Semi-Supervised Classification with Graph Convolutional Networks

Abstract

We present a scalable approach for semi-supervised learning on graph-structured data that is based on an efficient variant of convolutional neural networks which operate directly on graphs. We motivate the choice of our convolutional architecture via a localized first-order approximation of spectral graph convolutions. Our model scales linearly in the number of graph edges and learns hidden layer representations that encode both local graph structure and features of nodes. In a number of experiments on citation networks and on a knowledge graph dataset we demonstrate that our approach outperforms related methods by a significant margin.

Published as a conference paper at ICLR 2017

References in corpus (1)

• The Weisfeiler-Lehman Method and Graph Isomorphism Testing

Cited by in corpus (132)

• KGAT: Knowledge Graph Attention Network for Recommendation
• Graph Convolutional Matrix Completion
• Variational Graph Auto-Encoders
• A simple neural network module for relational reasoning
• Representation Learning for Attributed Multiplex Heterogeneous Network
• Session-based Social Recommendation via Dynamic Graph Attention Networks
• Self-Attention Graph Pooling
• Fake News Detection on Social Media using Geometric Deep Learning
• Learning Multimodal Graph-to-Graph Translation for Molecular Optimization
• Relational Graph Attention Networks
• Deep Closest Point: Learning Representations for Point Cloud Registration
• Social-BiGAT: Multimodal Trajectory Forecasting using Bicycle-GAN and Graph Attention Networks
• GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding
• Learning to Generate Questions by Learning What not to Generate
• Adaptive Graph Convolutional Neural Networks
• Learning Graph-Level Representation for Drug Discovery
• Learning Graph Representations with Embedding Propagation
• Drug-Drug Adverse Effect Prediction with Graph Co-Attention
• Alchemy: A Quantum Chemistry Dataset for Benchmarking AI Models
• Human Pose Estimation with Spatial Contextual Information
• DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
• MolecularRNN: Generating realistic molecular graphs with optimized properties
• Temporal Graph Convolutional Networks for Automatic Seizure Detection
• Structured Sequence Modeling with Graph Convolutional Recurrent Networks
• MeshGAN: Non-linear 3D Morphable Models of Faces
• All SMILES Variational Autoencoder
• Multiresolution Graph Attention Networks for Relevance Matching
• Geometric deep learning on graphs and manifolds using mixture model CNNs
• GAP: Generalizable Approximate Graph Partitioning Framework
• Meta-GNN: On Few-shot Node Classification in Graph Meta-learning
• PullNet: Open Domain Question Answering with Iterative Retrieval on Knowledge Bases and Text
• SR-LSTM: State Refinement for LSTM towards Pedestrian Trajectory Prediction
• Neural Graph Evolution: Towards Efficient Automatic Robot Design
• Construct Dynamic Graphs for Hand Gesture Recognition via Spatial-Temporal Attention
• Graph Star Net for Generalized Multi-Task Learning
• RAVEN: A Dataset for Relational and Analogical Visual rEasoNing
• A Neural Influence Diffusion Model for Social Recommendation
• A Context-Aware Citation Recommendation Model with BERT and Graph Convolutional Networks
• Premise Selection for Theorem Proving by Deep Graph Embedding
• Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs
• E-LSTM-D: A Deep Learning Framework for Dynamic Network Link Prediction
• Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking
• 3D Dense Face Alignment via Graph Convolution Networks
• Graph Convolution: A High-Order and Adaptive Approach
• HAHE: Hierarchical Attentive Heterogeneous Information Network Embedding
• Efficient Representation Learning Using Random Walks for Dynamic Graphs
• Linkage Based Face Clustering via Graph Convolution Network
• Adversarial Defense Framework for Graph Neural Network
• Can Adversarial Network Attack be Defended?
• Morphological Error Detection in 3D Segmentations
• Capsule Neural Networks for Graph Classification using Explicit Tensorial Graph Representations
• A Behavioral Approach to Visual Navigation with Graph Localization Networks
• InceptionGCN: Receptive Field Aware Graph Convolutional Network for Disease Prediction
• Advancing GraphSAGE with A Data-Driven Node Sampling
• Graph Neural Networks for User Identity Linkage
• Neural Diffusion Model for Microscopic Cascade Prediction
• PH-GCN: Person Re-identification with Part-based Hierarchical Graph Convolutional Network
• Spatio-Temporal Deep Graph Infomax
• DEMO-Net: Degree-specific Graph Neural Networks for Node and Graph Classification
• Uncertainty quantification of molecular property prediction with Bayesian neural networks
• Step Change Improvement in ADMET Prediction with PotentialNet Deep Featurization
• Graph Neural Network for Interpreting Task-fMRI Biomarkers
• Learning Cross-Domain Representation with Multi-Graph Neural Network
• Factor Graph Neural Network
• Stability and Generalization of Graph Convolutional Neural Networks
• Incorporating Biological Knowledge with Factor Graph Neural Network for Interpretable Deep Learning
• Deep Co-Space: Sample Mining Across Feature Transformation for Semi-Supervised Learning
• Generative Graph Convolutional Network for Growing Graphs
• Discriminative structural graph classification
• Learning K-way D-dimensional Discrete Code For Compact Embedding Representations
• Adaptively Connected Neural Networks
• Spatio-temporal Action Recognition: A Survey
• Coherent Comment Generation for Chinese Articles with a Graph-to-Sequence Model
• Redundancy-Free Computation Graphs for Graph Neural Networks
• Graph Convolutional Networks with EigenPooling
• Learning Edge Properties in Graphs from Path Aggregations
• Context-Aware Visual Compatibility Prediction
• Learning Graph While Training: An Evolving Graph Convolutional Neural Network
• All Graphs Lead to Rome: Learning Geometric and Cycle-Consistent Representations with Graph Convolutional Networks
• Learning Topological Representation for Networks via Hierarchical Sampling
• Trimmed Action Recognition, Dense-Captioning Events in Videos, and Spatio-temporal Action Localization with Focus on ActivityNet Challenge 2019
• Neural IR Meets Graph Embedding: A Ranking Model for Product Search
• DAGCN: Dual Attention Graph Convolutional Networks
• ES-CTC: A Deep Neuroevolution Model for Cooperative Intelligent Freeway Traffic Control
• Regional based query in graph active learning
• Point Clouds Learning with Attention-based Graph Convolution Networks
• Data Poisoning Attack against Knowledge Graph Embedding
• Neural Message Passing for Multi-Label Classification
• Deep learning in bioinformatics: introduction, application, and perspective in big data era
• Can GAN Learn Topological Features of a Graph?
• DNN-based Speaker Embedding Using Subjective Inter-speaker Similarity for Multi-speaker Modeling in Speech Synthesis
• Look Again at the Syntax: Relational Graph Convolutional Network for Gendered Ambiguous Pronoun Resolution
• BotGraph: Web Bot Detection Based on Sitemap
• Representation Learning for Heterogeneous Information Networks via Embedding Events
• Graph DNA: Deep Neighborhood Aware Graph Encoding for Collaborative Filtering
• Inferring Javascript types using Graph Neural Networks
• Manifold Graph with Learned Prototypes for Semi-Supervised Image Classification
• Exploring Hypergraph Representation on Face Anti-spoofing Beyond 2D Attacks
• Topological based classification of paper domains using graph convolutional networks
• Graph Representation Learning via Hard and Channel-Wise Attention Networks
• Multimodal Deep Network Embedding with Integrated Structure and Attribute Information
• Data-driven Policy on Feasibility Determination for the Train Shunting Problem
• Uncertainty quantification of molecular property prediction using Bayesian neural network models
• A Unified Deep Learning Formalism For Processing Graph Signals
• NLProlog: Reasoning with Weak Unification for Question Answering in Natural Language
• Generating superpixels using deep image representations
• Graph Attribute Aggregation Network with Progressive Margin Folding
• Imposing Label-Relational Inductive Bias for Extremely Fine-Grained Entity Typing
• Semi-Supervised Graph Embedding for Multi-Label Graph Node Classification
• Graph-Based Method for Anomaly Prediction in Brain Network
• Graph Convolution for Multimodal Information Extraction from Visually Rich Documents
• Unsupervised Open Domain Recognition by Semantic Discrepancy Minimization
• Neural Consciousness Flow
• Progressive Cluster Purification for Transductive Few-shot Learning
• Compositional Structure Learning for Sequential Video Data
• Patch Transformer for Multi-tagging Whole Slide Histopathology Images
• Multi-Label Network Classification via Weighted Personalized Factorizations
• Differentiable Representations For Multihop Inference Rules
• Based on Graph-VAE Model to Predict Student's Score
• Human-Guided Learning of Column Networks: Augmenting Deep Learning with Advice
• Extrapolating paths with graph neural networks
• Learning Large-Scale Topological Maps Using Sum-Product Networks
• Just-in-Time Dynamic-Batching
• Batched Sparse Matrix Multiplication for Accelerating Graph Convolutional Networks
• Induction of Decision Trees based on Generalized Graph Queries
• Multiple Graph Adversarial Learning
• Visualizing Semantic Structures of Sequential Data by Learning Temporal Dependencies
• Semantic Preserving Embeddings for Generalized Graphs
• Embedded-Graph Theory
• Cross-language Citation Recommendation via Hierarchical Representation Learning on Heterogeneous Graph
• Inferring Mesoscale Models of Neural Computation
• Convolutional Neural Network on Semi-Regular Triangulated Meshes and its Application to Brain Image Data