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 (1)

• Emergence of Complex-Like Cells in a Temporal Product Network with Local Receptive Fields

Cited by in corpus (140)

• Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
• A simple neural network module for relational reasoning
• Session-based Social Recommendation via Dynamic Graph Attention Networks
• SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Self-Attention Graph Pooling
• DeeperGCN: All You Need to Train Deeper GCNs
• Short-term traffic flow forecasting with spatial-temporal correlation in a hybrid deep learning framework
• Learning Multimodal Graph-to-Graph Translation for Molecular Optimization
• Relational Graph Attention Networks
• Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
• An Attention Enhanced Graph Convolutional LSTM Network for Skeleton-Based Action Recognition
• Adaptive Graph Convolutional Neural Networks
• Covariant Compositional Networks For Learning Graphs
• Relation Modeling with Graph Convolutional Networks for Facial Action Unit Detection
• Representation Learning for Natural Language Processing
• Lorentz Group Equivariant Neural Network for Particle Physics
• Quantum Graph Neural Networks
• On the Binding Problem in Artificial Neural Networks
• MeshGAN: Non-linear 3D Morphable Models of Faces
• LatentGNN: Learning Efficient Non-local Relations for Visual Recognition
• SyncSpecCNN: Synchronized Spectral CNN for 3D Shape Segmentation
• Spectral-based Graph Convolutional Network for Directed Graphs
• Learning Lane Graph Representations for Motion Forecasting
• Geometric deep learning on graphs and manifolds using mixture model CNNs
• Neural Graph Evolution: Towards Efficient Automatic Robot Design
• Inductive Representation Learning on Temporal Graphs
• Deep Shells: Unsupervised Shape Correspondence with Optimal Transport
• Edge-labeling Graph Neural Network for Few-shot Learning
• Edge-Featured Graph Attention Network
• Premise Selection for Theorem Proving by Deep Graph Embedding
• Image Classification with Hierarchical Multigraph Networks
• Graph Convolution: A High-Order and Adaptive Approach
• Federated Dynamic GNN with Secure Aggregation
• Improving Graph Attention Networks with Large Margin-based Constraints
• Hybrid Quantum-Classical Graph Convolutional Network
• Binarized Collaborative Filtering with Distilling Graph Convolutional Networks
• Adversarial Attack on Hierarchical Graph Pooling Neural Networks
• Inductive Representation Learning in Large Attributed Graphs
• Label Efficient Semi-Supervised Learning via Graph Filtering
• GRASS: Generative Recursive Autoencoders for Shape Structures
• All About Knowledge Graphs for Actions
• Augmenting correlation structures in spatial data using deep generative models
• Graph Inference Learning for Semi-supervised Classification
• Recursive Social Behavior Graph for Trajectory Prediction
• Higher-Order Attribute-Enhancing Heterogeneous Graph Neural Networks
• A Framework for Generalizing Graph-based Representation Learning Methods
• HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Clouds
• 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
• RigNet: Neural Rigging for Articulated Characters
• Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation
• Bayesian Graph Convolutional Neural Networks using Node Copying
• Deep Representation Learning for Social Network Analysis
• Focusing and Diffusion: Bidirectional Attentive Graph Convolutional Networks for Skeleton-based Action Recognition
• Stability and Generalization of Graph Convolutional Neural Networks
• Text Level Graph Neural Network for Text Classification
• Understanding Graph Neural Networks from Graph Signal Denoising Perspectives
• Hyperbolic Deep Neural Networks: A Survey
• CasGCN: Predicting future cascade growth based on information diffusion graph
• Graph Clustering with Dynamic Embedding
• VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification
• LaplacianNet: Learning on 3D Meshes with Laplacian Encoding and Pooling
• RepGN:Object Detection with Relational Proposal Graph Network
• Bayesian Graph Convolutional Neural Networks Using Non-Parametric Graph Learning
• 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
• Learning Graph While Training: An Evolving Graph Convolutional Neural Network
• Rubik: A Hierarchical Architecture for Efficient Graph Learning
• Convolutional Neural Networks on non-uniform geometrical signals using Euclidean spectral transformation
• Multi-Component Graph Convolutional Collaborative Filtering
• Gromov-Wasserstein Factorization Models for Graph Clustering
• Label-guided Learning for Text Classification
• Learning Color Compatibility in Fashion Outfits
• Attribute Propagation Network for Graph Zero-shot Learning
• Graph Classification via Deep Learning with Virtual Nodes
• TPCN: Temporal Point Cloud Networks for Motion Forecasting
• Face-GCN: A Graph Convolutional Network for 3D Dynamic Face Identification/Recognition
• DAGCN: Dual Attention Graph Convolutional Networks
• Continuous Geodesic Convolutions for Learning on 3D Shapes
• Sparse Diffusion-Convolutional Neural Networks
• Health Status Prediction with Local-Global Heterogeneous Behavior Graph
• Can Graph Neural Networks Go "Online"? An Analysis of Pretraining and Inference
• A Spatial-Temporal Decomposition Based Deep Neural Network for Time Series Forecasting
• DFNets: Spectral CNNs for Graphs with Feedback-Looped Filters
• Topological based classification using graph convolutional networks
• Interpretable Crowd Flow Prediction with Spatial-Temporal Self-Attention
• Can GAN Learn Topological Features of a Graph?
• DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model
• CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning
• Mesh-based Autoencoders for Localized Deformation Component Analysis
• Human Action Recognition with Multi-Laplacian Graph Convolutional Networks
• Exploring Hypergraph Representation on Face Anti-spoofing Beyond 2D Attacks
• Edge-aware Graph Representation Learning and Reasoning for Face Parsing
• Building Segmentation through a Gated Graph Convolutional Neural Network with Deep Structured Feature Embedding
• Graph Highway Networks
• CPR-GCN: Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling of Coronary Arteries
• Dual-Attention Graph Convolutional Network
• Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting
• Topological based classification of paper domains using graph convolutional networks
• GCN-LASE: Towards Adequately Incorporating Link Attributes in Graph Convolutional Networks
• Attribute-guided image generation from layout
• Improved Visual Localization via Graph Smoothing
• GmCN: Graph Mask Convolutional Network
• CoulGAT: An Experiment on Interpretability of Graph Attention Networks
• Tensor Graph Convolutional Networks for Text Classification
• Geometrically Principled Connections in Graph Neural Networks
• Learning Vertex Convolutional Networks for Graph Classification
• Graph Attribute Aggregation Network with Progressive Margin Folding
• Learning the Implicit Semantic Representation on Graph-Structured Data
• Tackling Graphical NLP problems with Graph Recurrent Networks
• Disentangle-based Continual Graph Representation Learning
• Open Knowledge Enrichment for Long-tail Entities
• Multifold Acceleration of Diffusion MRI via Slice-Interleaved Diffusion Encoding (SIDE)
• 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
• Neural Consciousness Flow
• GAIN: Graph Attention & Interaction Network for Inductive Semi-Supervised Learning over Large-scale Graphs
• Graph Analysis and Graph Pooling in the Spatial Domain
• Cut-Based Graph Learning Networks to Discover Compositional Structure of Sequential Video Data
• Graph Neural Networks for Node-Level Predictions
• Fast Mesh Data Augmentation via Chebyshev Polynomial of Spectral filtering
• Action Recognition with Kernel-based Graph Convolutional Networks
• Convolutional Neural Network on Semi-Regular Triangulated Meshes and its Application to Brain Image Data
• Neural Network Approximation of Graph Fourier Transforms for Sparse Sampling of Networked Flow Dynamics
• Lookup subnet based Spatial Graph Convolutional neural Network
• Joint Forecasting and Interpolation of Graph Signals Using Deep Learning
• Intrinsic Geometric Information Transfer Learning on Multiple Graph-Structured Datasets
• Resource Allocation via Graph Neural Networks in Free Space Optical Fronthaul Networks
• Policy Message Passing: A New Algorithm for Probabilistic Graph Inference
• Saliency Prediction with External Knowledge
• Multiple Graph Adversarial Learning
• Deep Learning for Predicting Dynamic Uncertain Opinions in Network Data
• Graph Neural Network for Hamiltonian-Based Material Property Prediction
• GraphSeam: Supervised Graph Learning Framework for Semantic UV Mapping
• Diversified Multiscale Graph Learning with Graph Self-Correction
• Probability Trajectory: One New Movement Description for Trajectory Prediction
• Computational Analysis of Deformable Manifolds: from Geometric Modelling to Deep Learning