methods for detecting pseudo-cliques in random graphs, showing limitations and potential.
problem Detecting planted pseudo-cliques in random dot product graphs.
method Adjacency Spectral Embedding (ASE) and Graph Encoder Embedding (GEE).
result These methods can localize pseudo-cliques with additional clean network data, but not without it.
Proposes GLNNs for robust semi-supervised classification using adaptive graphs.
problem Adaptive graph learning for robust semi-supervised classification.
method Optimizes graph structure from data and tasks using spectral graph theory and maximum a posteriori estimation.
result GLNNs outperform state-of-the-art approaches in semi-supervised classification.
New method clusters directed and undirected graphs without losing directional information.
problem Clustering directed graphs due to asymmetry in edge connectivity.
method Generalized Dirichlet Energy (GDE) and generalized spectral clustering (GSC).
result GSC outperforms existing methods in clustering accuracy and robustness.
GRAMPA algorithm recovers latent vertex correspondence in correlated graphs with high probability.
problem Recovering latent vertex correspondence between unlabeled, edge-correlated weighted graphs.
method Spectral graph matching algorithm, GRAMPA, with exact recovery guarantees for Erdős-Rényi graphs.
result GRAMPA exactly recovers latent vertex correspondence with high probability for Erdős-Rényi graphs with edge correlation coefficient 1−σ2 and average degree at least polylog(n) when σ≲1/polylog(n). Generative model controls heterophily in graph signals.
problem Controlling heterophily in graph signals for better model effectiveness.
method Combines graphon-based generator with spectral filtering of Gaussian node features.
result Establishes theoretical guarantees for heterophily control and convergence.
Paper generalizes spectral embedding for better graph interpretation.
problem Modeling heterophilic connectivity and negative eigenvalues in graph data.
method Generalized latent position network model (Random Dot Product Graph).
result Consistent latent position estimates with asymptotically Gaussian error.
This paper develops a multilayer spectral clustering method for heterogeneous data.
problem Clustering in multilayer graphs with varying layer weights and structures.
method Convex layer aggregation for multilayer spectral graph clustering (SGC).
result Phase transition analysis and automated cluster assignment with statistical guarantees.
In this work, we are interested in generalizing convolutional neural networks (CNNs) from low-dimensional regular grids, where image, video and speech are represented, to high-dimensional irregular domains, such as social networks, brain connectomes or words' embedding, represented by graphs. We present a formulation o…
Paper shows graphs can be embedded in lower dimensions than expected.
problem Choosing the right embedding dimension for graph analysis.
method Utilizes hidden manifold structure to predict lower-dimensional embedding.
result Graphs can be embedded in much lower dimensions than previously thought.