Learning Convolutional Neural Networks for Graphs

Abstract

Numerous important problems can be framed as learning from graph data. We propose a framework for learning convolutional neural networks for arbitrary graphs. These graphs may be undirected, directed, and with both discrete and continuous node and edge attributes. Analogous to image-based convolutional networks that operate on locally connected regions of the input, we present a general approach to extracting locally connected regions from graphs. Using established benchmark data sets, we demonstrate that the learned feature representations are competitive with state of the art graph kernels and that their computation is highly efficient.

To be presented at ICML 2016

Cited by in corpus (163)

• Semi-Supervised Classification with Graph Convolutional Networks
• Inductive Representation Learning on Large Graphs
• Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
• Graph Embedding Techniques, Applications, and Performance: A Survey
• A Review on Deep Learning Techniques Applied to Semantic Segmentation
• Hierarchical Graph Representation Learning with Differentiable Pooling
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Disease Prediction using Graph Convolutional Networks: Application to Autism Spectrum Disorder and Alzheimer's Disease
• MeshCNN: A Network with an Edge
• Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition
• DeepInf: Social Influence Prediction with Deep Learning
• A simple neural network module for relational reasoning
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Graph Neural Networks with convolutional ARMA filters
• The History Began from AlexNet: A Comprehensive Survey on Deep Learning Approaches
• Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks
• Scaling Graph Neural Networks with Approximate PageRank
• Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
• DynGEM: Deep Embedding Method for Dynamic Graphs
• Link Prediction Based on Graph Neural Networks
• Graph networks as learnable physics engines for inference and control
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• DeeperGCN: All You Need to Train Deeper GCNs
• Deep Vessel Segmentation By Learning Graphical Connectivity
• Attention-based Graph Neural Network for Semi-supervised Learning
• Transferring Robustness for Graph Neural Network Against Poisoning Attacks
• Towards Sparse Hierarchical Graph Classifiers
• LanczosNet: Multi-Scale Deep Graph Convolutional Networks
• Graph Neural Networks: Taxonomy, Advances and Trends
• Graph2Seq: Graph to Sequence Learning with Attention-based Neural Networks
• Graph-Bert: Only Attention is Needed for Learning Graph Representations
• Anonymous Walk Embeddings
• Masked Label Prediction: Unified Message Passing Model for Semi-Supervised Classification
• Deep Learning with Topological Signatures
• Predicting Research Trends with Semantic and Neural Networks with an application in Quantum Physics
• Graph Capsule Convolutional Neural Networks
• 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 Graph-Level Representation for Drug Discovery
• A Semantic Loss Function for Deep Learning with Symbolic Knowledge
• Edge Attention-based Multi-Relational Graph Convolutional Networks
• N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials
• Action-Attending Graphic Neural Network
• DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
• Learning Human-Object Interactions by Graph Parsing Neural Networks
• AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter
• Context-Dependent Diffusion Network for Visual Relationship Detection
• Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
• Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
• Structured Sequence Modeling with Graph Convolutional Recurrent Networks
• GRAINS: Generative Recursive Autoencoders for INdoor Scenes
• Graph InfoClust: Leveraging cluster-level node information for unsupervised graph representation learning
• Short term prediction of demand for ride hailing services: A deep learning approach
• Subgraph Neural Networks
• Mining Point Cloud Local Structures by Kernel Correlation and Graph Pooling
• 3D Graph Convolutional Networks with Temporal Graphs: A Spatial Information Free Framework For Traffic Forecasting
• A simple yet effective baseline for non-attributed graph classification
• DeepCas: an End-to-end Predictor of Information Cascades
• NODLINK: An Online System for Fine-Grained APT Attack Detection and Investigation
• Efficient Metropolitan Traffic Prediction Based on Graph Recurrent Neural Network
• Learning non-maximum suppression
• Precise Learning of Source Code Contextual Semantics via Hierarchical Dependence Structure and Graph Attention Networks
• Tracklets Predicting Based Adaptive Graph Tracking
• Deep Learning and Quantum Entanglement: Fundamental Connections with Implications to Network Design
• Skeleton-Based Action Recognition with Spatial Reasoning and Temporal Stack Learning
• From Node Embedding To Community Embedding
• Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition
• Motif-based Convolutional Neural Network on Graphs
• Mean-field theory of graph neural networks in graph partitioning
• Premise Selection for Theorem Proving by Deep Graph Embedding
• G-TAD: Sub-Graph Localization for Temporal Action Detection
• Network representation learning systematic review: ancestors and current development state
• Implementing graph neural networks with TensorFlow-Keras
• Distance Metric Learning using Graph Convolutional Networks: Application to Functional Brain Networks
• Iterative Visual Reasoning Beyond Convolutions
• Improving Graph Attention Networks with Large Margin-based Constraints
• Graph Convolution: A High-Order and Adaptive Approach
• Federated Dynamic GNN with Secure Aggregation
• Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules
• Hierarchical stochastic graphlet embedding for graph-based pattern recognition
• Fused Gromov-Wasserstein distance for structured objects: theoretical foundations and mathematical properties
• Decimated Framelet System on Graphs and Fast G-Framelet Transforms
• Morphological Error Detection in 3D Segmentations
• Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
• Beyond Graph Neural Networks with Lifted Relational Neural Networks
• Provably Powerful Graph Networks
• Person Re-identification with Deep Similarity-Guided Graph Neural Network
• DeepGraph: Graph Structure Predicts Network Growth
• Towards Generalizable Surgical Activity Recognition Using Spatial Temporal Graph Convolutional Networks
• HONE: Higher-Order Network Embeddings
• Interpreting the Mechanism of Synergism for Drug Combinations Using Attention-Based Hierarchical Graph Pooling
• Distance Metric Learning for Graph Structured Data
• FSCNMF: Fusing Structure and Content via Non-negative Matrix Factorization for Embedding Information Networks
• FeaStNet: Feature-Steered Graph Convolutions for 3D Shape Analysis
• When Work Matters: Transforming Classical Network Structures to Graph CNN
• Graph Clustering with Dynamic Embedding
• Feature-Based Classification of Networks
• Global Attention Improves Graph Networks Generalization
• Semi-supervised learning of hierarchical representations of molecules using neural message passing
• On Graph Classification Networks, Datasets and Baselines
• Knowledge-Embedded Representation Learning for Fine-Grained Image Recognition
• Collective Vertex Classification Using Recursive Neural Network
• Dynamics Based Features For Graph Classification
• Data Considerations in Graph Representation Learning for Supply Chain Networks
• Learning Graph While Training: An Evolving Graph Convolutional Neural Network
• Learning Graph-Level Representations with Recurrent Neural Networks
• Outlier Aware Network Embedding for Attributed Networks
• Network Embedding via Deep Prediction Model
• Mini-batch graphs for robust image classification
• Graph Classification via Deep Learning with Virtual Nodes
• Graph2Seq: Scalable Learning Dynamics for Graphs
• Graph Node-Feature Convolution for Representation Learning
• A Lagrangian Approach to Information Propagation in Graph Neural Networks
• Set-to-Sequence Methods in Machine Learning: a Review
• Learning from similarity and information extraction from structured documents
• LinkNet: Relational Embedding for Scene Graph
• JOLO-GCN: Mining Joint-Centered Light-Weight Information for Skeleton-Based Action Recognition
• Dynamic-structured Semantic Propagation Network
• Sparse Diffusion-Convolutional Neural Networks
• DGCNN: Disordered Graph Convolutional Neural Network Based on the Gaussian Mixture Model
• Convolutional neural networks on irregular domains based on approximate vertex-domain translations
• Segmented Graph-Bert for Graph Instance Modeling
• Attentional Multilabel Learning over Graphs: A Message Passing Approach
• Mesh-based Autoencoders for Localized Deformation Component Analysis
• Exploring Hypergraph Representation on Face Anti-spoofing Beyond 2D Attacks
• Get Rid of Suspended Animation Problem: Deep Diffusive Neural Network on Graph Semi-Supervised Classification
• SGR: Self-Supervised Spectral Graph Representation Learning
• GraLSP: Graph Neural Networks with Local Structural Patterns
• Global Weisfeiler-Lehman Graph Kernels
• Learning Vertex Convolutional Networks for Graph Classification
• STEP: Spatial-Temporal Network Security Event Prediction
• Graph Attribute Aggregation Network with Progressive Margin Folding
• Deep Sequence Learning with Auxiliary Information for Traffic Prediction
• Zero-Shot Video Object Segmentation via Attentive Graph Neural Networks
• Message Passing Graph Kernels
• Ensemble Manifold Segmentation for Model Distillation and Semi-supervised Learning
• Gaussian-Induced Convolution for Graphs
• Data-driven Policy on Feasibility Determination for the Train Shunting Problem
• Revisiting convolutional neural network on graphs with polynomial approximations of Laplace-Beltrami spectral filtering
• SNE: Signed Network Embedding
• Graph-Based Method for Anomaly Prediction in Brain Network
• Learning Actor Relation Graphs for Group Activity Recognition
• Interpretable Drug Synergy Prediction with Graph Neural Networks for Human-AI Collaboration in Healthcare
• Graph Self-Supervised Learning with Learnable Structural and Positional Encodings
• GFCN: A New Graph Convolutional Network Based on Parallel Flows
• Deep Constraint-based Propagation in Graph Neural Networks
• Multi-Level Attention Pooling for Graph Neural Networks: Unifying Graph Representations with Multiple Localities
• Table understanding in structured documents
• Sparse hierarchical representation learning on molecular graphs
• Relational dynamic memory networks
• Lookup subnet based Spatial Graph Convolutional neural Network
• Combining exogenous and endogenous signals with a semi-supervised co-attention network for early detection of COVID-19 fake tweets
• Spatio-Temporal Inception Graph Convolutional Networks for Skeleton-Based Action Recognition
• SConE: Siamese Constellation Embedding Descriptor for Image Matching
• Wall Stress Estimation of Cerebral Aneurysm based on Zernike Convolutional Neural Networks
• CoRGi: Content-Rich Graph Neural Networks with Attention
• A Survey of Hierarchy Identification in Social Networks
• Fractional order graph neural network
• Prediction of Hereditary Cancers Using Neural Networks
• Learning Chebyshev Basis in Graph Convolutional Networks for Skeleton-based Action Recognition
• PiNet: Attention Pooling for Graph Classification