Fast Graph Representation Learning with PyTorch Geometric

2019/03/06 by Matthias Fey, Jan Eric Lenssen, Fey, Matthias +1 · 307 citations
Computer Science · #Advanced Graph Neural Networks #Data Visualization and Analytics #Graph Theory and Algorithms

paper · pdf · doi:10.48550/arxiv.1903.02428

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.

Citations

• Variational Graph Auto-Encoders
• PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space

Cited by

• What Matters in Deep Learning for Time Series Forecasting?
• MEGA-CL: A Molecular Foundation Model for Generalizable ADMET Prediction through Graph External Attention and Contrastive Learning
• ParasGB: A Graph Benchmark Suite for Parasitic Estimation on AMS Circuits
• Learned, Relied Upon, or Necessary? Separating Checkpoint Dependence from Task-Level Value in Sheaf GNNs
• Graph Neural Networks for Predicting Solvability of Finite Groups
• Forecasting Ionospheric Irregularities on GNSS Lines of Sight Using Dynamic Graphs with Ephemeris Conditioning
• Plain Transformers are Surprisingly Powerful Link Predictors
• SparScene: Efficient Traffic Scene Representation via Sparse Graph Learning for Large-Scale Trajectory Generation
• SHIRO: Near-Optimal Communication Strategies for Distributed Sparse Matrix Multiplication
• Machine Learning Enabled Graph Analysis of Particulate Composites: Application to Solid-state Battery Cathodes
• Feature-Centric Unsupervised Node Representation Learning Without Homophily Assumption
• Composition-agnostic prediction of self-assembly in multicomponent amphiphile mixtures from molecular structure
• gridfm-datakit-v1: A Python Library for Scalable and Realistic Power Flow and Optimal Power Flow Data Generation
• ProtoFlow: Interpretable and Robust Surgical Workflow Modeling with Learned Dynamic Scene Graph Prototypes
• Torch Geometric Pool: the PyTorch library for pooling in Graph Neural Networks
• Fully Inductive Node Representation Learning via Graph View Transformation
• DAPO: Design Structure-Aware Pass Ordering in High-Level Synthesis with Graph Contrastive and Reinforcement Learning
• Transport Novelty Distance: A Distributional Metric for Evaluating Material Generative Models
• gHAWK: Local and Global Structure Encoding for Scalable Training of Graph Neural Networks on Knowledge Graphs
• Empowering GNNs for Domain Adaptation via Denoising Target Graph
• Hierarchical geometric deep learning enables scalable analysis of molecular dynamics
• NEAT: Neighborhood-Guided, Efficient, Autoregressive Set Transformer for 3D Molecular Generation
• GCoDE: Efficient Device-Edge Co-Inference for GNNs via Architecture-Mapping Co-Search
• Morphling: Fast, Fused, and Flexible GNN Training at Scale
• QuantumCanvas: A Multimodal Benchmark for Visual Learning of Atomic Interactions
• ARES: Anomaly Recognition Model For Edge Streams
• EZ-SP: Fast and Lightweight Superpoint-Based 3D Segmentation
• Provably Powerful Graph Networks
• Nodal Hybrid Neural Solvers for Parametric PDE Systems
• Accelerating Materials Discovery: Learning a Universal Representation of Chemical Processes for Cross-Domain Property Prediction
• Accumulated Local Effects and Graph Neural Networks for link prediction
• Rethinking Message Passing Neural Networks with Diffusion Distance-guided Stress Majorization
• On the Optimality of Discrete Object Naming: a Kinship Case Study
• Resolving Node Identifiability in Graph Neural Processes via Laplacian Spectral Encodings
• Comparative Analysis of Precipitation Forecasts between the ECMWF Artificial Intelligence System (AIFS) and Its Integrated Forecast System (IFS)
• LMSeg: an end-to-end geometric message-passing network on barycentric dualgraphs for large-scale landscape mesh segmentation
• Pre-training Graph Neural Networks on 2D and 3D Molecular Structures by using Multi-View Conditional Information Bottleneck
• GROOT: Graph Edge Re-growth and Partitioning for the Verification of Large Designs in Logic Synthesis
• Protein Set Transformer: a protein-based genome language model to power high-diversity viromics
• Towards Effective, Stealthy, and Persistent Backdoor Attacks Targeting Graph Foundation Models
• PrismSSL: One Interface, Many Modalities; A Single-Interface Library for Multimodal Self-Supervised Learning
• Optimizing Quantum Key Distribution Network Performance using Graph Neural Networks
• HGCN2SP: Hierarchical Graph Convolutional Network for Two-Stage Stochastic Programming
• N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
• Platform-Agnostic Reinforcement Learning Framework for Safe Exploration of Cluttered Environments with Graph Attention
• AutoMate: A Dataset and Learning Approach for Automatic Mating of CAD Assemblies
• Why Physics Still Matters: Improving Machine Learning Prediction of Material Properties with Phonon-Informed Datasets
• PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
• AutoSAGE: Input-Aware CUDA Scheduling for Sparse GNN Aggregation (SpMM/SDDMM) and CSR Attention
• FuseSampleAgg: Fused Neighbor Sampling and Aggregation for Mini-batch GNNs
• Edge-aware baselines for ogbn-proteins in PyTorch Geometric: species-wise normalization, post-hoc calibration, and cost-accuracy trade-offs
• Learning to Solve Resource-Constrained Project Scheduling Problems with Duration Uncertainty using Graph Neural Networks
• InteractiveGNNExplainer: A Visual Analytics Framework for Multi-Faceted Understanding and Probing of Graph Neural Network Predictions
• Understanding graph embedding methods and their applications
• Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures
• Search to aggregate neighborhood for graph neural network
• Improving the Generalisation of Learned Reconstruction Frameworks
• Decimated Framelet System on Graphs and Fast G-Framelet Transforms
• Drug-Target Interaction Prediction with Graph Attention networks
• Graph Condensation for Graph Neural Networks
• Edge Representation Learning with Hypergraphs
• ReCoG: A Deep Learning Framework with Heterogeneous Graph for Interaction-Aware Trajectory Prediction
• Leveraging Compact Satellite Embeddings and Graph Neural Networks for Large-Scale Poverty Mapping
• Simplifying Architecture Search for Graph Neural Network
• Mesh-based Super-resolution of Detonation Flows with Multiscale Graph Transformers
• MIRNet: Integrating Constrained Graph-Based Reasoning with Pre-training for Diagnostic Medical Imaging
• On topological descriptors for graph products
• Direct Molecular Polarizability Prediction with SO(3) Equivariant Local Frame GNNs
• Heterogeneous Graph Transformer
• Learning Time-Varying Graph Signals via Koopman
• Breaking the Dyadic Barrier: Rethinking Fairness in Link Prediction Beyond Demographic Parity
• Linking Warm Dark Matter to Merger Tree Histories via Deep Learning Networks
• FuseFlow: A Fusion-Centric Compilation Framework for Sparse Deep Learning on Streaming Dataflow
• Hardware-Accelerated GNN-based Hit Filtering for the Belle II Level-1 Trigger
• wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation
• GNN-MoE: Context-Aware Patch Routing using GNNs for Parameter-Efficient Domain Generalization
• A Transferable Machine Learning Approach to Predict Quantum Circuit Parameters for Electronic Structure Problems
• BoolSkeleton: Boolean Network Skeletonization via Homogeneous Pattern Reduction
• Graph-Based Alternatives to LLMs for Human Simulation
• X-TRACK: Physics-Aware xLSTM for Realistic Vehicle Trajectory Prediction
• Data-driven Projection Generation for Efficiently Solving Heterogeneous Quadratic Programming Problems
• MeixnerNet: Adaptive and Robust Spectral Graph Neural Networks with Discrete Orthogonal Polynomials
• Traffic4cast 2020 -- Graph Ensemble Net and the Importance of Feature And Loss Function Design for Traffic Prediction
• Towards a predictive spatio-temporal representation of brain data
• NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
• Accelerating 3D Deep Learning with PyTorch3D
• Rethinking pooling in graph neural networks
• ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations
• Strategies for Pre-training Graph Neural Networks
• Multipole Graph Neural Operator for Parametric Partial Differential Equations
• Examining the Efficacy of Graph Neural Network Message-Passing in Regression Contexts
• Automorphism-Induced Non-Canonicity in Top-k Explanations of Graph Neural Networks
• Lifelong Graph Learning
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Understanding GNN Computational Graph: A Coordinated Computation, IO, and Memory Perspective
• Transform2Act: Learning a Transform-and-Control Policy for Efficient Agent Design
• Simultaneous Inference of Past Demography and Selection from the Ancestral Recombination Graph under the Beta Coalescent
• Generalization of Graph Neural Network Models for Distribution Grid Fault Detection
• Inductive Matrix Completion Based on Graph Neural Networks
• Policy-GNN: Aggregation Optimization for Graph Neural Networks
• Graph neural networks: A review of methods and applications
• Causal Effect Inference for Structured Treatments
• GPT-GNN: Generative Pre-Training of Graph Neural Networks
• Graph Geometry Interaction Learning
• On the Significance of Question Encoder Sequence Model in the\n Out-of-Distribution Performance in Visual Question Answering
• Edgeless-GNN: Unsupervised Representation Learning for Edgeless Nodes
• A Meta-Learning Approach for Graph Representation Learning in Multi-Task Settings
• TestRank: Bringing Order into Unlabeled Test Instances for Deep Learning Tasks
• Are Graph Neural Networks Miscalibrated?
• Graph Coarsening with Neural Networks
• Symmetry and Generalisation in Neural Approximations of Renormalisation Transformations
• Knowledge Distillation of a Protein Language Model Yields a Foundational Implicit Solvent Model
• Understanding Graph Neural Networks from Graph Signal Denoising Perspectives
• Graph Neural Networks: Methods, Applications, and Opportunities
• Curvature Graph Neural Network
• MAGNET: A Multi-Graph Attentional Network for Code Clone Detection
• TriDS: AI-native molecular docking framework unified with binding site identification, conformational sampling and scoring
• On Self-Distilling Graph Neural Network
• Understanding Isomorphism Bias in Graph Data Sets
• If You Want to Be Robust, Be Wary of Initialization
• Enhancing Graph Classification Robustness with Singular Pooling
• Self-Attention Graph Pooling
• Adaptive Universal Generalized PageRank Graph Neural Network
• A Hybrid GNN-LSE Method for Fast, Robust, and Physically-Consistent AC Power Flow
• Relieving the Over-Aggregating Effect in Graph Transformers
• Deep Graph Contrastive Representation Learning
• Learning to Triage Taint Flows Reported by Dynamic Program Analysis in Node.js Packages
• Drug-disease networks and drug repurposing
• AegisMCP: Online Graph Intrusion Detection for Tool-Augmented LLMs on Edge Devices
• Robustness Verification of Graph Neural Networks Via Lightweight Satisfiability Testing
• Simple and Efficient Heterogeneous Temporal Graph Neural Network
• Towards Unsupervised Open-Set Graph Domain Adaptation via Dual Reprogramming
• Unifying and Enhancing Graph Transformers via a Hierarchical Mask Framework
• PyKale: Knowledge-Aware Machine Learning from Multiple Sources in Python
• Contrastive Adaptive Propagation Graph Neural Networks for Efficient Graph Learning
• On The Expressive Power of GNN Derivatives
• RoBCtrl: Attacking GNN-Based Social Bot Detectors via Reinforced Manipulation of Bots Control Interaction
• Composition-based Multi-Relational Graph Convolutional Networks
• Graph Neural Networks: A Review of Methods and Applications
• Message Passing on the Edge: Towards Scalable and Expressive GNNs
• Towards Affordable, Adaptive and Automatic GNN Training on CPU-GPU Heterogeneous Platforms
• AGNES: Adaptive Graph Neural Network and Dynamic Programming Hybrid Framework for Real-Time Nanopore Seed Chaining
• Ensemble AnalySis with Interpretable Genomic Prediction (EasiGP): Computational tool for interpreting ensembles of genomic prediction models
• ACE-GNN: Adaptive GNN Co-Inference with System-Aware Scheduling in Dynamic Edge Environments
• Dirichlet Energy Constrained Learning for Deep Graph Neural Networks
• Machine Learning on Graphs: A Model and Comprehensive Taxonomy
• Integrating Sequential and Relational Modeling for User Events: Datasets and Prediction Tasks
• Structured Spectral Graph Representation Learning for Multi-label Abnormality Analysis from 3D CT Scans
• Preserving Core Structures of Social Networks via Information Guided Multi-Step Graph Pruning
• Preference-driven Knowledge Distillation for Few-shot Node Classification
• Open Biomedical Network Benchmark A Python Toolkit for Benchmarking Datasets with Biomedical Networks
• Understanding and Resolving Performance Degradation in Graph Convolutional Networks
• Graph Neural Network Training with Data Tiering
• Knowledge Graph Sparsification for GNN-based Rare Disease Diagnosis
• SPA-GCN: Efficient and Flexible GCN Accelerator with an Application for Graph Similarity Computation
• Zero-Shot Reinforcement Learning on Graphs for Autonomous Exploration Under Uncertainty
• Instance Segmentation GNNs for One-Shot Conformal Tracking at the LHC
• SGAS: Sequential Greedy Architecture Search
• TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs
• Convolution and Graph-based Deep Learning Approaches for Gamma/Hadron Separation in Imaging Atmospheric Cherenkov Telescopes
• Inductive inference of gradient-boosted decision trees on graphs for insurance fraud detection
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning
• Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View
• Test-Time Search in Neural Graph Coarsening Procedures for the Capacitated Vehicle Routing Problem
• STCRpy: a software suite for T-cell receptor structure parsing, interaction profiling, and machine learning dataset preparation
• VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks
• Neural Operator: Graph Kernel Network for Partial Differential Equations
• DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs
• Equivariance by Local Canonicalization: A Matter of Representation
• Are neural scaling laws leading quantum chemistry astray?
• Identifying obfuscated code through graph-based semantic analysis of binary code
• SoREX: Towards Self-Explainable Social Recommendation with Relevant Ego-Path Extraction
• SLogic: Subgraph-Informed Logical Rule Learning for Knowledge Graph Completion
• Neural Message-Passing on Attention Graphs for Hallucination Detection
• Sub-graph Contrast for Scalable Self-Supervised Graph Representation Learning
• Monotonic Transformation Invariant Multi-task Learning
• Weighing the Milky Way and Andromeda with Artificial Intelligence
• Probabilistic Numeric Convolutional Neural Networks
• CrediBench: Building Web-Scale Network Datasets for Information Integrity
• HighwayGraph: Modelling Long-distance Node Relations for Improving General Graph Neural Network
• HELIOS: Hierarchical Exploration for Language-grounded Interaction in Open Scenes
• Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
• Rebuild AC Power Flow Models with Graph Attention Networks
• OmniPlantSeg: Species Agnostic 3D Point Cloud Organ Segmentation for High-Resolution Plant Phenotyping Across Modalities
• Semi-supervised Anomaly Detection on Attributed Graphs
• C²MIL: Synchronizing Semantic and Topological Causalities in Multiple Instance Learning for Robust and Interpretable Survival Analysis
• SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs
• Adaptive Approach to Enhance Machine Learning Scheduling Algorithms During Runtime Using Reinforcement Learning in Metascheduling Applications
• Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization
• Symmetry-adapted graph neural networks for constructing molecular dynamics force fields
• AGL: a Scalable System for Industrial-purpose Graph Machine Learning
• GRIPHIN: grids of pharmacophore interaction fields for affinity prediction
• Message Passing Networks for Molecules with Tetrahedral Chirality
• Analyzing the Performance of Graph Neural Networks with Pipe Parallelism
• LLMulator: Generalizable Cost Modeling for Dataflow Accelerators with Input-Adaptive Control Flow
• ViG-LRGC: Vision Graph Neural Networks with Learnable Reparameterized Graph Construction
• SAS: A Simple, Accurate and Scalable Node Classification Algorithm
• Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforcement Learning
• DeepEOSNet: Capturing the dependency on thermodynamic state in property prediction tasks
• Self-Supervised Discovery of Neural Circuits in Spatially Patterned Neural Responses with Graph Neural Networks
• Automated Cyber Defense with Generalizable Graph-based Reinforcement Learning Agents
• Accelerating Atomic Fine Structure Determination with Graph Reinforcement Learning
• Physics-Informed GCN-LSTM Framework for Long-Term Forecasting of 2D and 3D Microstructure Evolution
• RelEx: A Model-Agnostic Relational Model Explainer
• Metapath- and Entity-aware Graph Neural Network for Recommendation
• From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness
• Graph Neural Networks Including Sparse Interpretability
• Anomaly Detection in Industrial Control Systems Based on Cross-Domain Representation Learning
• Weisfeiler and Lehman Go Topological: Message Passing Simplicial\n Networks
• Drug Repurposing Using Deep Embedded Clustering and Graph Neural Networks
• Optimal message passing for molecular prediction is simple, attentive and spatial
• Learning 3D Representations of Molecular Chirality with Invariance to Bond Rotations
• NuGraph2 with Explainability: Post-hoc Explanations for Geometric Neural Network Predictions
• Vejde: A Framework for Inductive Deep Reinforcement Learning Based on Factor Graph Color Refinement
• A Bi-Level Framework for Learning to Solve Combinatorial Optimization on Graphs
• Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast
• How Attentive are Graph Attention Networks?
• BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignment
• Track Seeding and Labelling with Embedded-space Graph Neural Networks
• Towards Robust Graph Contrastive Learning
• Learning to Reflect and to Beamform for Intelligent Reflecting Surface with Implicit Channel Estimation
• Just Jump: Dynamic Neighborhood Aggregation in Graph Neural Networks
• A guide to machine learning for biologists
• Discovering Symbolic Models from Deep Learning with Inductive Biases
• Disentangling Human Error from the Ground Truth in Segmentation of Medical Images
• TEn-CATG:Text-Enriched Audio-Visual Video Parsing with Multi-Scale Category-Aware Temporal Graph
• Rashomon in the Streets: Explanation Ambiguity in Scene Understanding
• Fast and Accurate RFIC Performance Prediction via Pin Level Graph Neural Networks and Probabilistic Flow
• A Composite-Loss Graph Neural Network for the Multivariate Post-Processing of Ensemble Weather Forecasts
• Quantum-Enhanced Optimization by Warm Starts
• HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware Analysis
• Graph Contrastive Learning versus Untrained Baselines: The Role of Dataset Size
• What Expressivity Theory Misses: Message Passing Complexity for GNNs
• On the Hardness of Learning GNN-based SAT Solvers: The Role of Graph Ricci Curvature
• Independent Prototype Propagation for Zero-Shot Compositionality
• Efficient Colon Cancer Grading with Graph Neural Networks
• GLaRE: A Graph-based Landmark Region Embedding Network for Emotion Recognition
• Controllable Open-ended Question Generation with A New Question Type Ontology
• Weisfeiler and Lehman Go Cellular: CW Networks
• Multimodal Conditional MeshGAN for Personalized Aneurysm Growth Prediction
• Memorization in Graph Neural Networks
• DeeperGCN: All You Need to Train Deeper GCNs
• OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
• Autonomous Exploration Under Uncertainty via Deep Reinforcement Learning on Graphs
• Fast Graph Neural Network for Image Classification
• Statistical Arbitrage in Options Markets by Graph Learning and Synthetic Long Positions
• Nested Graph Neural Networks
• HyperDiff: Hypergraph Guided Diffusion Model for 3D Human Pose Estimation
• Accelerating Image Classification with Graph Convolutional Neural Networks using Voronoi Diagrams
• Explaining Data Anomalies over the NMSSM Parameter Space with Deep Learning Techniques
• Personalized Subgraph Federated Learning with Sheaf Collaboration
• Ranking over Regression for Bayesian Optimization and Molecule Selection
• GCExplainer: Human-in-the-Loop Concept-based Explanations for Graph Neural Networks
• One-Class Intrusion Detection with Dynamic Graphs
• Improving the Expressive Power of Graph Neural Network with Tinhofer Algorithm
• Data-driven particle dynamics: Structure-preserving coarse-graining for emergent behavior in non-equilibrium systems
• Task-Agnostic Morphology Evolution
• DHG-Bench: A Comprehensive Benchmark for Deep Hypergraph Learning
• Graph Learning via Logic-Based Weisfeiler-Leman Variants and Tabularization
• Virtual Sensing for Solder Layer Degradation and Temperature Monitoring in IGBT Modules
• Re-thinking Memory-Bound Limitations in CGRAs
• Contextual Scene Augmentation and Synthesis via GSACNet
• Time-Aware and Transition-Semantic Graph Neural Networks for Interpretable Predictive Business Process Monitoring
• Exact Verification of Graph Neural Networks with Incremental Constraint Solving
• Meta-learning optimizes predictions of missing links in real-world networks
• Morphological Analysis of Semiconductor Microstructures using Skeleton Graphs
• TLV-HGNN: Thinking Like a Vertex for Memory-efficient HGNN Inference
• On Understanding of the Dynamics of Model Capacity in Continual Learning
• Graph Neural Network for Product Recommendation on the Amazon Co-purchase Graph
• Deep Learning for School Dropout Detection: A Comparison of Tabular and Graph-Based Models for Predicting At-Risk Students
• Discriminative structural graph classification
• Learning Geometric-Aware Quadrature Rules for Functional Minimization
• Will You Be Aware? Eye Tracking-Based Modeling of Situational Awareness in Augmented Reality
• Functional Connectivity Graph Neural Networks
• Privacy Risk Predictions Based on Fundamental Understanding of Personal Data and an Evolving Threat Landscape
• Learned Low Precision Graph Neural Networks
• Rubik: A Hierarchical Architecture for Efficient Graph Learning
• Adaptive Riemannian Graph Neural Networks
• GR-Gaussian: Graph-Based Radiative Gaussian Splatting for Sparse-View CT Reconstruction
• Spatio-Temporal Sparsification for General Robust Graph Convolution Networks
• Considering Spatial Structure of the Road Network in Pavement Deterioration Modeling
• Boosting Sensitivity to HH→ bb γγ with Graph Neural Networks and XGBoost
• Explaining GNN Explanations with Edge Gradients
• Quality-of-Service Aware LLM Routing for Edge Computing with Multiple Experts
• Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning
• GraphiT: Encoding Graph Structure in Transformers
• FMIP: Joint Continuous-Integer Flow For Mixed-Integer Linear Programming
• HGCN(O): A Self-Tuning GCN HyperModel Toolkit for Outcome Prediction in Event-Sequence Data
• Graph neural networks for residential location choice: connection to classical logit models
• MGN-Net: a multi-view graph normalizer for integrating heterogeneous\n biological network populations
• A pipeline for fair comparison of graph neural networks in node classification tasks
• Weisfeiler and Leman go sparse: Towards scalable higher-order graph embeddings
• SGQuant: Squeezing the Last Bit on Graph Neural Networks with Specialized Quantization
• Lossless Compression of Structured Convolutional Models via Lifting
• Graph Information Bottleneck
• Gradient-based grand canonical optimization enabled by graph neural networks with fractional atomic existence
• Physics-Informed Graph Neural Networks for Transverse Momentum Estimation in CMS Trigger Systems
• ProGMLP: A Progressive Framework for GNN-to-MLP Knowledge Distillation with Efficient Trade-offs
• Query-Aware Graph Neural Networks for Enhanced Retrieval-Augmented Generation
• Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors
• BiPointNet: Binary Neural Network for Point Clouds
• A Dynamic Reduction Network for Point Clouds
• Self-Supervised Coarsening of Unstructured Grid with Automatic Differentiation
• Progressive Adversarial Learning for Bootstrapping: A Case Study on Entity Set Expansion
• CommPOOL: An Interpretable Graph Pooling Framework for Hierarchical Graph Representation Learning
• Scaling Up Graph Neural Networks Via Graph Coarsening
• Adaptive Visibility Graph Neural Network and its Application in Modulation Classification
• Belief Propagation Neural Networks
• A Framework for Joint Unsupervised Learning of Cluster-Aware Embedding for Heterogeneous Networks

Related

• PyTorch-based Geometric Learning with Non-CUDA Processing Units: Experiences from Intel Gaudi-v2 HPUs
• PyG 2.0: Scalable Learning on Real World Graphs
• pyGSL: A Graph Structure Learning Toolkit
• Learning distributed representations of graphs with Geo2DR
• PyTorch Geometric High Order: A Unified Library for High Order Graph Neural Network