Fast Graph Representation Learning with PyTorch Geometric

Abstract

We introduce PyTorch Geometric, a library for deep learning on irregularly structured input data such as graphs, point clouds and manifolds, built upon PyTorch. In addition to general graph data structures and processing methods, it contains a variety of recently published methods from the domains of relational learning and 3D data processing. PyTorch Geometric achieves high data throughput by leveraging sparse GPU acceleration, by providing dedicated CUDA kernels and by introducing efficient mini-batch handling for input examples of different size. In this work, we present the library in detail and perform a comprehensive comparative study of the implemented methods in homogeneous evaluation scenarios.

ICLR 2019 (RLGM Workshop)

References in corpus (11)

• Geometric deep learning: going beyond Euclidean data
• Simplifying Graph Convolutional Networks
• Variational Graph Auto-Encoders
• Pitfalls of Graph Neural Network Evaluation
• Graph Neural Networks with convolutional ARMA filters
• PCPNET: Learning Local Shape Properties from Raw Point Clouds
• Towards Sparse Hierarchical Graph Classifiers
• Adversarially Regularized Graph Autoencoder for Graph Embedding
• Dynamic Edge-Conditioned Filters in Convolutional Neural Networks on Graphs
• A simple yet effective baseline for non-attributed graph classification
• Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks

Cited by in corpus (450)

• Graph Neural Networks: A Review of Methods and Applications
• Graph Contrastive Learning with Adaptive Augmentation
• The Open Catalyst 2020 (OC20) Dataset and Community Challenges
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• Towards Deeper Graph Neural Networks
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Graph Neural Networks with convolutional ARMA filters
• Deep Graph Contrastive Representation Learning
• Self-Attention Graph Pooling
• Scaling Graph Neural Networks with Approximate PageRank
• A Gentle Introduction to Deep Learning for Graphs
• TUDataset: A collection of benchmark datasets for learning with graphs
• Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
• Global Attention based Graph Convolutional Neural Networks for Improved Materials Property Prediction
• Discovering Symbolic Models from Deep Learning with Inductive Biases
• DeeperGCN: All You Need to Train Deeper GCNs
• Benchmarking Graph Neural Networks
• DeepGCNs: Making GCNs Go as Deep as CNNs
• Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction
• Strategies for Pre-training Graph Neural Networks
• Multipole Graph Neural Operator for Parametric Partial Differential Equations
• Deep Learning on Graphs: A Survey
• Neural Operator: Graph Kernel Network for Partial Differential Equations
• InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
• Composition-based Multi-Relational Graph Convolutional Networks
• OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
• Accelerating 3D Deep Learning with PyTorch3D
• Graph Barlow Twins: A self-supervised representation learning framework for graphs
• Understanding Pooling in Graph Neural Networks
• A Fair Comparison of Graph Neural Networks for Graph Classification
• How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
• Combining Label Propagation and Simple Models Out-performs Graph Neural Networks
• Graph Attention Multi-Layer Perceptron
• Adaptive Propagation Graph Convolutional Network
• Edge Contraction Pooling for Graph Neural Networks
• Machine Learning on Graphs: A Model and Comprehensive Taxonomy
• SPINN: Sparse, Physics-based, and partially Interpretable Neural Networks for PDEs
• Graph Information Bottleneck
• Adaptive Universal Generalized PageRank Graph Neural Network
• On the Bottleneck of Graph Neural Networks and its Practical Implications
• Deep Graph Matching and Searching for Semantic Code Retrieval
• Multilevel Graph Matching Networks for Deep Graph Similarity Learning
• 3D Infomax improves GNNs for Molecular Property Prediction
• A Comparison of Neural Network Architectures for Data-Driven Reduced-Order Modeling
• Julia Language in Machine Learning: Algorithms, Applications, and Open Issues
• Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View
• Disentangling Human Error from the Ground Truth in Segmentation of Medical Images
• Learning Dynamic Graph Representation of Brain Connectome with Spatio-Temporal Attention
• Power Normalizations in Fine-grained Image, Few-shot Image and Graph Classification
• GPT-GNN: Generative Pre-Training of Graph Neural Networks
• Graph Neural Networks for Natural Language Processing: A Survey
• The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey
• Representation Learning for Dynamic Graphs: A Survey
• Automated Machine Learning on Graphs: A Survey
• Graph Signal Processing and Deep Learning: Convolution, Pooling, and Topology
• Modeling Global and Local Node Contexts for Text Generation from Knowledge Graphs
• DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks
• Structure-Feature based Graph Self-adaptive Pooling
• On Representation Knowledge Distillation for Graph Neural Networks
• Auto-GNN: Neural Architecture Search of Graph Neural Networks
• TabularNet: A Neural Network Architecture for Understanding Semantic Structures of Tabular Data
• Integrating Pattern- and Fact-based Fake News Detection via Model Preference Learning
• Graph Neural Network Based Coarse-Grained Mapping Prediction
• DIG: A Turnkey Library for Diving into Graph Deep Learning Research
• Deep Graph Matching Consensus
• Graph Communal Contrastive Learning
• On Learning Sets of Symmetric Elements
• Short-term Hourly Streamflow Prediction with Graph Convolutional GRU Networks
• Rethinking pooling in graph neural networks
• Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures
• Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
• Towards Reusable Surrogate Models: Graph-Based Transfer Learning on Trusses
• Geoopt: Riemannian Optimization in PyTorch
• Topology-Imbalance Learning for Semi-Supervised Node Classification
• Scalable Graph Neural Network Training: The Case for Sampling
• Fully Convolutional Mesh Autoencoder using Efficient Spatially Varying Kernels
• Automating Botnet Detection with Graph Neural Networks
• Digital Twin-based Anomaly Detection with Curriculum Learning in Cyber-physical Systems
• Learning physical properties of anomalous random walks using graph neural networks
• Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
• Is Heterophily A Real Nightmare For Graph Neural Networks To Do Node Classification?
• Subgraph Neural Networks
• GraphiT: Encoding Graph Structure in Transformers
• The LHC Olympics 2020: A Community Challenge for Anomaly Detection in High Energy Physics
• How Attentive are Graph Attention Networks?
• EEG-GCNN: Augmenting Electroencephalogram-based Neurological Disease Diagnosis using a Domain-guided Graph Convolutional Neural Network
• ReCoG: A Deep Learning Framework with Heterogeneous Graph for Interaction-Aware Trajectory Prediction
• EPGAT: Gene Essentiality Prediction With Graph Attention Networks
• Continuous Conditional Random Field Convolution for Point Cloud Segmentation
• Spectral-based Graph Convolutional Network for Directed Graphs
• Relational Graph Convolutional Networks: A Closer Look
• A Flexible Generative Framework for Graph-based Semi-supervised Learning
• Dirichlet Energy Constrained Learning for Deep Graph Neural Networks
• BOTAN: BOnd TArgeting Network for prediction of slow glassy dynamics by machine learning relative motion
• On-device Training: A First Overview on Existing Systems
• Architectural Implications of Graph Neural Networks
• Hierarchical Inter-Message Passing for Learning on Molecular Graphs
• Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
• Graph Neural Network contextual embedding for Deep Learning on Tabular Data
• Efficient Scaling of Dynamic Graph Neural Networks
• Cell Complex Neural Networks
• Path Integral Based Convolution and Pooling for Graph Neural Networks
• Directed Acyclic Graph Neural Networks
• Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree
• Nested Graph Neural Networks
• CatGCN: Graph Convolutional Networks with Categorical Node Features
• AGL: a Scalable System for Industrial-purpose Graph Machine Learning
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
• Inductive Representation Learning on Temporal Graphs
• PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
• Incorporating Symbolic Domain Knowledge into Graph Neural Networks
• Inductive Matrix Completion Based on Graph Neural Networks
• Graph Neural Networks: Methods, Applications, and Opportunities
• BernNet: Learning Arbitrary Graph Spectral Filters via Bernstein Approximation
• Heterogeneous Graph Transformer
• Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
• Semantic and Relational Spaces in Science of Science: Deep Learning Models for Article Vectorisation
• Can Graph Neural Networks Count Substructures?
• Towards Robust Graph Contrastive Learning
• From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness
• On Feature Normalization and Data Augmentation
• Implementing graph neural networks with TensorFlow-Keras
• Non-Local Graph Neural Networks
• Search to aggregate neighborhood for graph neural network
• Predicting fluid-structure interaction with graph neural networks
• Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks
• Scalable Graph Neural Networks for Heterogeneous Graphs
• GraphCL: Contrastive Self-Supervised Learning of Graph Representations
• ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations
• Beyond Low-Pass Filters: Adaptive Feature Propagation on Graphs
• Lifelong Learning of Graph Neural Networks for Open-World Node Classification
• Graph Neural Networks for Knowledge Enhanced Visual Representation of Paintings
• Understanding and Resolving Performance Degradation in Graph Convolutional Networks
• Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning
• IGNNITION: Bridging the Gap Between Graph Neural Networks and Networking Systems
• Independent Prototype Propagation for Zero-Shot Compositionality
• DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs
• Boost then Convolve: Gradient Boosting Meets Graph Neural Networks
• HighAir: A Hierarchical Graph Neural Network-Based Air Quality Forecasting Method
• Learning Graph Structures with Transformer for Multivariate Time Series Anomaly Detection in IoT
• Automated Self-Supervised Learning for Graphs
• Building powerful and equivariant graph neural networks with structural message-passing
• Understanding GNN Computational Graph: A Coordinated Computation, IO, and Memory Perspective
• Probabilistic Dual Network Architecture Search on Graphs
• Decimated Framelet System on Graphs and Fast G-Framelet Transforms
• Graph Geometry Interaction Learning
• Lifelong Learning on Evolving Graphs Under the Constraints of Imbalanced Classes and New Classes
• Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining
• Degree-Quant: Quantization-Aware Training for Graph Neural Networks
• Graph Condensation for Graph Neural Networks
• Mesh convolutional neural networks for wall shear stress estimation in 3D artery models
• Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment
• GraphPAS: Parallel Architecture Search for Graph Neural Networks
• GripNet: Graph Information Propagation on Supergraph for Heterogeneous Graphs
• GCNNMatch: Graph Convolutional Neural Networks for Multi-Object Tracking via Sinkhorn Normalization
• Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations
• Provably Powerful Graph Networks
• Beyond Graph Neural Networks with Lifted Relational Neural Networks
• Edge Representation Learning with Hypergraphs
• Drug-Target Interaction Prediction with Graph Attention networks
• STAR: Sparse Transformer-based Action Recognition
• SHREC 2021: Retrieval and classification of protein surfaces equipped with physical and chemical properties
• Learned Low Precision Graph Neural Networks
• Scalable Surface Reconstruction with Delaunay-Graph Neural Networks
• Heterogeneous Edge-Enhanced Graph Attention Network For Multi-Agent Trajectory Prediction
• Predicting cognitive scores with graph neural networks through sample selection learning
• Message Passing Networks for Molecules with Tetrahedral Chirality
• Belief Propagation Neural Networks
• wsGAT: Weighted and Signed Graph Attention Networks for Link Prediction
• A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs
• Understanding Isomorphism Bias in Graph Data Sets
• A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settings
• BrainNNExplainer: An Interpretable Graph Neural Network Framework for Brain Network based Disease Analysis
• Erdos Goes Neural: an Unsupervised Learning Framework for Combinatorial Optimization on Graphs
• Balancing Multi-level Interactions for Session-based Recommendation
• A Hybrid Similarity-Aware Graph Neural Network with Transformer for Node Classification
• TELESTO: A Graph Neural Network Model for Anomaly Classification in Cloud Services
• Graph Neural Network for Interpreting Task-fMRI Biomarkers
• GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks
• A Large-Scale Database for Graph Representation Learning
• Graph Coarsening with Neural Networks
• TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks
• Supervised Learning and the Finite-Temperature String Method for Computing Committor Functions and Reaction Rates
• DRIFT: Deep Reinforcement Learning for Functional Software Testing
• Intraoperative Liver Surface Completion with Graph Convolutional VAE
• NODE-SELECT: A Graph Neural Network Based On A Selective Propagation Technique
• Equivariant Subgraph Aggregation Networks
• NodePiece: Compositional and Parameter-Efficient Representations of Large Knowledge Graphs
• SGAS: Sequential Greedy Architecture Search
• Point Cloud Instance Segmentation using Probabilistic Embeddings
• Understanding Graph Neural Networks from Graph Signal Denoising Perspectives
• Speaker attribution with voice profiles by graph-based semi-supervised learning
• FeatGraph: A Flexible and Efficient Backend for Graph Neural Network Systems
• Track Seeding and Labelling with Embedded-space Graph Neural Networks
• Understanding graph embedding methods and their applications
• VQ-GNN: A Universal Framework to Scale up Graph Neural Networks using Vector Quantization
• Global Attention Improves Graph Networks Generalization
• Discriminative structural graph classification
• On Graph Classification Networks, Datasets and Baselines
• Syntax-Aware Aspect Level Sentiment Classification with Graph Attention Networks
• Tri-graph Information Propagation for Polypharmacy Side Effect Prediction
• Graph Convolutional Networks for traffic anomaly
• Finite-difference-informed graph network for solving steady-state incompressible flows on block-structured grids
• On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
• Optimization of Graph Neural Networks with Natural Gradient Descent
• Fairness-Aware Node Representation Learning
• mGNN: Generalizing the Graph Neural Networks to the Multilayer Case
• Study of Mass Composition of Cosmic Rays with IceTop and IceCube
• Bi-Level Graph Neural Networks for Drug-Drug Interaction Prediction
• DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling
• A Variational-Sequential Graph Autoencoder for Neural Architecture Performance Prediction
• BiPointNet: Binary Neural Network for Point Clouds
• You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks
• MAAS: Multi-modal Assignation for Active Speaker Detection
• Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization
• Reconstructing nodal pressures in water distribution systems with graph neural networks
• AutoMate: A Dataset and Learning Approach for Automatic Mating of CAD Assemblies
• VersaGNN: a Versatile accelerator for Graph neural networks
• From Local Structures to Size Generalization in Graph Neural Networks
• EnGN: A High-Throughput and Energy-Efficient Accelerator for Large Graph Neural Networks
• Size-Invariant Graph Representations for Graph Classification Extrapolations
• Orthogonal Relation Transforms with Graph Context Modeling for Knowledge Graph Embedding
• Rubik: A Hierarchical Architecture for Efficient Graph Learning
• Revisiting Graph Convolutional Network on Semi-Supervised Node Classification from an Optimization Perspective
• HeterSkinNet: A Heterogeneous Network for Skin Weights Prediction
• Lifelong Graph Learning
• Graph Posterior Network: Bayesian Predictive Uncertainty for Node Classification
• MGN-Net: a multi-view graph normalizer for integrating heterogeneous biological network populations
• AWB-GCN: A Graph Convolutional Network Accelerator with Runtime Workload Rebalancing
• INT: An Inequality Benchmark for Evaluating Generalization in Theorem Proving
• Graph Attention Network based Pruning for Reconstructing 3D Liver Vessel Morphology from Contrasted CT Images
• SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
• Spatial Graph Attention and Curiosity-driven Policy for Antiviral Drug Discovery
• Relation Matters in Sampling: A Scalable Multi-Relational Graph Neural Network for Drug-Drug Interaction Prediction
• GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks
• Simplicial Complex Representation Learning
• Causal Effect Inference for Structured Treatments
• Where are the Keys? -- Learning Object-Centric Navigation Policies on Semantic Maps with Graph Convolutional Networks
• A Graph Based Neural Network Approach to Immune Profiling of Multiplexed Tissue Samples
• Information Obfuscation of Graph Neural Networks
• Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs
• MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning
• RelEx: A Model-Agnostic Relational Model Explainer
• Lymph Node Graph Neural Networks for Cancer Metastasis Prediction
• Deep Mesh Prior: Unsupervised Mesh Restoration using Graph Convolutional Networks
• Graph-Revised Convolutional Network
• Simplifying Architecture Search for Graph Neural Network
• Are Graph Neural Networks Miscalibrated?
• Learning to Reflect and to Beamform for Intelligent Reflecting Surface with Implicit Channel Estimation
• Benchmarking Graph Neural Networks on Link Prediction
• A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects
• Chickenpox Cases in Hungary: a Benchmark Dataset for Spatiotemporal Signal Processing with Graph Neural Networks
• Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes
• Self-supervised Representation Learning for Evolutionary Neural Architecture Search
• Multi-view Hybrid Graph Convolutional Network for Volume-to-mesh Reconstruction in Cardiovascular MRI
• Positional Encoder Graph Neural Networks for Geographic Data
• GE-SpMM: General-purpose Sparse Matrix-Matrix Multiplication on GPUs for Graph Neural Networks
• Ranking over Regression for Bayesian Optimization and Molecule Selection
• Red-QAOA: Efficient Variational Optimization through Circuit Reduction
• QT-Routenet: Improved GNN generalization to larger 5G networks by fine-tuning predictions from queueing theory
• Probabilistic Numeric Convolutional Neural Networks
• Utilising Graph Machine Learning within Drug Discovery and Development
• Ivy: Templated Deep Learning for Inter-Framework Portability
• Graph Representation learning for Audio & Music genre Classification
• Net2: A Graph Attention Network Method Customized for Pre-Placement Net Length Estimation
• Calibrating and Improving Graph Contrastive Learning
• Link Prediction using Graph Neural Networks for Master Data Management
• Node Feature Extraction by Self-Supervised Multi-scale Neighborhood Prediction
• Weisfeiler and Lehman Go Cellular: CW Networks
• Tiered Graph Autoencoders with PyTorch Geometric for Molecular Graphs
• Self-supervised Graph Representation Learning via Bootstrapping
• Nudge Attacks on Point-Cloud DNNs
• Traffic4cast 2020 -- Graph Ensemble Net and the Importance of Feature And Loss Function Design for Traffic Prediction
• Attention-Based Learning on Molecular Ensembles
• Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design
• Direct Feedback Alignment Scales to Modern Deep Learning Tasks and Architectures
• Exploiting Edge-Oriented Reasoning for 3D Point-based Scene Graph Analysis
• Multitask Learning On Graph Neural Networks Applied To Molecular Property Predictions
• Policy-GNN: Aggregation Optimization for Graph Neural Networks
• Quaternion Graph Neural Networks
• Semi-supervised Anomaly Detection on Attributed Graphs
• Integrating Sensing and Communication in Cellular Networks via NR Sidelink
• CogDL: A Comprehensive Library for Graph Deep Learning
• Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisions
• Generalizing Downsampling from Regular Data to Graphs
• Uncertainty-aware Attention Graph Neural Network for Defending Adversarial Attacks
• Message Passing Query Embedding
• Metapath- and Entity-aware Graph Neural Network for Recommendation
• Refactoring Policy for Compositional Generalizability using Self-Supervised Object Proposals
• Task-Agnostic Morphology Evolution
• Improving Molecular Graph Neural Network Explainability with Orthonormalization and Induced Sparsity
• Node2Seq: Towards Trainable Convolutions in Graph Neural Networks
• A pipeline for fair comparison of graph neural networks in node classification tasks
• Contextualised Graph Attention for Improved Relation Extraction
• Wasserstein Embedding for Graph Learning
• Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
• A Dynamic Reduction Network for Point Clouds
• Transformer-based Machine Learning for Fast SAT Solvers and Logic Synthesis
• Reconstruction for Powerful Graph Representations
• $p$-Laplacian Based Graph Neural Networks
• Roto-translated Local Coordinate Frames For Interacting Dynamical Systems
• CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning
• Train on Small, Play the Large: Scaling Up Board Games with AlphaZero and GNN
• Graph Neural Networks for Scalable Radio Resource Management: Architecture Design and Theoretical Analysis
• Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks
• Graph and Recurrent Neural Network-based Vehicle Trajectory Prediction For Highway Driving
• ZIPPER: Exploiting Tile- and Operator-level Parallelism for General and Scalable Graph Neural Network Acceleration
• Learning to Pool in Graph Neural Networks for Extrapolation
• Implicit SVD for Graph Representation Learning
• Wireless Link Scheduling via Graph Representation Learning: A Comparative Study of Different Supervision Levels
• Releasing Graph Neural Networks with Differential Privacy Guarantees
• Deep Policies for Online Bipartite Matching: A Reinforcement Learning Approach
• An Empirical Study of Graph Contrastive Learning
• Optimization-Based Algebraic Multigrid Coarsening Using Reinforcement Learning
• Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking
• Explainable Link Prediction for Privacy-Preserving Contact Tracing
• Breaking the Expressive Bottlenecks of Graph Neural Networks
• BrainNetGAN: Data augmentation of brain connectivity using generative adversarial network for dementia classification
• PyTorch-Direct: Enabling GPU Centric Data Access for Very Large Graph Neural Network Training with Irregular Accesses
• On Self-Distilling Graph Neural Network
• Unsupervised Joint $k$-node Graph Representations with Compositional Energy-Based Models
• GraphGallery: A Platform for Fast Benchmarking and Easy Development of Graph Neural Networks Based Intelligent Software
• When Contrastive Learning Meets Active Learning: A Novel Graph Active Learning Paradigm with Self-Supervision
• Graph Classification by Mixture of Diverse Experts
• Lossless Compression of Structured Convolutional Models via Lifting
• Graph Neural Networks Including Sparse Interpretability
• Isometric Transformation Invariant and Equivariant Graph Convolutional Networks
• Mesorasi: Architecture Support for Point Cloud Analytics via Delayed-Aggregation
• Learning distributed representations of graphs with Geo2DR
• Towards a predictive spatio-temporal representation of brain data
• HighwayGraph: Modelling Long-distance Node Relations for Improving General Graph Neural Network
• HyGCN: A GCN Accelerator with Hybrid Architecture
• Deep learning of material transport in complex neurite networks
• SGQuant: Squeezing the Last Bit on Graph Neural Networks with Specialized Quantization
• SoGCN: Second-Order Graph Convolutional Networks
• Distributed Optimization of Graph Convolutional Network using Subgraph Variance
• Are Hyperbolic Representations in Graphs Created Equal?
• Particle Graph Autoencoders and Differentiable, Learned Energy Mover's Distance
• Curriculum learning for multilevel budgeted combinatorial problems
• A Graph Deep Learning Framework for High-Level Synthesis Design Space Exploration
• Aiding Medical Diagnosis Through the Application of Graph Neural Networks to Functional MRI Scans
• Deep Generative Modeling in Network Science with Applications to Public Policy Research
• Message Passing in Graph Convolution Networks via Adaptive Filter Banks
• Embedding Signals on Knowledge Graphs with Unbalanced Diffusion Earth Mover's Distance
• A Framework for Joint Unsupervised Learning of Cluster-Aware Embedding for Heterogeneous Networks
• User Preference-aware Fake News Detection
• LEReg: Empower Graph Neural Networks with Local Energy Regularization
• Embedding Graphs on Grassmann Manifold
• Controllable Open-ended Question Generation with A New Question Type Ontology
• Efficient Colon Cancer Grading with Graph Neural Networks
• ARENA: Asynchronous Reconfigurable Accelerator Ring to Enable Data-Centric Parallel Computing
• When to Talk: Chatbot Controls the Timing of Talking during Multi-turn Open-domain Dialogue Generation
• Adaptive Visibility Graph Neural Network and its Application in Modulation Classification
• On the combination of graph data for assessing thin-file borrowers' creditworthiness
• Efficient and Interpretable Robot Manipulation with Graph Neural Networks
• Edgeless-GNN: Unsupervised Representation Learning for Edgeless Nodes
• Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning
• SPA-GCN: Efficient and Flexible GCN Accelerator with an Application for Graph Similarity Computation
• Neuralizing Efficient Higher-order Belief Propagation
• Contrastive Adaptive Propagation Graph Neural Networks for Efficient Graph Learning
• Analyzing the Performance of Graph Neural Networks with Pipe Parallelism
• Graph Information Vanishing Phenomenon inImplicit Graph Neural Networks
• Dual Geometric Graph Network (DG2N) -- Iterative network for deformable shape alignment
• Catastrophic Forgetting in Deep Graph Networks: an Introductory Benchmark for Graph Classification
• Graph Partitioning and Sparse Matrix Ordering using Reinforcement Learning and Graph Neural Networks
• Gini in a Bottleneck: Sparse Molecular Representations for Graph Convolutional Neural Networks
• Geometric Graph Representations and Geometric Graph Convolutions for Deep Learning on Three-Dimensional (3D) Graphs
• On Graph Neural Network Ensembles for Large-Scale Molecular Property Prediction
• Partition and Code: learning how to compress graphs
• DPC: Unsupervised Deep Point Correspondence via Cross and Self Construction
• Connecting Graph Convolutional Networks and Graph-Regularized PCA
• Decentralized Statistical Inference with Unrolled Graph Neural Networks
• GeoGraph: Learning graph-based multi-view object detection with geometric cues end-to-end
• Combinatorial Learning of Graph Edit Distance via Dynamic Embedding
• Node Feature Kernels Increase Graph Convolutional Network Robustness
• Explainable Biomedical Recommendations via Reinforcement Learning Reasoning on Knowledge Graphs
• Weighing the Milky Way and Andromeda with Artificial Intelligence
• TreeRNN: Topology-Preserving Deep GraphEmbedding and Learning
• Autonomous Exploration Under Uncertainty via Deep Reinforcement Learning on Graphs
• Instance Segmentation GNNs for One-Shot Conformal Tracking at the LHC
• Network Generation with Differential Privacy
• Global Neighbor Sampling for Mixed CPU-GPU Training on Giant Graphs
• Optimizing Memory Efficiency of Graph Neural Networks on Edge Computing Platforms
• My House, My Rules: Learning Tidying Preferences with Graph Neural Networks
• Wireless 3D Point Cloud Delivery Using Deep Graph Neural Networks
• Distance-Geometric Graph Convolutional Network (DG-GCN) for Three-Dimensional (3D) Graphs
• Program-to-Circuit: Exploiting GNNs for Program Representation and Circuit Translation
• Topological Graph Neural Networks
• Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration Under Uncertainty
• Symmetry-adapted graph neural networks for constructing molecular dynamics force fields
• NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
• A Semi-Supervised Approach for Abnormal Event Prediction on Large Operational Network Time-Series Data
• End-to-End Learning from Complex Multigraphs with Latent-Graph Convolutional Networks
• SAS: A Simple, Accurate and Scalable Node Classification Algorithm
• Torch-Points3D: A Modular Multi-Task Frameworkfor Reproducible Deep Learning on 3D Point Clouds
• Approximate Knowledge Graph Query Answering: From Ranking to Binary Classification
• Graph Feature Gating Networks
• Node Attribute Completion in Knowledge Graphs with Multi-Relational Propagation
• Walk2Map: Extracting Floor Plans from Indoor Walk Trajectories
• A Weighted Heterogeneous Graph Based Dialogue System
• Improving Graph Property Prediction with Generalized Readout Functions
• Towards a Taxonomy of Graph Learning Datasets
• ClueReader: Heterogeneous Graph Attention Network for Multi-hop Machine Reading Comprehension
• On the Significance of Question Encoder Sequence Model in the Out-of-Distribution Performance in Visual Question Answering
• Spatio-Temporal Sparsification for General Robust Graph Convolution Networks
• OpenGraphGym-MG: Using Reinforcement Learning to Solve Large Graph Optimization Problems on MultiGPU Systems
• Contextual Scene Augmentation and Synthesis via GSACNet
• Pseudoinverse Graph Convolutional Networks: Fast Filters Tailored for Large Eigengaps of Dense Graphs and Hypergraphs
• StairwayGraphNet for Inter- and Intra-modality Multi-resolution Brain Graph Alignment and Synthesis
• Improving the Expressive Power of Graph Neural Network with Tinhofer Algorithm
• Recurrent Brain Graph Mapper for Predicting Time-Dependent Brain Graph Evaluation Trajectory
• Semi-Supervised Deep Learning for Multiplex Networks
• Characterizing and Understanding GCNs on GPU
• Unsupervised Diffeomorphic Surface Registration and Non-Linear Modelling
• Pooling in Graph Convolutional Neural Networks
• Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion
• Speaker diarization with session-level speaker embedding refinement using graph neural networks
• Adapted and Oversegmenting Graphs: Application to Geometric Deep Learning
• Graph Neural Network for Hamiltonian-Based Material Property Prediction
• A machine learning approach to commutative algebra: Distinguishing table vs non-table ideals
• Graph Neural Network Training with Data Tiering
• Isometric Graph Neural Networks
• LSP : Acceleration and Regularization of Graph Neural Networks via Locality Sensitive Pruning of Graphs
• Deep Iterative Surface Normal Estimation
• Link Analysis meets Ontologies: Are Embeddings the Answer?
• Deep Grouping Model for Unified Perceptual Parsing
• Explaining machine-learned particle-flow reconstruction
• Label-Consistency based Graph Neural Networks for Semi-supervised Node Classification
• Dual GNNs: Graph Neural Network Learning with Limited Supervision
• Curvature Graph Neural Network
• Non-isomorphic Inter-modality Graph Alignment and Synthesis for Holistic Brain Mapping
• Tesla-Rapture: A Lightweight Gesture Recognition System from mmWave Radar Point Clouds
• Cross-lingual Transfer for Text Classification with Dictionary-based Heterogeneous Graph
• Training Graph Neural Networks by Graphon Estimation
• Scalable Adversarial Attack on Graph Neural Networks with Alternating Direction Method of Multipliers
• An FEA surrogate model with Boundary Oriented Graph Embedding approach
• ICLR 2021 Challenge for Computational Geometry & Topology: Design and Results
• U-GAT: Multimodal Graph Attention Network for COVID-19 Outcome Prediction
• SN-Graph: a Minimalist 3D Object Representation for Classification
• Experiments with graph convolutional networks for solving the vertex $p$-center problem
• Graph Convolutional Policy for Solving Tree Decomposition via Reinforcement Learning Heuristics
• Graph Convolutional Memory using Topological Priors
• Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast
• Scaling Up Graph Neural Networks Via Graph Coarsening
• Survey of Image Based Graph Neural Networks
• Synthesizing Human Faces using Latent Space Factorization and Local Weights (Extended Version)
• PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python
• Fast Graph Learning with Unique Optimal Solutions
• Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretraining
• 3D Meta Point Signature: Learning to Learn 3D Point Signature for 3D Dense Shape Correspondence