Semi-supervised Learning for Aggregated Multilayer Graphs Using Diffuse Interface Methods and Fast Matrix-Vector Products

DOI10.1137/20M1352028MaRDI QIDQ4959467

Kai Bergermann, Martin Stoll, Toni Volkmer

Publication date: 13 September 2021

Published in: SIAM Journal on Mathematics of Data Science (Search for Journal in Brave)

Full work available at URL: https://arxiv.org/abs/2007.05239

zbMATH Keywords

nonequispaced fast Fourier transformgraph Laplaciandiffuse interface methodsfast eigenpair computationfeature groupingmulticlass semi-supervised learningpower mean Laplacian

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Numerical computation of eigenvalues and eigenvectors of matrices (65F15) Learning and adaptive systems in artificial intelligence (68T05) Graph theory (including graph drawing) in computer science (68R10) Graphs and linear algebra (matrices, eigenvalues, etc.) (05C50) Numerical methods for discrete and fast Fourier transforms (65T50)

Related Items (2)

Preconditioned Algorithm for Difference of Convex Functions with Applications to Graph Ginzburg–Landau Model ⋮ Adaptive Rational Krylov Methods for Exponential Runge–Kutta Integrators

Uses Software

• NFFT
• NFFT3
• GenLouvain
• GitHub
• mftoolbox

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Numerical Fourier analysis
• Fast convolution with radial kernels at nonequispaced knots
• Graph clustering, variational image segmentation methods and Hough transform scale detection for object measurement in images
• Mean curvature, threshold dynamics, and phase field theory on finite graphs
• Diffuse interface methods for multiclass segmentation of high-dimensional data
• Convergence of the graph Allen-Cahn scheme
• A Rayleigh-Chebyshev procedure for finding the smallest eigenvalues and associated eigenvectors of large sparse Hermitian matrices
• Diffuse Interface Models on Graphs for Classification of High Dimensional Data
• An MBO Scheme on Graphs for Classification and Image Processing
• Using NFFT 3---A Software Library for Various Nonequispaced Fast Fourier Transforms
• Community Structure in Time-Dependent, Multiscale, and Multiplex Networks
• Introduction to Semi-Supervised Learning
• Fast Summation at Nonequispaced Knots by NFFT
• Generalizing Diffuse Interface Methods on Graphs: Nonsmooth Potentials and Hypergraphs
• Community Detection in Networks via Nonlinear Modularity Eigenvectors
• Diffuse Interface Models on Graphs for Classification of High Dimensional Data
• Exploring complex networks
• Phase Transition Dynamics
• Functions of Matrices

This page was built for publication: Semi-supervised Learning for Aggregated Multilayer Graphs Using Diffuse Interface Methods and Fast Matrix-Vector Products