Deep Convolutional Networks on Graph-Structured Data

Abstract

Deep Learning's recent successes have mostly relied on Convolutional Networks, which exploit fundamental statistical properties of images, sounds and video data: the local stationarity and multi-scale compositional structure, that allows expressing long range interactions in terms of shorter, localized interactions. However, there exist other important examples, such as text documents or bioinformatic data, that may lack some or all of these strong statistical regularities. In this paper we consider the general question of how to construct deep architectures with small learning complexity on general non-Euclidean domains, which are typically unknown and need to be estimated from the data. In particular, we develop an extension of Spectral Networks which incorporates a Graph Estimation procedure, that we test on large-scale classification problems, matching or improving over Dropout Networks with far less parameters to estimate.

References in corpus (2)

• Fast Training of Convolutional Networks through FFTs
• Emergence of Complex-Like Cells in a Temporal Product Network with Local Receptive Fields

Cited by in corpus (399)

• Geometric deep learning: going beyond Euclidean data
• Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties
• Graph Embedding Techniques, Applications, and Performance: A Survey
• Convolutional Neural Networks on Graphs with Fast Localized Spectral Filtering
• Graph Neural Networks: A Review of Methods and Applications
• Graph Neural Network for Traffic Forecasting: A Survey
• A Review on Deep Learning Techniques Applied to Semantic Segmentation
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• MeshCNN: A Network with an Edge
• DropEdge: Towards Deep Graph Convolutional Networks on Node Classification
• Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
• Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review
• A simple neural network module for relational reasoning
• Discriminative Embeddings of Latent Variable Models for Structured Data
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
• Session-based Social Recommendation via Dynamic Graph Attention Networks
• dyngraph2vec: Capturing Network Dynamics using Dynamic Graph Representation Learning
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Graph Neural Networks with convolutional ARMA filters
• Learning Deep Generative Models of Graphs
• Few-Shot Learning with Graph Neural Networks
• Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
• Self-Attention Graph Pooling
• PCPNET: Learning Local Shape Properties from Raw Point Clouds
• CCNet: Criss-Cross Attention for Semantic Segmentation
• Optimal Wireless Resource Allocation with Random Edge Graph Neural Networks
• A Comprehensive Survey on Deep Graph Representation Learning
• Fault Location in Power Distribution Systems via Deep Graph Convolutional Networks
• Convolutional Neural Network Architectures for Signals Supported on Graphs
• Dynamic Graph CNN for Learning on Point Clouds
• How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey
• Graph-based Deep Learning for Communication Networks: A Survey
• Graph networks as learnable physics engines for inference and control
• DeeperGCN: All You Need to Train Deeper GCNs
• Deep Vessel Segmentation By Learning Graphical Connectivity
• Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework
• Attention-based Graph Neural Network for Semi-supervised Learning
• Residual Gated Graph ConvNets
• HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs
• Transferring Robustness for Graph Neural Network Against Poisoning Attacks
• SIGN: Scalable Inception Graph Neural Networks
• Complex Network Classification with Convolutional Neural Network
• Graph Neural Networks Exponentially Lose Expressive Power for Node Classification
• Deep Gaussian Embedding of Graphs: Unsupervised Inductive Learning via Ranking
• Deep Graph-Convolutional Image Denoising
• Deep Learning on Graphs: A Survey
• Graph Neural Networks: Taxonomy, Advances and Trends
• Flexible Neural Representation for Physics Prediction
• Learning Multimodal Graph-to-Graph Translation for Molecular Optimization
• A Comprehensive Survey of Graph Embedding: Problems, Techniques and Applications
• Robust Spatial Filtering with Graph Convolutional Neural Networks
• Cormorant: Covariant Molecular Neural Networks
• Relational Graph Attention Networks
• MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions
• How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
• Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
• Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting
• A Survey on Text Classification: From Shallow to Deep Learning
• An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
• Machine Learning on Graphs: A Model and Comprehensive Taxonomy
• Adaptive Graph Convolutional Neural Networks
• Graph Capsule Convolutional Neural Networks
• Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds
• Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
• Learning Backtrackless Aligned-Spatial Graph Convolutional Networks for Graph Classification
• Covariant Compositional Networks For Learning Graphs
• RGCNN: Regularized Graph CNN for Point Cloud Segmentation
• Relation Modeling with Graph Convolutional Networks for Facial Action Unit Detection
• Learning to fail: Predicting fracture evolution in brittle material models using recurrent graph convolutional neural networks
• Efficiently Embedding Dynamic Knowledge Graphs
• Attention Guided Graph Convolutional Networks for Relation Extraction
• Representation Learning for Natural Language Processing
• Deep Graph Convolutional Reinforcement Learning for Financial Portfolio Management -- DeepPocket
• A Generalization of Convolutional Neural Networks to Graph-Structured Data
• Neural Networks and Quantum Field Theory
• SPLATNet: Sparse Lattice Networks for Point Cloud Processing
• Graph Neural Networks for Natural Language Processing: A Survey
• Lorentz Group Equivariant Neural Network for Particle Physics
• Edge Attention-based Multi-Relational Graph Convolutional Networks
• Tackling Over-Smoothing for General Graph Convolutional Networks
• Graph Convolutional Networks for Text Classification
• Quantum Graph Neural Networks
• PasteGAN: A Semi-Parametric Method to Generate Image from Scene Graph
• Invariance-Preserving Localized Activation Functions for Graph Neural Networks
• Context-Dependent Diffusion Network for Visual Relationship Detection
• Tensor Programs II: Neural Tangent Kernel for Any Architecture
• Large Scale Graph Learning from Smooth Signals
• On the Binding Problem in Artificial Neural Networks
• Simulation study on the fleet performance of shared autonomous bicycles
• Deep Image Clustering with Contrastive Learning and Multi-scale Graph Convolutional Networks
• MeshGAN: Non-linear 3D Morphable Models of Faces
• Towards Semi-supervised Universal Graph Classification
• LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
• Training Deep Networks with Structured Layers by Matrix Backpropagation
• Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization
• Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling
• Learning Resilient Radio Resource Management Policies with Graph Neural Networks
• SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation
• HMSG: Heterogeneous Graph Neural Network based on Metapath Subgraph Learning
• Tensor Programs I: Wide Feedforward or Recurrent Neural Networks of Any Architecture are Gaussian Processes
• Spectral-based Graph Convolutional Network for Directed Graphs
• Learning from Pixel-Level Label Noise: A New Perspective for Semi-Supervised Semantic Segmentation
• Hypergraph Convolution and Hypergraph Attention
• Bridging the Gap Between Spectral and Spatial Domains in Graph Neural Networks
• Geometric deep learning on graphs and manifolds using mixture model CNNs
• Learning Lane Graph Representations for Motion Forecasting
• Constant Curvature Graph Convolutional Networks
• Dual-Primal Graph Convolutional Networks
• Learning to Adapt Invariance in Memory for Person Re-identification
• Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design
• Learning Graph Neural Networks with Positive and Unlabeled Nodes
• Neural Graph Evolution: Towards Efficient Automatic Robot Design
• Deep Feature Mining via Attention-based BiLSTM-GCN for Human Motor Imagery Recognition
• Graph Convolutional Reinforcement Learning
• Learning to SMILE(S)
• Inductive Representation Learning on Temporal Graphs
• Deep Shells: Unsupervised Shape Correspondence with Optimal Transport
• Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning
• The Evolution of Reinforcement Learning in Quantitative Finance: A Survey
• Edge-labeling Graph Neural Network for Few-shot Learning
• Pedestrian Attribute Recognition: A Survey
• Edge-Featured Graph Attention Network
• Dynamic Spatio-temporal Graph-based CNNs for Traffic Prediction
• Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective
• Reasoning Graph Networks for Kinship Verification: from Star-shaped to Hierarchical
• Stochastic Graph Neural Networks
• Adaptive Filters in Graph Convolutional Neural Networks
• Hierarchical Graph-to-Graph Translation for Molecules
• Convolutional Neural Networks for Toxic Comment Classification
• Premise Selection for Theorem Proving by Deep Graph Embedding
• Generating 3D faces using Convolutional Mesh Autoencoders
• Iterative Visual Reasoning Beyond Convolutions
• Image Classification with Hierarchical Multigraph Networks
• MILE: A Multi-Level Framework for Scalable Graph Embedding
• Higher-order Graph Convolutional Networks
• FoldingNet: Point Cloud Auto-encoder via Deep Grid Deformation
• Improving Graph Attention Networks with Large Margin-based Constraints
• Federated Dynamic GNN with Secure Aggregation
• Graph Convolution: A High-Order and Adaptive Approach
• The More You Know: Using Knowledge Graphs for Image Classification
• A literature survey of matrix methods for data science
• Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules
• Hybrid Quantum-Classical Graph Convolutional Network
• Graph Random Neural Network for Semi-Supervised Learning on Graphs
• Binarized Collaborative Filtering with Distilling Graph Convolutional Networks
• Graph Neural Networks in Computer Vision -- Architectures, Datasets and Common Approaches
• Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition
• Deriving Neural Architectures from Sequence and Graph Kernels
• Adversarial Attack on Hierarchical Graph Pooling Neural Networks
• Spatial Pyramid Based Graph Reasoning for Semantic Segmentation
• Inductive Representation Learning in Large Attributed Graphs
• Data-driven Thresholding in Denoising with Spectral Graph Wavelet Transform
• Towards Graph Self-Supervised Learning with Contrastive Adjusted Zooming
• Structure-Aware DropEdge Towards Deep Graph Convolutional Networks
• Label Efficient Semi-Supervised Learning via Graph Filtering
• Graph Edge Convolutional Neural Networks for Skeleton Based Action Recognition
• All About Knowledge Graphs for Actions
• GRASS: Generative Recursive Autoencoders for Shape Structures
• HONEM: Learning Embedding for Higher Order Networks
• Feedback Graph Convolutional Network for Skeleton-based Action Recognition
• Graph Inference Learning for Semi-supervised Classification
• Provably Powerful Graph Networks
• NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs
• A Pixel-Based Framework for Data-Driven Clothing
• Augmenting correlation structures in spatial data using deep generative models
• PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks
• Parallel Transport Convolution: A New Tool for Convolutional Neural Networks on Manifolds
• Heterogeneous Edge-Enhanced Graph Attention Network For Multi-Agent Trajectory Prediction
• Few-Shot Learning on Graphs via Super-Classes based on Graph Spectral Measures
• Recursive Social Behavior Graph for Trajectory Prediction
• Person Re-identification with Deep Similarity-Guided Graph Neural Network
• Quantifying the Alignment of Graph and Features in Deep Learning
• Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks
• FPConv: Learning Local Flattening for Point Convolution
• A Framework for Generalizing Graph-based Representation Learning Methods
• Unifying local and non-local signal processing with graph CNNs
• Walk-Steered Convolution for Graph Classification
• Optimized Skeleton-based Action Recognition via Sparsified Graph Regression
• Beltrami Flow and Neural Diffusion on Graphs
• Clustering-Based Relational Unsupervised Representation Learning with an Explicit Distributed Representation
• Graph Neural Networks for IceCube Signal Classification
• Traffic congestion anomaly detection and prediction using deep learning
• LiDAR-based Online 3D Video Object Detection with Graph-based Message Passing and Spatiotemporal Transformer Attention
• ManifoldNet: A Deep Network Framework for Manifold-valued Data
• Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation
• Optimal Solving of Constrained Path-Planning Problems with Graph Convolutional Networks and Optimized Tree Search
• Tensor Programs IIb: Architectural Universality of Neural Tangent Kernel Training Dynamics
• RigNet: Neural Rigging for Articulated Characters
• HONE: Higher-Order Network Embeddings
• HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds
• Orthogonal Inductive Matrix Completion
• Bayesian Graph Convolutional Neural Networks using Node Copying
• Sampling methods for efficient training of graph convolutional networks: A survey
• Deep Representation Learning for Social Network Analysis
• Parameterized Hypercomplex Graph Neural Networks for Graph Classification
• Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information
• Stability and Generalization of Graph Convolutional Neural Networks
• Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition
• When Work Matters: Transforming Classical Network Structures to Graph CNN
• Multi-dimensional Graph Convolutional Networks
• Understanding Graph Neural Networks from Graph Signal Denoising Perspectives
• FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis
• Ripple Walk Training: A Subgraph-based training framework for Large and Deep Graph Neural Network
• Text Level Graph Neural Network for Text Classification
• A Tailored Convolutional Neural Network for Nonlinear Manifold Learning of Computational Physics Data using Unstructured Spatial Discretizations
• Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning
• Hyperbolic Deep Neural Networks: A Survey
• Top-Down Learning for Structured Labeling with Convolutional Pseudoprior
• FedGL: Federated Graph Learning Framework with Global Self-Supervision
• CasGCN: Predicting future cascade growth based on information diffusion graph
• Graph Clustering with Dynamic Embedding
• Learning event representations for temporal segmentation of image sequences by dynamic graph embedding
• Towards Interpretable Sparse Graph Representation Learning with Laplacian Pooling
• Towards Efficient Large-Scale Graph Neural Network Computing
• Benchmarks for Graph Embedding Evaluation
• VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification
• Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning
• A Variational-Sequential Graph Autoencoder for Neural Architecture Performance Prediction
• LaplacianNet: Learning on 3D Meshes with Laplacian Encoding and Pooling
• RepGN:Object Detection with Relational Proposal Graph Network
• A deep learning approach to real-time parking occupancy prediction in spatio-temporal networks incorporating multiple spatio-temporal data sources
• Graph Convolutional Networks with EigenPooling
• VersaGNN: a Versatile accelerator for Graph neural networks
• Rubik: A Hierarchical Architecture for Efficient Graph Learning
• Learning Graph While Training: An Evolving Graph Convolutional Neural Network
• Graph Signal Processing for Geometric Data and Beyond: Theory and Applications
• AWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload Rebalancing
• SCE: Scalable Network Embedding from Sparsest Cut
• Building Footprint Extraction with Graph Convolutional Network
• Learning Deep Graph Representations via Convolutional Neural Networks
• Bayesian Graph Convolutional Neural Networks Using Non-Parametric Graph Learning
• Convolutional Neural Networks on non-uniform geometrical signals using Euclidean spectral transformation
• Mini-batch graphs for robust image classification
• Attribute Propagation Network for Graph Zero-shot Learning
• Multi-Component Graph Convolutional Collaborative Filtering
• Learning Color Compatibility in Fashion Outfits
• Label-guided Learning for Text Classification
• Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection
• Gromov-Wasserstein Factorization Models for Graph Clustering
• Graph Classification via Deep Learning with Virtual Nodes
• MeshWalker: Deep Mesh Understanding by Random Walks
• A Lagrangian Approach to Information Propagation in Graph Neural Networks
• DAGCN: Dual Attention Graph Convolutional Networks
• Learning to Infer Unseen Single-/Multi-Attribute-Object Compositions with Graph Networks
• Online Semi-Supervised Learning with Bandit Feedback
• TPCN: Temporal Point Cloud Networks for Motion Forecasting
• Graph Learning-Convolutional Networks
• Graph-Revised Convolutional Network
• Face-GCN: A Graph Convolutional Network for 3D Dynamic Face Identification/Recognition
• Interpretable Crowd Flow Prediction with Spatial-Temporal Self-Attention
• Ranking Structured Objects with Graph Neural Networks
• Modeling Attention Flow on Graphs
• DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters
• Graph Learning for Combinatorial Optimization: A Survey of State-of-the-Art
• Topological based classification using graph convolutional networks
• Health Status Prediction with Local-Global Heterogeneous Behavior Graph
• Sparse Diffusion-Convolutional Neural Networks
• Local Propagation in Constraint-based Neural Network
• Learning Global and Local Consistent Representations for Unsupervised Image Retrieval via Deep Graph Diffusion Networks
• Can Graph Neural Networks Go "Online"? An Analysis of Pretraining and Inference
• Continuous Geodesic Convolutions for Learning on 3D Shapes
• Convolutional Geometric Matrix Completion
• A Spatial-Temporal Decomposition Based Deep Neural Network for Time Series Forecasting
• A Graph-CNN for 3D Point Cloud Classification
• Integrative Analysis of Patient Health Records and Neuroimages via Memory-based Graph Convolutional Network
• LinkNet: Relational Embedding for Scene Graph
• Pose Refinement Graph Convolutional Network for Skeleton-based Action Recognition
• DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model
• An Overview on the Application of Graph Neural Networks in Wireless Networks
• Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures
• Fast Spectral Ranking for Similarity Search
• Semi-Supervised Learning on Graphs Based on Local Label Distributions
• A graph-embedded deep feedforward network for disease outcome classification and feature selection using gene expression data
• Graph Few-shot Learning via Knowledge Transfer
• Can GAN Learn Topological Features of a Graph?
• Edge-aware Graph Representation Learning and Reasoning for Face Parsing
• ReLaText: Exploiting Visual Relationships for Arbitrary-Shaped Scene Text Detection with Graph Convolutional Networks
• Rational Neural Networks for Approximating Jump Discontinuities of Graph Convolution Operator
• CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning
• SportsCap: Monocular 3D Human Motion Capture and Fine-grained Understanding in Challenging Sports Videos
• $p$-Laplacian Based Graph Neural Networks
• Exploring Hypergraph Representation on Face Anti-spoofing Beyond 2D Attacks
• Mesh Variational Autoencoders with Edge Contraction Pooling
• Improved Generalization Bounds of Group Invariant / Equivariant Deep Networks via Quotient Feature Spaces
• Mesh-based Autoencoders for Localized Deformation Component Analysis
• Human Action Recognition with Multi-Laplacian Graph Convolutional Networks
• RRNet: Relational Reasoning Network with Parallel Multi-scale Attention for Salient Object Detection in Optical Remote Sensing Images
• HodgeNet: Learning Spectral Geometry on Triangle Meshes
• KMF: Knowledge-Aware Multi-Faceted Representation Learning for Zero-Shot Node Classification
• Topological based classification of paper domains using graph convolutional networks
• CPR-GCN: Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling of Coronary Arteries
• Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting
• Dual-Attention Graph Convolutional Network
• Attribute-guided image generation from layout
• Graph Highway Networks
• A Survey on Deep Geometry Learning: From a Representation Perspective
• Building Segmentation through a Gated Graph Convolutional Neural Network with Deep Structured Feature Embedding
• GCN-LASE: Towards Adequately Incorporating Link Attributes in Graph Convolutional Networks
• Improved Visual Localization via Graph Smoothing
• Disentangle-based Continual Graph Representation Learning
• Learning the Implicit Semantic Representation on Graph-Structured Data
• GmCN: Graph Mask Convolutional Network
• Representation Learning of Point Cloud Upsampling in Global and Local Inputs
• Gaussian-Induced Convolution for Graphs
• Hybrid Low-order and Higher-order Graph Convolutional Networks
• Random Projection Forest Initialization for Graph Convolutional Networks
• Semi-supervised Learning with Adaptive Neighborhood Graph Propagation Network
• Low-Rank Matrix Completion: A Contemporary Survey
• CoulGAT: An Experiment on Interpretability of Graph Attention Networks
• Methods for Recovering Conditional Independence Graphs: A Survey
• GraphITE: Estimating Individual Effects of Graph-structured Treatments
• Tensor Graph Convolutional Networks for Text Classification
• Learning Predicates as Functions to Enable Few-shot Scene Graph Prediction
• NPTC-net: Narrow-Band Parallel Transport Convolutional Neural Network on Point Clouds
• Graph Attribute Aggregation Network with Progressive Margin Folding
• Learning Vertex Convolutional Networks for Graph Classification
• Skeleton-based Hand-Gesture Recognition with Lightweight Graph Convolutional Networks
• Tackling Graphical NLP problems with Graph Recurrent Networks
• Learning Feature Aggregation for Deep 3D Morphable Models
• Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
• Quantifying the Reproducibility of Graph Neural Networks using Multigraph Brain Data
• Geometrically Principled Connections in Graph Neural Networks
• Critical Percolation as a Framework to Analyze the Training of Deep Networks
• Which Hyperparameters to Optimise? An Investigation of Evolutionary Hyperparameter Optimisation in Graph Neural Network For Molecular Property Prediction
• Learning to Schedule DAG Tasks
• Graph Information Vanishing Phenomenon inImplicit Graph Neural Networks
• Analyzing the Performance of Graph Neural Networks with Pipe Parallelism
• GAIN: Graph Attention & Interaction Network for Inductive Semi-Supervised Learning over Large-scale Graphs
• Graph Denoising with Framelet Regularizer
• Equivariant and Invariant Reynolds Networks
• Probabilistic modeling of lake surface water temperature using a Bayesian spatio-temporal graph convolutional neural network
• Feature Correlation Aggregation: on the Path to Better Graph Neural Networks
• Enterprise Analytics using Graph Database and Graph-based Deep Learning
• Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution
• Graph Neural Networks for Node-Level Predictions
• End-to-end analysis using image classification
• Neural Trees for Learning on Graphs
• Noise-robust classification with hypergraph neural network
• Learning Conjoint Attentions for Graph Neural Nets
• Fast Mesh Data Augmentation via Chebyshev Polynomial of Spectral filtering
• Graph Analysis and Graph Pooling in the Spatial Domain
• Gasper: GrAph Signal ProcEssing in R
• Deep Constraint-based Propagation in Graph Neural Networks
• SAG-VAE: End-to-end Joint Inference of Data Representations and Feature Relations
• Graph convolutional networks for learning with few clean and many noisy labels
• Context-Aware Graph Attention Networks
• Cut-Based Graph Learning Networks to Discover Compositional Structure of Sequential Video Data
• GFCN: A New Graph Convolutional Network Based on Parallel Flows
• Open Knowledge Enrichment for Long-tail Entities
• Multifold Acceleration of Diffusion MRI via Slice-Interleaved Diffusion Encoding (SIDE)
• Modelling Irregular Spatial Patterns using Graph Convolutional Neural Networks
• Discriminative Learning of Similarity and Group Equivariant Representations
• Relational dynamic memory networks
• Neural Consciousness Flow
• Convolutional Imputation of Matrix Networks
• Convolutional Neural Network on Semi-Regular Triangulated Meshes and its Application to Brain Image Data
• Wall Stress Estimation of Cerebral Aneurysm based on Zernike Convolutional Neural Networks
• Multiple Graph Adversarial Learning
• Neural Network Approximation of Graph Fourier Transforms for Sparse Sampling of Networked Flow Dynamics
• DeepDrawing: A Deep Learning Approach to Graph Drawing
• Fast Haar Transforms for Graph Neural Networks
• Graph Neural Network for Hamiltonian-Based Material Property Prediction
• Graph Node Embeddings using Domain-Aware Biased Random Walks
• Fractional order graph neural network
• Distribution-Based Invariant Deep Networks for Learning Meta-Features
• Pre-Trained Models for Heterogeneous Information Networks
• Diversified Multiscale Graph Learning with Graph Self-Correction
• Deep Learning for Predicting Dynamic Uncertain Opinions in Network Data
• Policy Message Passing: A New Algorithm for Probabilistic Graph Inference
• Improving Graph Property Prediction with Generalized Readout Functions
• On the Global Self-attention Mechanism for Graph Convolutional Networks
• Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition
• Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognition
• Graph Feature Gating Networks
• Computational Analysis of Deformable Manifolds: from Geometric Modelling to Deep Learning
• Saliency Prediction with External Knowledge
• Spectral Transform Forms Scalable Transformer
• ChebLieNet: Invariant Spectral Graph NNs Turned Equivariant by Riemannian Geometry on Lie Groups
• Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation
• The Deep Latent Position Topic Model for Clustering and Representation of Networks with Textual Edges
• Meta-Path Learning for Multi-relational Graph Neural Networks
• Resource Allocation via Graph Neural Networks in Free Space Optical Fronthaul Networks
• Parameter-Efficient Neural Question Answering Models via Graph-Enriched Document Representations
• Equivariance-bridged SO(2)-Invariant Representation Learning using Graph Convolutional Network
• Multi-modal Entity Alignment in Hyperbolic Space
• Survey of Image Based Graph Neural Networks
• Dual GNNs: Graph Neural Network Learning with Limited Supervision
• Curvature Graph Neural Network
• Constrained Shortest Path Search with Graph Convolutional Neural Networks
• U-mesh: Human Correspondence Matching with Mesh Convolutional Networks
• GraphSeam: Supervised Graph Learning Framework for Semantic UV Mapping
• Intrinsic Geometric Information Transfer Learning on Multiple Graph-Structured Datasets
• Action Recognition with Kernel-based Graph Convolutional Networks
• Probability Trajectory: One New Movement Description for Trajectory Prediction
• Lookup subnet based Spatial Graph Convolutional neural Network
• Joint Forecasting and Interpolation of Graph Signals Using Deep Learning
• Lovasz Convolutional Networks
• Distributed Cartesian Power Graph Segmentation for Graphon Estimation