The emerging field of signal processing on graphs: Extending high-dimensional data analysis to networks and other irregular domains
2013/04/05 by David I Shuman, D. I. Shuman, Sunil K. Narang +7 · 294 citations
Physics and Astronomy · Computer Science · Biochemistry, Genetics and Molecular Biology · #Complex Network Analysis Techniques #Advanced Graph Neural Networks #Bioinformatics and Genomic Networks
paper · doi:10.1109/msp.2012.2235192
Abstract
In applications such as social, energy, transportation, sensor, and neuronal networks, high-dimensional data naturally reside on the vertices of weighted graphs. The emerging field of signal processing on graphs merges algebraic and spectral graph theoretic concepts with computational harmonic analysis to process such signals on graphs. In this tutorial overview, we outline the main challenges of the area, discuss different ways to define graph spectral domains, which are the analogs to the classical frequency domain, and highlight the importance of incorporating the irregular structures of graph data domains when processing signals on graphs. We then review methods to generalize fundamental operations such as filtering, translation, modulation, dilation, and downsampling to the graph setting and survey the localized, multiscale transforms that have been proposed to efficiently extract information from high-dimensional data on graphs. We conclude with a brief discussion of open issues and possible extensions.
Citations
Cited by
- Design of Sampling Set for Bandlimited Graph Signal Estimation
- Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks
- Entrywise convergence of iterative methods for eigenproblems
- Graph Learning from Data under Structural and Laplacian Constraints
- Stationary Signal Processing on Graphs
- Geometric Deep Learning: Going beyond Euclidean data
- Learning Graphs From Data: A Signal Representation Perspective
- Connecting the Dots: Identifying Network Structure via Graph Signal Processing
- Twenty-Five Years of Sensor Array and Multichannel Signal Processing: A review of progress to date and potential research directions
- Hermitian random walk graph Fourier transform for directed graphs and its applications
- ST-UNet: A Spatio-Temporal U-Network for Graph-structured Time Series Modeling
- Low-dimensional controllability of brain networks
- Spectral Graph Attention Network with Fast Eigen-approximation
- Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks
- Graph neural networks: A review of methods and applications
- Approximating Orthogonal Matrices with Effective Givens Factorization
- Optimization of a partial differential equation on a complex network
- Vertex-Frequency Graph Signal Processing: A review
- Projective Graph Residualization: Variation-Allocation Frontiers for Control-Function IV
- TPCN: Temporal Point Cloud Networks for Motion Forecasting
- Fast Hierarchical Neural Network for Feature Learning on Point Cloud
- Performance Analysis of Plug-and-Play ADMM: A Graph Signal Processing\n Perspective
- Continuous-Flow Graph Transportation Distances
- Structured Sequence Modeling with Graph Convolutional Recurrent Networks
- Deep geometric knowledge distillation with graphs
- Skeleton-Based Action Recognition With Multi-Stream Adaptive Graph Convolutional Networks
- Learning Graphs With Monotone Topology Properties and Multiple Connected Components
- Average Consensus by Graph Filtering: New Approach, Explicit Convergence Rate and Optimal Design
- Deep Graph Similarity Learning: A Survey
- Multi-dimensional Graph Fourier Transform
- Learning Lane Graph Representations for Motion Forecasting
- Exploring Deep 3D Spatial Encodings for Large-Scale 3D Scene Understanding
- Revisiting Spatial-Temporal Similarity: A Deep Learning Framework for Traffic Prediction
- Interpretable Neuron Structuring with Graph Spectral Regularization
- Grassmanian Interpolation of Low-Pass Graph Filters: Theory and Applications
- Interpretable Stability Bounds for Spectral Graph Filters
- Error Adjustment Based on Spatiotemporal Correlation Fusion for Traffic Forecasting
- Adaptive Universal Generalized PageRank Graph Neural Network
- A proximal algorithm incorporating difference of convex functions optimization for solving a class of single-ratio fractional programming
- Training-Free Spectral Fingerprints of Voice Processing in Transformers
- A Graph Signal Processing Framework for Hallucination Detection in Large Language Models
- PET Image Reconstruction with Multiple Kernels and Multiple Kernel Space Regularizers
- Learning Time-Varying Graphs from Incomplete Graph Signals
- A Simple Method for PMF Estimation on Large Supports
- Graph Neural Networks: A Review of Methods and Applications
- Robust Tangent Space Estimation via Laplacian Eigenvector Gradient Orthogonalization
- Two-Dimensional Graph Bi-Fractional Fourier Transform
- Multitask Learning with Learned Task Relationships
- Graph Signal Wiener Filtering in the Linear Canonical Domain: Theory and Method Design
- Graph-Time Spectral Analysis for Atrial Fibrillation
- SVD-Based UGRM-GFT on Directed Product Graphs
- From Spectrum Wavelet to Vertex Propagation: Graph Convolutional Networks Based on Taylor Approximation
- CDSA: Cross-Dimensional Self-Attention for Multivariate, Geo-tagged Time Series Imputation
- Constructing Frequency Domains on Graphs in Near-Linear Time
- Translation Operator in Graph Signal Processing: A Generalized Approach
- Label Efficient Semi-Supervised Learning via Graph Filtering
- Eigen component analysis: A quantum theory incorporated machine learning technique to find linearly maximum separable components
- Estimating Fair Graphs from Graph-Stationary Data
- Directional Sheaf Hypergraph Networks: Unifying Learning on Directed and Undirected Hypergraphs
- Steady-State Spread Bounds for Graph Diffusion via Laplacian Regularisation in Networked Systems
- On the Convergence and Size Transferability of Continuous-depth Graph Neural Networks
- A Multiscale Pyramid Transform for Graph Signals
- Graph Neural Networks in Large Scale Wireless Communication Networks: Scalability Across Random Geometric Graphs
- Graph Metric Learning via Gershgorin Disc Alignment
- FedGL: Federated Graph Learning Framework with Global Self-Supervision
- VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks
- Graph Distribution-valued Signals: A Wasserstein Space Perspective
- A Graph-CNN for 3D Point Cloud Classification
- A Generative Model for Controllable Feature Heterophily in Graphs
- From Noise to Laws: Regularized Time-Series Forecasting via Denoised Dynamic Graphs
- Vertex-frequency analysis on graphs
- Random sampling of bandlimited signals on graphs
- Reproduction Number and Spatial Connectivity Structure Estimation via Graph Sparsity-Promoting Penalized Functional
- Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition
- Leveraging ancestral sequence reconstruction for protein representation learning
- Analog Courant Numbers and their Role in Analog Computing
- Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks
- Schreier-Coset Graph Rewiring
- Impact of Connectivity on Laplacian Representations in Reinforcement Learning
- Detection of functional activity in brain white matter using fiber architecture informed synchrony mapping
- Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
- Polynomial control on stability, inversion and powers of matrices on simple graphs
- Graphs for deep learning representations
- Quaternion LMS for Graph Signal Recovery
- Bayesian Convolutional Neural Networks for Prior Learning in Graph Signal Recovery
- A general method to compute numerical dispersion errors and its application to stretched meshes
- Variational Graph Methods for Efficient Point Cloud Sparsification
- Unitary Shift Operators on a Graph
- Feature Selection via Graph Topology Inference for Soundscape Emotion Recognition
- A CARLA-based Simulation of Electrically Driven Forklifts
- Learning Graph from Smooth Signals under Partial Observation: A Robustness Analysis
- 3D Point Cloud Denoising using Graph Laplacian Regularization of a Low Dimensional Manifold Model
- ST-LINK: Spatially-Aware Large Language Models for Spatio-Temporal Forecasting
- Active Sampling for Approximately Bandlimited Graph Signals
- Secure Blind Graph Signal Recovery and Adversary Detection Using Smoothness Maximization
- GSPBOX: A toolbox for signal processing on graphs
- Graphon Signal Processing for Spiking and Biological Neural Networks
- Topology Adaptive Graph Convolutional Networks
- Blind Deconvolution of Nonstationary Graph Signals over Shift-Invariant Channels
- How to learn a graph from smooth signals
- Kalman Filtering of Stationary Graph Signals
- Learning from Heterophilic Graphs: A Spectral Theory Perspective on the Impact of Self-Loops and Parallel Edges
- A Graph Signal Processing View on Functional Brain Imaging
- Simultaneous Low-rank Component and Graph Estimation for High-dimensional Graph Signals: Application to Brain Imaging
- AdaSTI: Conditional Diffusion Models with Adaptive Dependency Modeling for Spatio-Temporal Imputation
- Node Similarity Preserving Graph Convolutional Networks
- Filter Design for Autoregressive Moving Average Graph Filters
- Real-time identification and control of influential pandemic regions using graph signal variation
- Multi-Dictionary Learning for Low Rank Sparse Coding
- Signal Processing on Directed Graphs
- Graph Denoising with Framelet Regularizer
- JFRFFNet: A Data-Model Co-Driven Graph Signal Denoising Model with Partial Prior Information
- Signed Graph Learning with Hidden Nodes
- Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast
- Graph Signal Processing: Modulation, Convolution, and Sampling
- Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks
- Signal Representations on Graphs: Tools and Applications
- From Eigenmodes to Proofs: Integrating Graph Spectral Operators with Symbolic Interpretable Reasoning
- A Unified Framework for Structured Graph Learning via Spectral Constraints
- On the Shift Operator, Graph Frequency and Optimal Filtering in Graph Signal Processing
- Multi-dimensional graph fractional Fourier transform and its application
- Space-Time Graph Neural Networks
- Data-Efficient Psychiatric Disorder Detection via Self-supervised Learning on Frequency-enhanced Brain Networks
- Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting
- Compact Graph Architecture for Speech Emotion Recognition
- Polynomial graph filter of multiple shifts and distributed implementation of inverse filtering
- Vertex-Frequency Analysis on Graphs
- Tensor Networks for Multi-Modal Non-Euclidean Data
- Learning Product Graphs Underlying Smooth Graph Signals
- Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
- Faster Inference of Cell Complexes from Flows via Matrix Factorization
- Sampling Theory of Jointly Bandlimited Time-vertex Graph Signals
- Signal processing on simplicial complexes
- Low-dimensional controllability of brain networks
- Joint Demosaicking / Rectification of Fisheye Camera Images using Multi-color Graph Laplacian Regularization
- Network Representation Learning: From Traditional Feature Learning to Deep Learning
- GRASPED: Graph Anomaly Detection using Autoencoder with Spectral Encoder and Decoder (Full Version)
- GegenNet: Spectral Convolutional Neural Networks for Link Sign Prediction in Signed Bipartite Graphs
- InfraredGP: Efficient Graph Partitioning via Spectral Graph Neural Networks with Negative Corrections
- From graphs to signals and back: Identification of network structures\n using spectral analysis
- Unifying local and non-local signal processing with graph CNNs
- Graph WaveNet for Deep Spatial-Temporal Graph Modeling
- Spectrum-Adapted Polynomial Approximation for Matrix Functions
- A Fully Spectral Neuro-Symbolic Reasoning Architecture with Graph Signal Processing as the Computational Backbone
- Predicting the Performance of Graph Convolutional Networks with Spectral Properties of the Graph Laplacian
- Adversarial Graph Disentanglement
- GraphCogent: Mitigating LLMs' Working Memory Constraints via Multi-Agent Collaboration in Complex Graph Understanding
- A Novel Unified Extended Matrix for Graph Signal Processing: Theory and Application
- Deep Haar Scattering Networks
- Beyond Semantic Understanding: Preserving Collaborative Frequency Components in LLM-based Recommendation
- Human Action Recognition with Multi-Laplacian Graph Convolutional Networks
- Directed Cycles as Higher-Order Units of Information Processing in Complex Networks
- Agentic Graph Neural Networks for Wireless Communications and Networking Towards Edge General Intelligence: A Survey
- Graph Capsule Convolutional Neural Networks
- Neural Embedding Propagation on Heterogeneous Networks
- High-dimensional Longitudinal Inference via a De-sparsified Dantzig-Selector
- A short-graph Fourier transform via personalized PageRank vectors
- Joint Learning of Graph Representation and Node Features in Graph Convolutional Neural Networks
- Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks
- Convolutional neural networks on irregular domains based on approximate vertex-domain translations
- Stability of Graph Scattering Transforms
- Graph Embedding in the Graph Fractional Fourier Transform Domain
- Localization, Decomposition, and Dictionary Learning of Piecewise-Constant Signals on Graphs
- Distributed Network Privacy using Error Correcting Codes
- Adaptive Graph-based Total Variation for Tomographic Reconstructions
- Trainable Joint Time-Vertex Fractional Fourier Transform
- Beyond Neural Networks: Symbolic Reasoning over Wavelet Logic Graph Signals
- Robust Deep Graph Based Learning for Binary Classification
- AMOS: An Automated Model Order Selection Algorithm for Spectral Graph Clustering
- Neural Graph Embedding Methods for Natural Language Processing
- Robust, Deep, and Reinforcement Learning for Management of Communication\n and Power Networks
- Bespoke multiresolution analysis of graph signals
- Graph Pooling with Node Proximity for Hierarchical Representation Learning
- Euclidean Distance Deflation Under High-Dimensional Heteroskedastic Noise
- Brain Maturation Study during Adolescence Using Graph Laplacian Learning Based Fourier Transform
- Fast Decentralized Linear Functions Over Edge Fluctuating Graphs
- Distributed Linear Network Operators using Graph Filters
- Spectrum-Adapted Tight Graph Wavelet and Vertex-Frequency Frames
- Scalable Perception-Action-Communication Loops with Convolutional and Graph Neural Networks
- Unsupervised Deep Haar Scattering on Graphs
- AN-GCN: An Anonymous Graph Convolutional Network Defense Against Edge-Perturbing Attack
- SF-GRASS: Solver-Free Graph Spectral Sparsification
- Spectral representation of EEG data using learned graphs with application to motor imagery decoding
- How likely is a random graph shift-enabled?
- EEG-based video identification using graph signal modeling and graph convolutional neural network
- Graph-LDA: Graph Structure Priors to Improve the Accuracy in Few-Shot Classification
- Regret-based spectral sensor scheduling for multi-agent estimation
- Unsupervised Learning of Spike Patterns for Seizure Detection and Wavefront Estimation of High Resolution Micro Electrocorticographic (μECoG) Data
- Deep Iterative and Adaptive Learning for Graph Neural Networks
- Weighted sampling and weighted interpolation on combinatorial graphs
- When Product Search Meets Collaborative Filtering: A Hierarchical Heterogeneous Graph Neural Network Approach
- Pose Refinement Graph Convolutional Network for Skeleton-based Action Recognition
- Ranking Deep Learning Generalization using Label Variation in Latent Geometry Graphs
- Wavelet Logic Machines: Learning and Reasoning in the Spectral Domain Without Neural Networks
- Learning Graph While Training: An Evolving Graph Convolutional Neural Network
- Data Transformation Strategies to Remove Heterogeneity
- Mesh Learning Using Persistent Homology on the Laplacian Eigenfunctions
- Coding Method for Parallel Iterative Linear Solver
- Laplacian-regularized graph bandits: Algorithms and theoretical analysis
- Time-Varying Graph Learning with Constraints on Graph Temporal Variation
- Zoom and Learn: Generalizing Deep Stereo Matching to Novel Domains
- Dense 3D Face Decoding over 2500FPS: Joint Texture & Shape Convolutional Mesh Decoders
- Fast Spectral Ranking for Similarity Search
- Bayesian Semi-supervised Learning with Graph Gaussian Processes
- Boosting of Image Denoising Algorithms
- Nonlinear Dimensionality Reduction on Graphs
- Subgraph Signal Processing
- Guided Signal Reconstruction Theory
- Deconvolutional Networks on Graph Data
- When Does Self-Supervision Help Graph Convolutional Networks?
- Signed Graph Learning: Algorithms and Theory
- Node Embedding via Word Embedding for Network Community Discovery
- Attacking Graph Convolutional Networks via Rewiring
- When Work Matters: Transforming Classical Network Structures to Graph CNN
- Scalable Semi-Supervised Learning over Networks using Nonsmooth Convex Optimization
- Graph Convolutional Networks with EigenPooling
- Understanding Graph Isomorphism Network for rs-fMRI Functional Connectivity Analysis
- Graph Neural Ordinary Differential Equations
- Blind Community Detection from Low-rank Excitations of a Graph Filter
- GraSSNet: Graph Soft Sensing Neural Networks
- Anomaly Detection on Graph Time Series
- Persistent Homology as a Theory of Emergent Structure
- Stability and Generalization of Graph Convolutional Neural Networks
- FL-AGCNS: Federated Learning Framework for Automatic Graph Convolutional Network Search
- A Spectral Nonlocal Block for Neural Networks
- WATS: Calibrating Graph Neural Networks with Wavelet-Aware Temperature Scaling
- Estimating Centrality Blindly from Low-pass Filtered Graph Signals
- Double-Diffusion: Balancing Speed, Accuracy, and Uncertainty in Probabilistic Forecasting for Urban Sensor Networks
- Supervised Linear Regression for Graph Learning from Graph Signals
- GKNet: Graph Kalman Filtering and Model Inference via Model-based Deep Learning
- Graph Fourier Transform with Negative Edges for Depth Image Coding
- Compressive PCA for Low-Rank Matrices on Graphs
- Learning Parametrised Graph Shift Operators
- Spectral Embedding of Graph Networks
- EHCube4P: Learning Epistatic Patterns Through Hypercube Graph Convolution Neural Network for Protein Fitness Function Estimation
- Spatio-Temporal Graph Scattering Transform
- Robust recovery of bandlimited graph signals via randomized dynamical sampling
- SlepNet: Spectral Subgraph Representation Learning for Neural Dynamics
- Mitigating Over-Squashing in Graph Neural Networks by Spectrum-Preserving Sparsification
- Functional Alignment with Anatomical Networks is Associated with\n Cognitive Flexibility
- Edge-variational Graph Convolutional Networks for Uncertainty-aware Disease Prediction
- VersaGNN: a Versatile accelerator for Graph neural networks
- Toward An Uncertainty Principle For Weighted Graphs
- Local Frequency Interpretation and Non-Local Self-Similarity on Graph for Point Cloud Inpainting
- Structured Graph Learning for Clustering and Semi-supervised Classification
- Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
- Learning hidden influences in large-scale dynamical social networks: A data-driven sparsity-based approach
- Dynamic Graph CNN for Learning on Point Clouds
- Graph Convolutional Network for Recommendation with Low-pass Collaborative Filters
- Principled Simplicial Neural Networks for Trajectory Prediction
- Efficient Traffic Forecasting on Large-Scale Road Network by Regularized Adaptive Graph Convolution
- A Markov Variation Approach to Smooth Graph Signal Interpolation
- Sampling methods for efficient training of graph convolutional networks: A survey
- Steering Macro-Scale Network Community Structure by Micro-Scale Features
- FA-INR: Adaptive Implicit Neural Representations for Interpretable Exploration of Simulation Ensembles
- Network Topology Inference Using Information Cascades with Limited Statistical Knowledge
- Robust Graph Learning Under Wasserstein Uncertainty
- Joint Network Topology Inference via Structured Fusion Regularization
- Action Recognition via Pose-Based Graph Convolutional Networks with Intermediate Dense Supervision
- GFCN: A New Graph Convolutional Network Based on Parallel Flows
- DeepWORD: A GCN-based Approach for Owner-Member Relationship Detection in Autonomous Driving
- An Introduction to Robust Graph Convolutional Networks
- Asymptotic Justification of Bandlimited Interpolation of Graph signals\n for Semi-Supervised Learning
- Capturing and Explaining Trajectory Singularities using Composite Signal Neural Networks
- Signal Recovery on Graphs: Fundamental Limits of Sampling Strategies
- Convolutional Geometric Matrix Completion
- Online Distributed Learning over Graphs with Multitask Graph-Filter Models
- Stationarity of Time-Series on Graph via Bivariate Translation Invariance
- Reconstructing nodal pressures in water distribution systems with graph\n neural networks
- Deep Learning on Graphs: A Survey
- Discovering the structure of complex networks by minimizing cyclic bandwidth sum
- Enhancing Geometric Deep Learning via Graph Filter Deconvolution
- Quantitative Error Feedback for Quantization Noise Reduction of Filtering over Graphs
- Efficient Learning of Balanced Signed Graphs via Sparse Linear Programming
- Smoothness Sensor: Adaptive Smoothness-Transition Graph Convolutions for Attributed Graph Clustering
- Graph Neural Networks for Distributed Linear-Quadratic Control
- On the Stability of Graph Convolutional Neural Networks: A Probabilistic Perspective
- Transient Error Analysis of the LMS and RLS Algorithm for Graph Signal Estimation
- Cascading: Association Augmented Sequential Recommendation
- Graph-Based Object Classification for Neuromorphic Vision Sensing
- Orthogonal Transforms for Signals on Directed Graphs
- Joint estimation of smooth graph signals from partial linear measurements
- Training Matters: Unlocking Potentials of Deeper Graph Convolutional Neural Networks
- Hyperbolic-PDE GNN: Spectral Graph Neural Networks in the Perspective of A System of Hyperbolic Partial Differential Equations
- Graph learning under spectral sparsity constraints
- Algorithm Unrolling-based Denoising of Multimodal Graph Signals
- Efficient Identity and Position Graph Embedding via Spectral-Based Random Feature Aggregation
- ISTD-GCN: Iterative Spatial-Temporal Diffusion Graph Convolutional Network for Traffic Speed Forecasting
- Graph Wave Networks
- Spatially Focused Attack against Spatiotemporal Graph Neural Networks
- Convexified Message-Passing Graph Neural Networks
- On Sparse Graph Fourier Transform
- Principal Patterns on Graphs: Discovering Coherent Structures in\n Datasets
- Reconstruction of Graph Signals on Complex Manifolds with Kernel Methods
Related