New neural architectures invariant to sign flips and basis symmetries for graph representation learning.
problem Learning invariant graph representations from eigenvectors.
method SignNet and BasisNet neural architectures that are invariant to sign flips and basis symmetries.
result Proven to be universal, approximating any continuous function of eigenvectors with desired invariances.
New algorithm updates eigenvectors of evolving graphs efficiently.
problem Updating eigenvectors of dynamic graphs.
method Subspace projection based on Rayleigh-Ritz projections.
result Strong performance in eigenvector approximation and downstream tasks.
Graph convolutional networks fail to use eigenvectors beyond the first, unlike spectral embedding.
problem Understanding when graph convolutional networks fail compared to spectral embedding.
method Presented a simple generative model to illustrate failure.
result Graph convolutional networks fail to use eigenvectors beyond the first in certain graphs.
The original contributions of this paper are twofold: a new understanding of the influence of noise on the eigenvectors of the graph Laplacian of a set of image patches, and an algorithm to estimate a denoised set of patches from a noisy image. The algorithm relies on the following two observations: (1) the low-index e…
The paper proves Lipschitz regularity of graph Laplacian eigenvectors on random data clouds.
problem Analyzing the regularity of solutions to graph Laplacian equations on random data points.
method Probabilistic coupling of random walks and interpolation method for point clouds to continuum.
result Graph Laplacian eigenvectors are essentially Lipschitz with constants depending on eigenvalues.
We prove a central limit theorem for the components of the largest eigenvectors of the adjacency matrix of a finite-dimensional random dot product graph whose true latent positions are unknown. In particular, we follow the methodology outlined in \citet{sussman2012universally} to construct consistent estimates for the …
A new method for spectral barycentre of graph datasets.
problem Creating a summary graph from a set of graphs with community structure.
method Using multiscale spectral distance based on normalized graph Laplacian eigenvalues.
result The barycentre inherits the topological structure of the graphs in the sample dataset.
In many applications, one has side information, e.g., labels that are provided in a semi-supervised manner, about a specific target region of a large data set, and one wants to perform machine learning and data analysis tasks "nearby" that prespecified target region. For example, one might be interested in the clusteri…
Graph Laplacian converges to Laplace-Beltrami operator with a specific rate.
problem Convergence of graph Laplacian to Laplace-Beltrami operator on random geometric graphs.
method Analysis of random geometric graphs and eigenvalue convergence rates.
result Eigenvalues and eigenvectors of graph Laplacian converge to Laplace-Beltrami operator with rate O((nlogn)2m1). ELD compares graphs by their embedded Laplacian eigenvectors, resolving ambiguities.
problem Comparing graphs of different sizes and structures.
method ELD uses symmetrization and perturbation techniques to compare graph embeddings.
result ELD resolves ambiguities in graph comparisons, making it a natural pseudo-metric.
A new method approximates Laplacian eigenvectors for RL efficiently.
problem Efficiently learning state representations in RL.
method General and scalable approach to approximating Laplacian eigenvectors.
result Empirically shows improved performance in RL tasks.
New method learns high-quality Laplacian representations for reinforcement learning.
problem Lack of accurate Laplacian representations in large or continuous state spaces.
method Reformulated spectral graph drawing objective to have eigenvectors as unique global minimizer.
result Learned Laplacian representations more faithfully approximate the ground truth.
New insights into spectral clustering reveal strong connections within eigenvectors.
problem Clustering on graphs when there are two underlying clusters.
method Analyzes the eigenvector corresponding to the second largest eigenvalue of the adjacency matrix.
result Vertices with extreme values in the eigenvector are more reliably classified.
We prove a central limit theorem for the components of the eigenvectors corresponding to the d largest eigenvalues of the normalized Laplacian matrix of a finite dimensional random dot product graph. As a corollary, we show that for stochastic blockmodel graphs, the rows of the spectral embedding of the normalized La…
New algorithm speeds up spectral clustering for dynamic graphs.
problem Prohibitive complexity of spectral clustering for dynamic graphs.
method Reuse past cluster assignments and use fast Chebyshev graph filtering.
result Achieves clustering quality approximating spectral clustering with significant complexity benefits.
This paper explains spectral clustering and its equivalence to PCA, breaking it into fully connected and multi-connected cases.
problem Understanding the mathematics behind spectral clustering and its equivalence to PCA.
method Dividing spectral clustering into two categories based on graph connectivity and proving the equivalence to PCA.
result Spectral clustering and PCA are equivalent, with specific proofs for fully connected and multi-connected graphs.
Enhanced spectral clustering for geometric graphs improves clustering accuracy.
problem Ineffective standard spectral clustering for geometric graphs.
method Higher-order spectral clustering using higher-order eigenvectors.
result Established weak and strong consistency for Soft Geometric Block Model.
GRAMPA spectral method solves graph matching problem with high probability.
problem Finding vertex correspondence between unlabeled graphs.
method GRAMPA constructs a similarity matrix from weighted eigenvector comparisons, rounding to produce a matching.
result GRAMPA exactly recovers correct vertex correspondence with high probability for Gaussian models.
Improved spectral clustering with fewer eigenvectors performs better.
problem Improving spectral clustering performance under weaker conditions.
method Tighter analysis and using fewer eigenvectors for embedding.
result Spectral clustering can produce better results with fewer eigenvectors.
We show how to approximate large graphs with smaller ones using spectral properties.
problem How coarsening affects the spectrum of a graph.
method Conditions for the closeness of principal eigenvalues and eigenspaces of coarsened and original graph Laplacian matrices.
result Coarse eigenvectors can be used for spectral clustering without refinement.
New method uses random signals to quickly approximate graph eigenvectors.
problem Estimating the first k eigenvectors of graph Laplacians efficiently.
method Filtering Gaussian random signals to recover eigenvectors.
result Only k random signals needed to recover k smallest eigenvectors.
Novel spectral embedding considers node weights for graph analysis.
problem Graph node importance quantification.
method Normalized Laplacian eigenvectors for low-energy configurations.
result Weighted embeddings improve graph configurations.
The paper tackles learning symmetries in data without expert knowledge.
problem Learning symmetries in data from raw data without prior knowledge.
method Develops methods to select eigenvectors for orthogonal symmetries and compares their effectiveness.
result The problem of learning symmetries is as hard as the graph automorphism problem in the worst case, but can be simplified with certain restrictions.
Spectral clustering is widely used to partition graphs into distinct modules or communities. Existing methods for spectral clustering use the eigenvalues and eigenvectors of the graph Laplacian, an operator that is closely associated with random walks on graphs. We propose a new spectral partitioning method that exploi…
This paper develops the exact linear relationship between the leading eigenvector of the unnormalized modularity matrix and the eigenvectors of the adjacency matrix. We propose a method for approximating the leading eigenvector of the modularity matrix, and we derive the error of the approximation. There is also a comp…
New method reduces spectral clustering complexity by sparsifying graphs.
problem Computational bottleneck in spectral clustering due to eigendeomposition of NN graph Laplacian matrices.
method Spectrum-preserving graph sparsification via low-stretch spanning trees and spectral off-tree embedding.
result Ultra-sparse NN graphs with preserved first few eigenvectors for scalable spectral clustering.
Sign equivariant networks improve model expressiveness for spectral geometric learning.
problem Limited expressiveness of sign invariant models for tasks like graph link prediction.
method Developed sign equivariant neural network architectures based on new analytic sign equivariant polynomials.
result Sign equivariant models achieve theoretical benefits in spectral geometric learning tasks.
Recently, Mahoney and Orecchia demonstrated that popular diffusion-based procedures to compute a quick \emph{approximation} to the first nontrivial eigenvector of a data graph Laplacian \emph{exactly} solve certain regularized Semi-Definite Programs (SDPs). In this paper, we extend that result by providing a statistica…
Introduces a new method for clustering multilayer graphs.
problem How to merge information from different layers in multilayer graphs.
method Introduces a one-parameter family of matrix power means for merging Laplacians from different layers.
result The method allows for accurate recovery of ground truth clusters under various settings.
Model predicts treatment initiation from clinical data using patient-clinician relations.
problem Predicting treatment initiation from clinical time series data considering patient-clinician relations.
method Graph-Augmented Time-Sensitive Model using top eigenvectors of graph Laplacian.
result Relational similarity improves prediction over baselines, e.g., 5% improvement in AUPRC.
We show that eigenvalues and eigenfunctions of the Laplace-Beltrami operator on a Riemannian manifold are approximated by eigenvalues and eigenvectors of a (suitably weighted) graph Laplace operator of a proximity graph on an epsilon-net.
New GCNs solve graph embedding problems efficiently and interpretably.
problem Graph embedding for scalable and interpretable machine learning.
method Proposed two GCNs: CAFE-GCN and sphere-GCN, based on constrained optimization.
result Both GCNs yield good approximations of dominant eigenvectors and perform dimensionality reduction.
Dual regularized graph Laplacian improves spectral clustering for community detection.
problem Detecting clusters in networks with improved spectral clustering methods.
method Proposes dual regularized graph Laplacian for three spectral clustering approaches.
result Theoretical analysis shows DRSC and DRSLIM yield stable consistent community detection.
A distributed Nesterov method for arbitrary graphs achieves faster convergence.
problem Optimizing distributed systems over arbitrary graphs.
method Distributed Nesterov method ABN and its variation FROZEN. result Achieves acceleration compared to state-of-the-art methods.
Networks or graphs can easily represent a diverse set of data sources that are characterized by interacting units or actors. Social networks, representing people who communicate with each other, are one example. Communities or clusters of highly connected actors form an essential feature in the structure of several emp…
Graph-based method ranks features using Eigenvector Centrality for feature selection.
problem Feature selection in high-dimensional data.
method Mapping features onto an affinity graph and ranking nodes based on Eigenvector Centrality.
result The method identifies effective features for classification, outperforming other methods in accuracy, stability, and speed.
Harmonic analysis on directed graphs for signal modeling and semi-supervised learning.
problem Signal analysis on directed graphs.
method Introduced a Fourier-type basis using eigenvectors of the random walk operator, developed wavelet transforms for multi-scale analysis.
result Efficiency of the proposed framework for semi-supervised learning and signal modeling on directed graphs.
Spectral clustering approaches have led to well-accepted algorithms for finding accurate clusters in a given dataset. However, their application to large-scale datasets has been hindered by computational complexity of eigenvalue decompositions. Several algorithms have been proposed in the recent past to accelerate spec…
New spectral method for community detection in complex networks.
problem Community detection in heterogeneous large networks.
method Spectral methods based on α-parametrized normalized modularity matrix, with regularization of eigenvectors.
result Existence of an optimal value α_opt for best community detection and on-line estimation of it.
New theory for eigenvectors of generalized Laplacian matrices, addressing dependency issues.
problem Dependency in random matrix theory hinders eigenvector analysis for latent embeddings.
method Introduces generalized Laplacian matrices and a new asymptotic theory framework.
result Established asymptotic normalities for spiked eigenvectors and eigenvalues.
New sampling methods improve node embedding efficiency.
problem Efficiency and scalability in node embedding methods.
method Sampling approaches to node embedding, modeling eigenvectors and feature vectors.
result Improved computational efficiency and scalability.
Study on signed graphs with random signs, focusing on community detection.
problem Community detection in signed stochastic block models.
method Strong concentration inequalities for adjacency and Laplacian matrices, applied to signed Laplacian matrix.
result The sign of the first eigenvector of the Laplacian matrix defines a weakly consistent estimator for balanced community detection.
New method clusters signed graphs using matrix power means.
problem Clustering signed graphs with positive and negative relations.
method Signed Power Mean Laplacian, defined as matrix power mean of normalized standard and signless Laplacians.
result Signed power mean Laplacian captures ground truth clusters under reasonable settings.
Spectral methods that are based on eigenvectors and eigenvalues of discrete graph Laplacians, such as Diffusion Maps and Laplacian Eigenmaps are often used for manifold learning and non-linear dimensionality reduction. It was previously shown by Belkin and Niyogi \cite{belkin_niyogi:2007} that the eigenvectors and eige…
Novel parametrized graph shift operators improve graph neural network performance.
problem Improving graph neural network performance on various datasets.
method Proposed a novel parametrized graph shift operator (PGSO) that optimizes parameters during training.
result PGSO improves accuracy in node and graph classification tasks on real-world datasets.
Better spectral partitioning of signed graphs using standard Laplacian.
problem Meaningless partitioning using signed Laplacian eigenvectors.
method Use standard graph Laplacian for spectral partitioning.
result Fiedler vector of standard Laplacian is easier to compute and more beneficial.
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.
Laplacian Eigenvectors of the graph constructed from a data set are used in many spectral manifold learning algorithms such as diffusion maps and spectral clustering. Given a graph constructed from a random sample of a d-dimensional compact submanifold M in RD, we establish the spectral convergence rate…