Simplifying Graph Convolutional Networks

Abstract

Graph Convolutional Networks (GCNs) and their variants have experienced significant attention and have become the de facto methods for learning graph representations. GCNs derive inspiration primarily from recent deep learning approaches, and as a result, may inherit unnecessary complexity and redundant computation. In this paper, we reduce this excess complexity through successively removing nonlinearities and collapsing weight matrices between consecutive layers. We theoretically analyze the resulting linear model and show that it corresponds to a fixed low-pass filter followed by a linear classifier. Notably, our experimental evaluation demonstrates that these simplifications do not negatively impact accuracy in many downstream applications. Moreover, the resulting model scales to larger datasets, is naturally interpretable, and yields up to two orders of magnitude speedup over FastGCN.

In ICML 2019. Code available at https://github.com/Tiiiger/SGC

References in corpus (7)

• Inductive Representation Learning on Large Graphs
• Graph Neural Networks: A Review of Methods and Applications
• Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning
• LanczosNet: Multi-Scale Deep Graph Convolutional Networks
• Attention Models in Graphs: A Survey
• A simple yet effective baseline for non-attributed graph classification
• Classifier and Exemplar Synthesis for Zero-Shot Learning

Cited by in corpus (367)

• Graph Neural Networks: A Review of Methods and Applications
• Fast Graph Representation Learning with PyTorch Geometric
• Graph Contrastive Learning with Adaptive Augmentation
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• Learning Intents behind Interactions with Knowledge Graph for Recommendation
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• Towards Deeper Graph Neural Networks
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Graph Neural Networks with convolutional ARMA filters
• LightGCN: Simplifying and Powering Graph Convolution Network for Recommendation
• Deep Graph Contrastive Representation Learning
• Deep Learning Based Text Classification: A Comprehensive Review
• Scaling Graph Neural Networks with Approximate PageRank
• Mining Latent Structures for Multimedia Recommendation
• Advances and Challenges in Conversational Recommender Systems: A Survey
• Adversarial Attack and Defense on Graph Data: A Survey
• Hyperbolic Graph Convolutional Neural Networks
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• PairNorm: Tackling Oversmoothing in GNNs
• Simple BERT Models for Relation Extraction and Semantic Role Labeling
• Transferring Robustness for Graph Neural Network Against Poisoning Attacks
• SIGN: Scalable Inception Graph Neural Networks
• Graph Neural Networks Exponentially Lose Expressive Power for Node Classification
• Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs
• Multi-View Graph Convolutional Network for Multimedia Recommendation
• Beyond Homophily in Graph Neural Networks: Current Limitations and Effective Designs
• Deep Learning on Graphs: A Survey
• Graph Neural Networks: Taxonomy, Advances and Trends
• DGCN: Diversified Recommendation with Graph Convolutional Networks
• A Survey on Graph-Based Deep Learning for Computational Histopathology
• Learning on Attribute-Missing Graphs
• OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
• Geom-GCN: Geometric Graph Convolutional Networks
• Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
• Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
• Graph Attention Multi-Layer Perceptron
• Self-supervised Learning on Graphs: Deep Insights and New Direction
• Contrastive Cross-Domain Sequential Recommendation
• FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
• Adversarial Examples on Graph Data: Deep Insights into Attack and Defense
• Learning Feature Recovery Transformer for Occluded Person Re-identification
• End-to-End Differentiable Molecular Mechanics Force Field Construction
• A Survey on Text Classification: From Shallow to Deep Learning
• Multiplex Heterogeneous Graph Convolutional Network
• A Note on Over-Smoothing for Graph Neural Networks
• Filter-informed Spectral Graph Wavelet Networks for Multiscale Feature Extraction and Intelligent Fault Diagnosis
• Adaptive Universal Generalized PageRank Graph Neural Network
• Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition
• TREND: TempoRal Event and Node Dynamics for Graph Representation Learning
• Variational Graph Normalized Auto-Encoders
• Graph Transformer for Recommendation
• Graph Unrolling Networks: Interpretable Neural Networks for Graph Signal Denoising
• Towards Deeper Graph Neural Networks with Differentiable Group Normalization
• A Comparison of Neural Network Architectures for Data-Driven Reduced-Order Modeling
• NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification
• K-Core based Temporal Graph Convolutional Network for Dynamic Graphs
• Directed Graph Convolutional Network
• RoSGAS: Adaptive Social Bot Detection with Reinforced Self-Supervised GNN Architecture Search
• Federated Graph Classification over Non-IID Graphs
• Hyper Meta-Path Contrastive Learning for Multi-Behavior Recommendation
• Accelerating Large Scale Real-Time GNN Inference using Channel Pruning
• Regular Splitting Graph Network for 3D Human Pose Estimation
• GraphAIR: Graph Representation Learning with Neighborhood Aggregation and Interaction
• Implicit Graph Neural Networks
• Multi-level Second-order Few-shot Learning
• Bi-GCN: Binary Graph Convolutional Network
• Graph-less Collaborative Filtering
• GIF: A General Graph Unlearning Strategy via Influence Function
• Revisiting Over-smoothing in Deep GCNs
• High-Level Synthesis Performance Prediction using GNNs: Benchmarking, Modeling, and Advancing
• AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter
• Scalable Graph Neural Networks via Bidirectional Propagation
• Rethinking pooling in graph neural networks
• Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering
• Graph-MLP: Node Classification without Message Passing in Graph
• Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
• Graph Structure Learning for Robust Graph Neural Networks
• Self-supervised Consensus Representation Learning for Attributed Graph
• BertGCN: Transductive Text Classification by Combining GCN and BERT
• ConsRec: Learning Consensus Behind Interactions for Group Recommendation
• Machine-learned molecular mechanics force field for the simulation of protein-ligand systems and beyond
• Topology-Imbalance Learning for Semi-Supervised Node Classification
• EEG-Based Emotion Recognition Using Regularized Graph Neural Networks
• How does spatial structure affect psychological restoration? A method based on Graph Neural Networks and Street View Imagery
• Approximate Graph Propagation
• PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm
• Learning Strong Graph Neural Networks with Weak Information
• Quantum Machine Learning in Drug Discovery: Applications in Academia and Pharmaceutical Industries
• Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
• Graph-less Neural Networks: Teaching Old MLPs New Tricks via Distillation
• Model Degradation Hinders Deep Graph Neural Networks
• How Attentive are Graph Attention Networks?
• ExpandNets: Linear Over-parameterization to Train Compact Convolutional Networks
• Continuous Graph Neural Networks
• A simple yet effective baseline for non-attributed graph classification
• AEGCN: An Autoencoder-Constrained Graph Convolutional Network
• Dirichlet Energy Constrained Learning for Deep Graph Neural Networks
• Personalized Graph Signal Processing for Collaborative Filtering
• Self-supervised Auxiliary Learning with Meta-paths for Heterogeneous Graphs
• Robust Mid-Pass Filtering Graph Convolutional Networks
• Predicting Basin Stability of Power Grids using Graph Neural Networks
• Unbiased Graph Embedding with Biased Graph Observations
• Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration
• Knowledge-refined Denoising Network for Robust Recommendation
• Meta-GNN: On Few-shot Node Classification in Graph Meta-learning
• GraphFL: A Federated Learning Framework for Semi-Supervised Node Classification on Graphs
• UltraGCN: Ultra Simplification of Graph Convolutional Networks for Recommendation
• Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks
• Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation
• Path Integral Based Convolution and Pooling for Graph Neural Networks
• Adversarial Robustness for Code
• On the design space between molecular mechanics and machine learning force fields
• InfoGCL: Information-Aware Graph Contrastive Learning
• Graph Star Net for Generalized Multi-Task Learning
• CatGCN: Graph Convolutional Networks with Categorical Node Features
• AdaGCN: Adaboosting Graph Convolutional Networks into Deep Models
• Graph Neural Networks: Methods, Applications, and Opportunities
• Graph Residual Flow for Molecular Graph Generation
• Boosting-GNN: Boosting Algorithm for Graph Networks on Imbalanced Node Classification
• BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
• Large-Scale Representation Learning on Graphs via Bootstrapping
• FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks
• Interpreting and Unifying Graph Neural Networks with An Optimization Framework
• Active Learning for Graph Neural Networks via Node Feature Propagation
• From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness
• Understanding the Message Passing in Graph Neural Networks via Power Iteration Clustering
• Subgroup Generalization and Fairness of Graph Neural Networks
• Adversarial Attack Framework on Graph Embedding Models with Limited Knowledge
• Scalable Graph Neural Networks for Heterogeneous Graphs
• Lifelong Learning of Graph Neural Networks for Open-World Node Classification
• New Benchmarks for Learning on Non-Homophilous Graphs
• Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning
• GraphWorld: Fake Graphs Bring Real Insights for GNNs
• RSI-Net: Two-Stream Deep Neural Network for Remote Sensing Imagesbased Semantic Segmentation
• Understanding and Resolving Performance Degradation in Graph Convolutional Networks
• Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
• Improving Graph Attention Networks with Large Margin-based Constraints
• Bayesian graph convolutional neural networks via tempered MCMC
• Coupled Layer-wise Graph Convolution for Transportation Demand Prediction
• Independent Prototype Propagation for Zero-Shot Compositionality
• ROD: Reception-aware Online Distillation for Sparse Graphs
• Graph Random Neural Network for Semi-Supervised Learning on Graphs
• Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data
• Meta-Weight Graph Neural Network: Push the Limits Beyond Global Homophily
• Graph-adaptive Rectified Linear Unit for Graph Neural Networks
• Keep It Simple: Graph Autoencoders Without Graph Convolutional Networks
• Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT
• Adversarial Attack on Hierarchical Graph Pooling Neural Networks
• Graph Geometry Interaction Learning
• INMO: A Model-Agnostic and Scalable Module for Inductive Collaborative Filtering
• Graph Neural Networks with Diverse Spectral Filtering
• Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training
• Transition Propagation Graph Neural Networks for Temporal Networks
• Graph Condensation for Graph Neural Networks
• Physical-Virtual Collaboration Modeling for Intra-and Inter-Station Metro Ridership Prediction
• Graph-based Label Propagation for Semi-Supervised Speaker Identification
• HeteGCN: Heterogeneous Graph Convolutional Networks for Text Classification
• A Network Science perspective of Graph Convolutional Networks: A survey
• Beyond Graph Convolutional Network: An Interpretable Regularizer-centered Optimization Framework
• Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks
• Spatial Heterophily Aware Graph Neural Networks
• Graph Representation Learning Beyond Node and Homophily
• CGNN: Traffic Classification with Graph Neural Network
• PAN: Path Integral Based Convolution for Deep Graph Neural Networks
• Improving Graph Neural Networks with Simple Architecture Design
• Dissecting the Diffusion Process in Linear Graph Convolutional Networks
• Quantifying the Alignment of Graph and Features in Deep Learning
• Multi-Scale Contrastive Siamese Networks for Self-Supervised Graph Representation Learning
• Structack: Structure-based Adversarial Attacks on Graph Neural Networks
• Evaluating Deep Graph Neural Networks
• AnchorGAE: General Data Clustering via $O(n)$ Bipartite Graph Convolution
• Geometry-enhanced graph neural network for learning the smoothness of glassy dynamics from static structure
• Single-Node Attacks for Fooling Graph Neural Networks
• USER: Unsupervised Structural Entropy-based Robust Graph Neural Network
• Beltrami Flow and Neural Diffusion on Graphs
• Large-scale graph representation learning with very deep GNNs and self-supervision
• Reliable Node Similarity Matrix Guided Contrastive Graph Clustering
• GraphZoom: A multi-level spectral approach for accurate and scalable graph embedding
• A Large-Scale Database for Graph Representation Learning
• SAC: Accelerating and Structuring Self-Attention via Sparse Adaptive Connection
• Bilinear Graph Neural Network with Neighbor Interactions
• "When they say weed causes depression, but it's your fav antidepressant": Knowledge-aware Attention Framework for Relationship Extraction
• Graph Neural Networks Inspired by Classical Iterative Algorithms
• Sampling methods for efficient training of graph convolutional networks: A survey
• Deep Graph Neural Networks with Shallow Subgraph Samplers
• Node Dependent Local Smoothing for Scalable Graph Learning
• Revisiting Graph based Collaborative Filtering: A Linear Residual Graph Convolutional Network Approach
• Zero-Shot Learning with Common Sense Knowledge Graphs
• Node Injection Attack Based on Label Propagation Against Graph Neural Network
• Training Robust Graph Neural Networks with Topology Adaptive Edge Dropping
• A Light Heterogeneous Graph Collaborative Filtering Model using Textual Information
• Contrastive and Generative Graph Convolutional Networks for Graph-based Semi-Supervised Learning
• Understanding Graph Neural Networks from Graph Signal Denoising Perspectives
• Fisher-Bures Adversary Graph Convolutional Networks
• VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization
• Graph Meta Learning via Local Subgraphs
• Webly Supervised Image Classification with Metadata: Automatic Noisy Label Correction via Visual-Semantic Graph
• Rank Flow Embedding for Unsupervised and Semi-Supervised Manifold Learning
• Graph Neural Bandits
• Fairness-Aware Node Representation Learning
• On the Equivalence of Decoupled Graph Convolution Network and Label Propagation
• On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
• Collapsible Linear Blocks for Super-Efficient Super Resolution
• DyGCN: Dynamic Graph Embedding with Graph Convolutional Network
• SCE: Scalable Network Embedding from Sparsest Cut
• Explainable Natural Language Processing with Matrix Product States
• Generalizing Graph Neural Networks on Out-Of-Distribution Graphs
• Cold Brew: Distilling Graph Node Representations with Incomplete or Missing Neighborhoods
• Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective
• You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks
• Self-Supervised Graph Co-Training for Session-based Recommendation
• Graph Signal Processing for Geometric Data and Beyond: Theory and Applications
• Reconstructing nodal pressures in water distribution systems with graph neural networks
• On Graph Neural Networks versus Graph-Augmented MLPs
• Redundancy-Free Computation Graphs for Graph Neural Networks
• Efficient Graph Deep Learning in TensorFlow with tf_geometric
• "Is depression related to cannabis?": A knowledge-infused model for Entity and Relation Extraction with Limited Supervision
• Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs
• Graph-based Interpolation of Feature Vectors for Accurate Few-Shot Classification
• Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
• Revisiting 2D Convolutional Neural Networks for Graph-based Applications
• L${}^2$-GCN: Layer-Wise and Learned Efficient Training of Graph Convolutional Networks
• FairSample: Training Fair and Accurate Graph Convolutional Neural Networks Efficiently
• Label-GCN: An Effective Method for Adding Label Propagation to Graph Convolutional Networks
• Network In Graph Neural Network
• Low-Rank Subspaces for Unsupervised Entity Linking
• Mask-GVAE: Blind Denoising Graphs via Partition
• Neural Dynamics on Complex Networks
• Deconvolutional Networks on Graph Data
• Cross-GCN: Enhancing Graph Convolutional Network with $k$-Order Feature Interactions
• DGTN: Dual-channel Graph Transition Network for Session-based Recommendation
• Graph-Revised Convolutional Network
• RelEx: A Model-Agnostic Relational Model Explainer
• Deep Representations for Time-varying Brain Datasets
• A Hierarchy of Graph Neural Networks Based on Learnable Local Features
• Deepened Graph Auto-Encoders Help Stabilize and Enhance Link Prediction
• Deoscillated Graph Collaborative Filtering
• Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction
• Modeling multi-scale data via a network of networks
• Item Graph Convolution Collaborative Filtering for Inductive Recommendations
• Simple Truncated SVD based Model for Node Classification on Heterophilic Graphs
• Price-aware Recommendation with Graph Convolutional Networks
• Privacy-Preserving Representation Learning on Graphs: A Mutual Information Perspective
• LT-OCF: Learnable-Time ODE-based Collaborative Filtering
• Traffic4cast 2020 -- Graph Ensemble Net and the Importance of Feature And Loss Function Design for Traffic Prediction
• Spectral Geometric Matrix Completion
• Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks
• Graph-based Village Level Poverty Identification
• GMLP: Building Scalable and Flexible Graph Neural Networks with Feature-Message Passing
• Fundamental Limits of Deep Graph Convolutional Networks
• Unsupervised Deep Manifold Attributed Graph Embedding
• Quaternion Graph Neural Networks
• Adversarial Graph Disentanglement
• Graph Autoencoders with Deconvolutional Networks
• Graph Neighborhood Attentive Pooling
• Semi-supervised Anomaly Detection on Attributed Graphs
• Adaptive Graph Auto-Encoder for General Data Clustering
• Edge Proposal Sets for Link Prediction
• Data Augmentation View on Graph Convolutional Network and the Proposal of Monte Carlo Graph Learning
• Fusion with Hierarchical Graphs for Mulitmodal Emotion Recognition
• Human Action Recognition with Multi-Laplacian Graph Convolutional Networks
• Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
• LookHops: light multi-order convolution and pooling for graph classification
• Climate Modeling with Neural Diffusion Equations
• $p$-Laplacian Based Graph Neural Networks
• Tree Decomposed Graph Neural Network
• Learning by Sampling and Compressing: Efficient Graph Representation Learning with Extremely Limited Annotations
• Spectral Graph Attention Network with Fast Eigen-approximation
• PushNet: Efficient and Adaptive Neural Message Passing
• Interpretable Stability Bounds for Spectral Graph Filters
• A Targeted Universal Attack on Graph Convolutional Network
• Robustness of Graph Neural Networks at Scale
• Neural Bandit with Arm Group Graph
• Parallel Computation of Graph Embeddings
• Order Matters: Probabilistic Modeling of Node Sequence for Graph Generation
• Continuous-Depth Neural Models for Dynamic Graph Prediction
• DeepHGCN: Toward Deeper Hyperbolic Graph Convolutional Networks
• Scalable Deep Graph Clustering with Random-walk based Self-supervised Learning
• Adaptive Gaussian Processes on Graphs via Spectral Graph Wavelets
• Adversarial Attack on Large Scale Graph
• Graph Highway Networks
• Isometric Transformation Invariant and Equivariant Graph Convolutional Networks
• PINE: Universal Deep Embedding for Graph Nodes via Partial Permutation Invariant Set Functions
• Expanding Label Sets for Graph Convolutional Networks
• Graph Neural Networks with Feature and Structure Aware Random Walk
• On the Impact of Communities on Semi-supervised Classification Using Graph Neural Networks
• SoGCN: Second-Order Graph Convolutional Networks
• LG4AV: Combining Language Models and Graph Neural Networks for Author Verification
• LEReg: Empower Graph Neural Networks with Local Energy Regularization
• A Hard Label Black-box Adversarial Attack Against Graph Neural Networks
• A Point Cloud Generative Model via Tree-Structured Graph Convolutions for 3D Brain Shape Reconstruction
• Comparisons of Graph Neural Networks on Cancer Classification Leveraging a Joint of Phenotypic and Genetic Features
• Semi-Supervised Node Classification on Graphs: Markov Random Fields vs. Graph Neural Networks
• Progressive Representative Labeling for Deep Semi-Supervised Learning
• Studying Limits of Explainability by Integrated Gradients for Gene Expression Models
• BiGCN: A Bi-directional Low-Pass Filtering Graph Neural Network
• GCN for HIN via Implicit Utilization of Attention and Meta-paths
• On the Stability of Graph Convolutional Neural Networks under Edge Rewiring
• Graph Belief Propagation Networks
• Edgeless-GNN: Unsupervised Representation Learning for Edgeless Nodes
• Multi-task Self-distillation for Graph-based Semi-Supervised Learning
• A Graph Convolutional Network Composition Framework for Semi-supervised Classification
• Multi-representations Space Separation based Graph-level Anomaly-aware Detection
• Simplification of Graph Convolutional Networks: A Matrix Factorization-based Perspective
• BiTe-GCN: A New GCN Architecture via BidirectionalConvolution of Topology and Features on Text-Rich Networks
• Learning Parametrised Graph Shift Operators
• Learning Conjoint Attentions for Graph Neural Nets
• Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels
• Focus Where It Matters: Graph Selective State Focused Attention Networks
• Sheaf Neural Networks
• Lorentzian Graph Convolutional Networks
• Graph-Based Tri-Attention Network for Answer Ranking in CQA
• Single-Layer Graph Convolutional Networks For Recommendation
• Graphs, Entities, and Step Mixture
• Connecting Graph Convolutional Networks and Graph-Regularized PCA
• Parallel Multi-Graph Convolution Network For Metro Passenger Volume Prediction
• Wide and Deep Graph Neural Networks with Distributed Online Learning
• AKE-GNN: Effective Graph Learning with Adaptive Knowledge Exchange
• Jointly Learnable Data Augmentations for Self-Supervised GNNs
• DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction
• Framework for Designing Filters of Spectral Graph Convolutional Neural Networks in the Context of Regularization Theory
• Contrastive Adaptive Propagation Graph Neural Networks for Efficient Graph Learning
• Trainable Class Prototypes for Few-Shot Learning
• Graph Convolutional Networks Meet with High Dimensionality Reduction
• Totally Deep Support Vector Machines
• Resilient UAV Swarm Communications with Graph Convolutional Neural Network
• PEFA: Parameter-Free Adapters for Large-scale Embedding-based Retrieval Models
• The Power of Graph Convolutional Networks to Distinguish Random Graph Models: Short Version
• Dual Geometric Graph Network (DG2N) -- Iterative network for deformable shape alignment
• Learnt Sparsification for Interpretable Graph Neural Networks
• New Insights into Graph Convolutional Networks using Neural Tangent Kernels
• Bridging the Gap of AutoGraph between Academia and Industry: Analysing AutoGraph Challenge at KDD Cup 2020
• Graph Neural Network for Large-Scale Network Localization
• Sequential Aggregation and Rematerialization: Distributed Full-batch Training of Graph Neural Networks on Large Graphs
• Action Recognition with Kernel-based Graph Convolutional Networks
• Deep graph learning for semi-supervised classification
• Graph-Preserving Grid Layout: A Simple Graph Drawing Method for Graph Classification using CNNs
• SStaGCN: Simplified stacking based graph convolutional networks
• Fully Linear Graph Convolutional Networks for Semi-Supervised Learning and Clustering
• Decoupling feature propagation from the design of graph auto-encoders
• Graph Partner Neural Networks for Semi-Supervised Learning on Graphs
• Fast Graph Learning with Unique Optimal Solutions
• Poisson Kernel Avoiding Self-Smoothing in Graph Convolutional Networks
• Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation
• Scaling Up Graph Neural Networks Via Graph Coarsening
• DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition
• FDGATII : Fast Dynamic Graph Attention with Initial Residual and Identity Mapping
• DNA-GCN: Graph convolutional networks for predicting DNA-protein binding
• Classifying Diagrams and Their Parts using Graph Neural Networks: A Comparison of Crowd-Sourced and Expert Annotations
• Tracing the Propagation Path: A Flow Perspective of Representation Learning on Graphs
• On the Global Self-attention Mechanism for Graph Convolutional Networks
• Co-embedding of Nodes and Edges with Graph Neural Networks
• Classification of vertices on social networks by multiple approaches
• Learn to Propagate Reliably on Noisy Affinity Graphs
• MetAL: Active Semi-Supervised Learning on Graphs via Meta Learning
• Graph Feature Gating Networks
• PiNet: Attention Pooling for Graph Classification
• LFGCN: Levitating over Graphs with Levy Flights
• Label-Aware Graph Convolutional Networks
• Fast Haar Transforms for Graph Neural Networks
• When Product Search Meets Collaborative Filtering: A Hierarchical Heterogeneous Graph Neural Network Approach
• Effective Eigendecomposition based Graph Adaptation for Heterophilic Networks
• Non-Recursive Graph Convolutional Networks
• Towards Quantized Model Parallelism for Graph-Augmented MLPs Based on Gradient-Free ADMM Framework
• Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast