Spectral Clustering via Adaptive Layer Aggregation for Multi-Layer Networks
From MaRDI portal
Publication:6180749
Abstract: One of the fundamental problems in network analysis is detecting community structure in multi-layer networks, of which each layer represents one type of edge information among the nodes. We propose integrative spectral clustering approaches based on effective convex layer aggregations. Our aggregation methods are strongly motivated by a delicate asymptotic analysis of the spectral embedding of weighted adjacency matrices and the downstream -means clustering, in a challenging regime where community detection consistency is impossible. In fact, the methods are shown to estimate the optimal convex aggregation, which minimizes the mis-clustering error under some specialized multi-layer network models. Our analysis further suggests that clustering using Gaussian mixture models is generally superior to the commonly used -means in spectral clustering. Extensive numerical studies demonstrate that our adaptive aggregation techniques, together with Gaussian mixture model clustering, make the new spectral clustering remarkably competitive compared to several popularly used methods.
Cites work
- A goodness-of-fit test for stochastic block models
- A nonparametric view of network models and Newman–Girvan and other modularities
- A useful variant of the Davis-Kahan theorem for statisticians
- Achieving optimal misclassification proportion in stochastic block models
- Asymptotic behaviour of classification maximum likelihood estimates
- Asymptotic mutual information for the balanced binary stochastic block model
- Asymptotic normality of maximum likelihood and its variational approximation for stochastic blockmodels
- Bias-Adjusted Spectral Clustering in Multi-Layer Stochastic Block Models
- Clustering With Multi-Layer Graphs: A Spectral Perspective
- Community detection and stochastic block models: recent developments
- Community detection in networks with node features
- Community detection in sparse networks via Grothendieck's inequality
- Community structure in social and biological networks
- Concentration and regularization of random graphs
- Consistency of community detection in networks under degree-corrected stochastic block models
- Consistency of maximum-likelihood and variational estimators in the stochastic block model
- Consistency of spectral clustering in stochastic block models
- Consistent community detection in multi-layer network data
- Consistent community detection in multi-relational data through restricted multi-layer stochastic blockmodel
- Detecting overlapping communities in networks using spectral methods
- Entrywise eigenvector analysis of random matrices with low expected rank
- Estimating Mixed Memberships With Sharp Eigenvector Deviations
- Exact Recovery in the Stochastic Block Model
- Fast community detection by SCORE
- Impact of regularization on spectral clustering
- Likelihood-based model selection for stochastic block models
- Limit theorems for eigenvectors of the normalized Laplacian for random graphs
- Limiting behavior of eigenvectors of large Wigner matrices
- Minimax rates of community detection in stochastic block models
- Mixed membership stochastic blockmodels
- Networks
- On semidefinite relaxations for the block model
- Optimal rates for community estimation in the weighted stochastic block model
- Pseudo-likelihood methods for community detection in large sparse networks
- Random matrices have simple spectrum
- Reconstruction and estimation in the planted partition model
- Robust and computationally feasible community detection in the presence of arbitrary outlier nodes
- Role of normalization in spectral clustering for stochastic blockmodels
- Sharp nonasymptotic bounds on the norm of random matrices with independent entries
- Sparse random matrices have simple spectrum
- Spectral and matrix factorization methods for consistent community detection in multi-layer networks
- Spectral clustering and the high-dimensional stochastic blockmodel
- Spectral redemption in clustering sparse networks
- Stochastic blockmodels with a growing number of classes
- Strong consistency of k-means clustering
- The solution of some random NP-hard problems in polynomial expected time
- The two-to-infinity norm and singular subspace geometry with applications to high-dimensional statistics
This page was built for publication: Spectral Clustering via Adaptive Layer Aggregation for Multi-Layer Networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6180749)
