A Comprehensive Survey on Graph Neural Networks

Abstract

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are typically represented in the Euclidean space. However, there is an increasing number of applications where data are generated from non-Euclidean domains and are represented as graphs with complex relationships and interdependency between objects. The complexity of graph data has imposed significant challenges on existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this survey, we provide a comprehensive overview of graph neural networks (GNNs) in data mining and machine learning fields. We propose a new taxonomy to divide the state-of-the-art graph neural networks into four categories, namely recurrent graph neural networks, convolutional graph neural networks, graph autoencoders, and spatial-temporal graph neural networks. We further discuss the applications of graph neural networks across various domains and summarize the open source codes, benchmark data sets, and model evaluation of graph neural networks. Finally, we propose potential research directions in this rapidly growing field.

Minor revision (updated tables and references)

References in corpus (20)

• DeepWalk: Online Learning of Social Representations
• LINE: Large-scale Information Network Embedding
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Geometric deep learning: going beyond Euclidean data
• Spatio-Temporal Graph Convolutional Networks: A Deep Learning Framework for Traffic Forecasting
• Automatic chemical design using a data-driven continuous representation of molecules
• Graph Convolutional Neural Networks for Web-Scale Recommender Systems
• Graph Embedding Techniques, Applications, and Performance: A Survey
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Discrete Signal Processing on Graphs
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Graph Convolutional Matrix Completion
• Discrete Signal Processing on Graphs: Sampling Theory
• DeepInf: Social Influence Prediction with Deep Learning
• Predicting multicellular function through multi-layer tissue networks
• Large-Scale Learnable Graph Convolutional Networks
• MolGAN: An implicit generative model for small molecular graphs
• Robust Spatial Filtering with Graph Convolutional Neural Networks
• Watch Your Step: Learning Node Embeddings via Graph Attention

Cited by in corpus (493)

• Deep Neural Networks and Tabular Data: A Survey
• A Comprehensive Survey on Graph Anomaly Detection with Deep Learning
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• Graph Self-Supervised Learning: A Survey
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
• Graph Learning: A Survey
• E-GraphSAGE: A Graph Neural Network based Intrusion Detection System for IoT
• A Comprehensive Survey on Deep Graph Representation Learning
• Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
• FedGNN: Federated Graph Neural Network for Privacy-Preserving Recommendation
• Graph Representation Learning in Biomedicine
• MST-GAT: A Multimodal Spatial-Temporal Graph Attention Network for Time Series Anomaly Detection
• How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey
• Higher-Order Explanations of Graph Neural Networks via Relevant Walks
• Graph-Based Deep Learning for Medical Diagnosis and Analysis: Past, Present and Future
• Spatio-temporal graph neural networks for multi-site PV power forecasting
• Global field reconstruction from sparse sensors with Voronoi tessellation-assisted deep learning
• Anomal-E: A Self-Supervised Network Intrusion Detection System based on Graph Neural Networks
• DGL-LifeSci: An Open-Source Toolkit for Deep Learning on Graphs in Life Science
• Generative and Contrastive Self-Supervised Learning for Graph Anomaly Detection
• DeepGCNs: Making GCNs Go as Deep as CNNs
• A Survey of Machine Learning for Computer Architecture and Systems
• Combinatorial Optimization with Physics-Inspired Graph Neural Networks
• Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction
• GCNs-Net: A Graph Convolutional Neural Network Approach for Decoding Time-resolved EEG Motor Imagery Signals
• Super-Resolution Analysis via Machine Learning: A Survey for Fluid Flows
• Remote Sensing Cross-Modal Text-Image Retrieval Based on Global and Local Information
• A Review of Location Encoding for GeoAI: Methods and Applications
• Joint Detection and Localization of Stealth False Data Injection Attacks in Smart Grids using Graph Neural Networks
• Learning Combinatorial Optimization on Graphs: A Survey with Applications to Networking
• A Survey of Knowledge Tracing: Models, Variants, and Applications
• NetLLM: Adapting Large Language Models for Networking
• Graph Neural Networks: Taxonomy, Advances and Trends
• Graph Neural Networks for an Accurate and Interpretable Prediction of the Properties of Polycrystalline Materials
• Probabilistic neural networks for fluid flow surrogate modeling and data recovery
• Multimodal Data Integration for Oncology in the Era of Deep Neural Networks: A Review
• Graph Convolutional Subspace Clustering: A Robust Subspace Clustering Framework for Hyperspectral Image
• LSTTN: A Long-Short Term Transformer-based Spatio-temporal Neural Network for Traffic Flow Forecasting
• TCGL: Temporal Contrastive Graph for Self-supervised Video Representation Learning
• Graph Neural Networks for Financial Fraud Detection: A Review
• Taking the Next Step with Generative Artificial Intelligence: The Transformative Role of Multimodal Large Language Models in Science Education
• FedNI: Federated Graph Learning with Network Inpainting for Population-Based Disease Prediction
• Automatic autism spectrum disorder detection using artificial intelligence methods with MRI neuroimaging: A review
• Temporal and Heterogeneous Graph Neural Network for Financial Time Series Prediction
• Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementation
• Attention-based graph neural networks: a survey
• OmiEmbed: a unified multi-task deep learning framework for multi-omics data
• A survey on the development status and application prospects of knowledge graph in smart grids
• GraphMFT: A Graph Network based Multimodal Fusion Technique for Emotion Recognition in Conversation
• SR-GNN: Spatial Relation-aware Graph Neural Network for Fine-Grained Image Categorization
• Trustworthy Graph Neural Networks: Aspects, Methods and Trends
• TodyNet: Temporal Dynamic Graph Neural Network for Multivariate Time Series Classification
• Spatial-Temporal Interactive Dynamic Graph Convolution Network for Traffic Forecasting
• Adaptive Propagation Graph Convolutional Network
• Self-Supervised Temporal Graph learning with Temporal and Structural Intensity Alignment
• FairDrop: Biased Edge Dropout for Enhancing Fairness in Graph Representation Learning
• Predicting Research Trends with Semantic and Neural Networks with an application in Quantum Physics
• Applications of knowledge graphs for food science and industry
• Investigating and Mitigating Degree-Related Biases in Graph Convolutional Networks
• Anomaly detection with Convolutional Graph Neural Networks
• Filter-informed Spectral Graph Wavelet Networks for Multiscale Feature Extraction and Intelligent Fault Diagnosis
• Generalization techniques of neural networks for fluid flow estimation
• Second-Order Pooling for Graph Neural Networks
• Density of States Prediction for Materials Discovery via Contrastive Learning from Probabilistic Embeddings
• DualVGR: A Dual-Visual Graph Reasoning Unit for Video Question Answering
• HUNTER: AI based Holistic Resource Management for Sustainable Cloud Computing
• TREND: TempoRal Event and Node Dynamics for Graph Representation Learning
• Engineering Semantic Communication: A Survey
• Deep Reinforcement Learning for Turbulence Modeling in Large Eddy Simulations
• Deep Graph Matching and Searching for Semantic Code Retrieval
• General Purpose Artificial Intelligence Systems (GPAIS): Properties, Definition, Taxonomy, Societal Implications and Responsible Governance
• Multilevel Graph Matching Networks for Deep Graph Similarity Learning
• Deep Graph-level Anomaly Detection by Glocal Knowledge Distillation
• Data-Driven Design-by-Analogy: State of the Art and Future Directions
• A Comparison of Neural Network Architectures for Data-Driven Reduced-Order Modeling
• Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast
• Robot Cooking with Stir-fry: Bimanual Non-prehensile Manipulation of Semi-fluid Objects
• Multi-Behavior Enhanced Recommendation with Cross-Interaction Collaborative Relation Modeling
• On Proximity and Structural Role-based Embeddings in Networks: Misconceptions, Techniques, and Applications
• Graph Neural Networks for Multimodal Single-Cell Data Integration
• Learning Fair Node Representations with Graph Counterfactual Fairness
• NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification
• Graph Autoencoders for Embedding Learning in Brain Networks and Major Depressive Disorder Identification
• AI-driven inverse design of materials: Past, present and future
• Multi-Behavior Graph Neural Networks for Recommender System
• Graph Neural Networks for Text Classification: A Survey
• A Survey of Large Language Models for Graphs
• The Evolution of Distributed Systems for Graph Neural Networks and their Origin in Graph Processing and Deep Learning: A Survey
• Graph Signal Processing and Deep Learning: Convolution, Pooling, and Topology
• Unsupervised Deep Learning for IoT Time Series
• Histogram Layers for Texture Analysis
• Coupling Model-Driven and Data-Driven Methods for Remote Sensing Image Restoration and Fusion
• MedGCN: Medication recommendation and lab test imputation via graph convolutional networks
• Augmenting Low-Resource Text Classification with Graph-Grounded Pre-training and Prompting
• SCENE: Reasoning about Traffic Scenes using Heterogeneous Graph Neural Networks
• Large-scale Personalized Video Game Recommendation via Social-aware Contextualized Graph Neural Network
• Knowledge Learning with Crowdsourcing: A Brief Review and Systematic Perspective
• A Survey on Hyperlink Prediction
• A Survey on Influence Maximization: From an ML-Based Combinatorial Optimization
• Graph Neural Networks for Pressure Estimation in Water Distribution Systems
• Physical Pooling Functions in Graph Neural Networks for Molecular Property Prediction
• A Temporal Graph Neural Network for Cyber Attack Detection and Localization in Smart Grids
• Structural engineering from an inverse problems perspective
• Continuous Human Action Recognition for Human-Machine Interaction: A Review
• ChatGPT Informed Graph Neural Network for Stock Movement Prediction
• On the Trade-off between Over-smoothing and Over-squashing in Deep Graph Neural Networks
• Toward cross-subject and cross-session generalization in EEG-based emotion recognition: Systematic review, taxonomy, and methods
• AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter
• Inverse design of glass structure with deep graph neural networks
• SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization
• MAgNET: A Graph U-Net Architecture for Mesh-Based Simulations
• Link Scheduling using Graph Neural Networks
• Charged particle tracking via edge-classifying interaction networks
• Sparse sensor reconstruction of vortex-impinged airfoil wake with machine learning
• Uncertainty Quantification of Sparse Travel Demand Prediction with Spatial-Temporal Graph Neural Networks
• Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering
• Source Localization of Graph Diffusion via Variational Autoencoders for Graph Inverse Problems
• Neuromorphic Camera Denoising using Graph Neural Network-driven Transformers
• Likelihood-Free Parameter Estimation with Neural Bayes Estimators
• Towards Reusable Surrogate Models: Graph-Based Transfer Learning on Trusses
• Generative AIBIM: An automatic and intelligent structural design pipeline integrating BIM and generative AI
• MAGNNETO: A Graph Neural Network-based Multi-Agent system for Traffic Engineering
• Neurosymbolic AI for Reasoning over Knowledge Graphs: A Survey
• Graph Neural Networks on SPD Manifolds for Motor Imagery Classification: A Perspective from the Time-Frequency Analysis
• Label Information Enhanced Fraud Detection against Low Homophily in Graphs
• Neural Airport Ground Handling
• Scalable Graph Neural Network Training: The Case for Sampling
• GPTFF: A high-accuracy out-of-the-box universal AI force field for arbitrary inorganic materials
• Advanced Unsupervised Learning: A Comprehensive Overview of Multi-View Clustering Techniques
• PaSca: a Graph Neural Architecture Search System under the Scalable Paradigm
• Combining physics-based and data-driven models: advancing the frontiers of research with Scientific Machine Learning
• Permutationless Many-Jet Event Reconstruction with Symmetry Preserving Attention Networks
• Recommender systems based on graph embedding techniques: A comprehensive review
• Longitudinal Speech Biomarkers for Automated Alzheimer's Detection
• Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning
• Machine learning methods for prediction of cancer driver genes: a survey paper
• Deep Learning Criminal Networks
• Graph Neural Networks for Graph Drawing
• Zero-shot Node Classification with Decomposed Graph Prototype Network
• Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
• Ginex: SSD-enabled Billion-scale Graph Neural Network Training on a Single Machine via Provably Optimal In-memory Caching
• Position-aware Structure Learning for Graph Topology-imbalance by Relieving Under-reaching and Over-squashing
• Show me your NFT and I tell you how it will perform: Multimodal representation learning for NFT selling price prediction
• Relational Graph Convolutional Networks: A Closer Look
• GALA: Graph Diffusion-based Alignment with Jigsaw for Source-free Domain Adaptation
• An actor-critic algorithm with policy gradients to solve the job shop scheduling problem using deep double recurrent agents
• IGB: Addressing The Gaps In Labeling, Features, Heterogeneity, and Size of Public Graph Datasets for Deep Learning Research
• Drug-Target Interaction/Affinity Prediction: Deep Learning Models and Advances Review
• Graph Machine Learning for Design of High-Octane Fuels
• Adaptive estimation of quantum observables
• Social Force Embedded Mixed Graph Convolutional Network for Multi-class Trajectory Prediction
• Graph Neural Networks in Vision-Language Image Understanding: A Survey
• Learning Graph Neural Networks with Positive and Unlabeled Nodes
• The Expressive Power of Graph Neural Networks: A Survey
• Graph-Based Intercategory and Intermodality Network for Multilabel Classification and Melanoma Diagnosis of Skin Lesions in Dermoscopy and Clinical Images
• Contrastive Graph Convolutional Networks for Hardware Trojan Detection in Third Party IP Cores
• A Machine Learning Surrogate Modeling Benchmark for Temperature Field Reconstruction of Heat-Source Systems
• Path Integral Based Convolution and Pooling for Graph Neural Networks
• Deep learning for dynamic graphs: models and benchmarks
• Efficient classical algorithms for simulating symmetric quantum systems
• Artificial Intelligence in Materials Science and Engineering: Current Landscape, Key Challenges, and Future Trajectorie
• AutoGraph: Automated Graph Neural Network
• Deep Transfer Learning with Graph Neural Network for Sensor-Based Human Activity Recognition
• Incorporating Symbolic Domain Knowledge into Graph Neural Networks
• Human and social capital strategies for Mafia network disruption
• Graph Mining for Cybersecurity: A Survey
• FreeKD: Free-direction Knowledge Distillation for Graph Neural Networks
• Harnessing the Power of Ego Network Layers for Link Prediction in Online Social Networks
• Graph neural networks for the prediction of molecular structure-property relationships
• Black-box Bayesian inference for economic agent-based models
• Graph Foundation Models: Concepts, Opportunities and Challenges
• Semantic2Graph: Graph-based Multi-modal Feature Fusion for Action Segmentation in Videos
• TCN: Table Convolutional Network for Web Table Interpretation
• Recent Advances in Deep Learning for Channel Coding: A Survey
• Edge Generation Scheduling for DAG Tasks Using Deep Reinforcement Learning
• Exploring Edge Disentanglement for Node Classification
• Stochastic Graph Neural Networks
• Deeper Insights into Deep Graph Convolutional Networks: Stability and Generalization
• On the Use of Neural Networks for Energy Reconstruction in High-granularity Calorimeters
• Time Series Predictions in Unmonitored Sites: A Survey of Machine Learning Techniques in Water Resources
• Network of Tensor Time Series
• INCREASE: Inductive Graph Representation Learning for Spatio-Temporal Kriging
• Contrastive Multi-Level Graph Neural Networks for Session-based Recommendation
• Multi-Modal Deep Learning for Credit Rating Prediction Using Text and Numerical Data Streams
• A Meta-Learning Approach for Training Explainable Graph Neural Networks
• Uncertainty Quantification via Spatial-Temporal Tweedie Model for Zero-inflated and Long-tail Travel Demand Prediction
• Neural Networks for Extreme Quantile Regression with an Application to Forecasting of Flood Risk
• Distributed Training of Graph Convolutional Networks
• Enhancing MRI-Based Classification of Alzheimer's Disease with Explainable 3D Hybrid Compact Convolutional Transformers
• Non-Local Graph Neural Networks
• Predicting origin-destination ride-sourcing demand with a spatio-temporal encoder-decoder residual multi-graph convolutional network
• DPAR: Decoupled Graph Neural Networks with Node-Level Differential Privacy
• A Mathematical Guide to Operator Learning
• APGL4SR: A Generic Framework with Adaptive and Personalized Global Collaborative Information in Sequential Recommendation
• Towards Multi-agent Reinforcement Learning based Traffic Signal Control through Spatio-temporal Hypergraphs
• Bayesian graph convolutional neural networks via tempered MCMC
• EEG Decoding for Datasets with Heterogenous Electrode Configurations using Transfer Learning Graph Neural Networks
• Applying Convolutional Neural Networks to Data on Unstructured Meshes with Space-Filling Curves
• Towards Fair Graph Neural Networks via Graph Counterfactual
• Representation learning for neural population activity with Neural Data Transformers
• GraphWorld: Fake Graphs Bring Real Insights for GNNs
• Improving the Timing Resolution of Positron Emission Tomography Detectors Using Boosted Learning -- A Residual Physics Approach
• RSI-Net: Two-Stream Deep Neural Network for Remote Sensing Imagesbased Semantic Segmentation
• Real-time Hosting Capacity Assessment for Electric Vehicles: A Sequential Forecast-then-Optimize Method
• NetFense: Adversarial Defenses against Privacy Attacks on Neural Networks for Graph Data
• Gegenbauer Graph Neural Networks for Time-varying Signal Reconstruction
• Trajectory-User Linking via Hierarchical Spatio-Temporal Attention Networks
• Partially Observable Mean Field Multi-Agent Reinforcement Learning Based on Graph-Attention
• GNN-Geo: A Graph Neural Network-based Fine-grained IP geolocation Framework
• Graph Convolutional Networks based on Manifold Learning for Semi-Supervised Image Classification
• A Computationally Efficient Hybrid Neural Network Architecture for Porous Media: Integrating Convolutional and Graph Neural Networks for Improved Property Predictions
• Structured Citation Trend Prediction Using Graph Neural Networks
• Enhancing the Robustness via Adversarial Learning and Joint Spatial-Temporal Embeddings in Traffic Forecasting
• Multi-frequency PolSAR Image Fusion Classification Based on Semantic Interactive Information and Topological Structure
• Graph-adaptive Rectified Linear Unit for Graph Neural Networks
• Topological Reconstruction of Particle Physics Processes using Graph Neural Networks
• Dairy Cow rumination detection: A deep learning approach
• Graph Neural Networks with Diverse Spectral Filtering
• Structure-Aware DropEdge Towards Deep Graph Convolutional Networks
• Kernel-based Graph Learning from Smooth Signals: A Functional Viewpoint
• Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment
• DGNN: Decoupled Graph Neural Networks with Structural Consistency between Attribute and Graph Embedding Representations
• Dynamic Interactive Relation Capturing via Scene Graph Learning for Robotic Surgical Report Generation
• Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation
• Solving AC Power Flow with Graph Neural Networks under Realistic Constraints
• Predicting the Temperature Dependence of Surfactant CMCs Using Graph Neural Networks
• Transition Propagation Graph Neural Networks for Temporal Networks
• SCARA: Scalable Graph Neural Networks with Feature-Oriented Optimization
• A Network Science perspective of Graph Convolutional Networks: A survey
• Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders
• DyEdgeGAT: Dynamic Edge via Graph Attention for Early Fault Detection in IIoT Systems
• Causal invariant geographic network representations with feature and structural distribution shifts
• Network Alignment
• DSTSA-GCN: Advancing Skeleton-Based Gesture Recognition with Semantic-Aware Spatio-Temporal Topology Modeling
• Beyond Graph Neural Networks with Lifted Relational Neural Networks
• EvGNN: An Event-driven Graph Neural Network Accelerator for Edge Vision
• Improved Constraints on Effective Top Quark Interactions using Edge Convolution Networks
• Prediction and mitigation of nonlocal cascading failures using graph neural networks
• Specification Overfitting in Artificial Intelligence
• Combining social relations and interaction data in Recommender System with Graph Convolution Collaborative Filtering
• Counterfactual Explanations for Deep Learning-Based Traffic Forecasting
• View-based Explanations for Graph Neural Networks
• DPGNN: Dual-Perception Graph Neural Network for Representation Learning
• Adversarial Inter-Group Link Injection Degrades the Fairness of Graph Neural Networks
• Predicting cognitive scores with graph neural networks through sample selection learning
• Quantifying the Alignment of Graph and Features in Deep Learning
• Graph-Segmenter: Graph Transformer with Boundary-aware Attention for Semantic Segmentation
• Physics-Enhanced Graph Neural Networks For Soft Sensing in Industrial Internet of Things
• Cardinality Estimation over Knowledge Graphs with Embeddings and Graph Neural Networks
• Large Language Model-driven Meta-structure Discovery in Heterogeneous Information Network
• wsGAT: Weighted and Signed Graph Attention Networks for Link Prediction
• Hierarchical Aggregations for High-Dimensional Multiplex Graph Embedding
• Multi-Task Semantic Communication With Graph Attention-Based Feature Correlation Extraction
• Addressing Heterophily in Node Classification with Graph Echo State Networks
• AnchorGAE: General Data Clustering via $O(n)$ Bipartite Graph Convolution
• Learning to Control Local Search for Combinatorial Optimization
• Beyond Localized Graph Neural Networks: An Attributed Motif Regularization Framework
• Collaborate to Adapt: Source-Free Graph Domain Adaptation via Bi-directional Adaptation
• The State of the Art in Creating Visualization Corpora for Automated Chart Analysis
• Data-driven decoding of quantum error correcting codes using graph neural networks
• Learning for routing: A guided review of recent developments and future directions
• Unsupervised Graph Outlier Detection: Problem Revisit, New Insight, and Superior Method
• FairEGM: Fair Link Prediction and Recommendation via Emulated Graph Modification
• Counterfactual Learning on Graphs: A Survey
• FunQG: Molecular Representation Learning Via Quotient Graphs
• Graph Kernel Neural Networks
• Audio Event-Relational Graph Representation Learning for Acoustic Scene Classification
• Predicting Tweet Engagement with Graph Neural Networks
• A Systematic Comparison Study on Hyperparameter Optimisation of Graph Neural Networks for Molecular Property Prediction
• Joint Time-Vertex Fractional Fourier Transform
• Distributed Structured Actor-Critic Reinforcement Learning for Universal Dialogue Management
• Dynamic Adaptive Spatio-temporal Graph Convolution for fMRI Modelling
• Disambiguated Node Classification with Graph Neural Networks
• AI-Driven Channel State Information (CSI) Extrapolation for 6G: Current Situations, Challenges and Future Research
• Towards Complex Dynamic Physics System Simulation with Graph Neural ODEs
• The Graph Database Interface: Scaling Online Transactional and Analytical Graph Workloads to Hundreds of Thousands of Cores
• Recommending on graphs: a comprehensive review from a data perspective
• Knowledge-based Entity Prediction for Improved Machine Perception in Autonomous Systems
• Parameterized Hypercomplex Graph Neural Networks for Graph Classification
• SSFG: Stochastically Scaling Features and Gradients for Regularizing Graph Convolutional Networks
• Reinforcement Learning Based Quantum Circuit Optimization via ZX-Calculus
• Deep learning optimal quantum annealing schedules for random Ising models
• Low-bit Quantization for Deep Graph Neural Networks with Smoothness-aware Message Propagation
• p2pGNN: A Decentralized Graph Neural Network for Node Classification in Peer-to-Peer Networks
• Forecasting West Nile Virus with Graph Neural Networks: Harnessing Spatial Dependence in Irregularly Sampled Geospatial Data
• Demystifying Chains, Trees, and Graphs of Thoughts
• Causality and Independence Enhancement for Biased Node Classification
• A Multidimensional Graph Fourier Transformation Neural Network for Vehicle Trajectory Prediction
• Interpretation of Brain Morphology in Association to Alzheimer's Disease Dementia Classification Using Graph Convolutional Networks on Triangulated Meshes
• Semi-supervised Domain Adaptation on Graphs with Contrastive Learning and Minimax Entropy
• A Spatio-Temporal Graph Convolutional Network for Gesture Recognition from High-Density Electromyography
• On the data-driven description of lattice materials mechanics
• Beyond the Eye: A Relational Model for Early Dementia Detection Using Retinal OCTA Images
• Dismantling Complex Networks by a Neural Model Trained from Tiny Networks
• LatticeGraphNet: A two-scale graph neural operator for simulating lattice structures
• Distributed Learning over Networks with Graph-Attention-Based Personalization
• GNN-LoFI: a Novel Graph Neural Network through Localized Feature-based Histogram Intersection
• Discovering Communication Pattern Shifts in Large-Scale Labeled Networks using Encoder Embedding and Vertex Dynamics
• Toward Sustainable Polymer Design: A Molecular Dynamics-Informed Machine Learning Approach for Vitrimers
• Memory-Efficient Graph Convolutional Networks for Object Classification and Detection with Event Cameras
• Study of Mass Composition of Cosmic Rays with IceTop and IceCube
• Cross-Network Learning with Partially Aligned Graph Convolutional Networks
• Learning Tree Structures from Leaves For Particle Decay Reconstruction
• Feature-Based Interpolation and Geodesics in the Latent Spaces of Generative Models
• Task-Equivariant Graph Few-shot Learning
• Using Graph Neural Networks and Frequency Domain Data for Automated Operational Modal Analysis of Populations of Structures
• Image Patch-Matching with Graph-Based Learning in Street Scenes
• Scalable Verification of GNN-based Job Schedulers
• Language Models as Emotional Classifiers for Textual Conversations
• Modeling Dual Period-Varying Preferences for Takeaway Recommendation
• High-quality Task Division for Large-scale Entity Alignment
• Beyond Euclid: An Illustrated Guide to Modern Machine Learning with Geometric, Topological, and Algebraic Structures
• Spatial-Temporal Graph Enhanced DETR Towards Multi-Frame 3D Object Detection
• Learning Geometry-Dependent and Physics-Based Inverse Image Reconstruction
• A Review of Graph-Powered Data Quality Applications for IoT Monitoring Sensor Networks
• Improving the Shortest Plank: Vulnerability-Aware Adversarial Training for Robust Recommender System
• Label Informed Contrastive Pretraining for Node Importance Estimation on Knowledge Graphs
• A Continuous Convolutional Trainable Filter for Modelling Unstructured Data
• Multi-Fidelity Machine Learning Applied to Steady Fluid Flows
• Graph Neural Networks with Parallel Neighborhood Aggregations for Graph Classification
• Network Analytics for Anti-Money Laundering -- A Systematic Literature Review and Experimental Evaluation
• Endowing Pre-trained Graph Models with Provable Fairness
• A Survey of Latent Factor Models in Recommender Systems
• Emergent properties and the multiscale characterization challenge in condensed matter, from crystals to complex materials: a Review
• Sort & Slice: A Simple and Superior Alternative to Hash-Based Folding for Extended-Connectivity Fingerprints
• Efficient Hate Speech Detection: Evaluating 38 Models from Traditional Methods to Transformers
• On the approximation capability of GNNs in node classification/regression tasks
• Revisiting 2D Convolutional Neural Networks for Graph-based Applications
• Reconciling Attribute and Structural Anomalies for Improved Graph Anomaly Detection
• Towards Incremental Learning in Large Language Models: A Critical Review
• Performance Comparison of Session-based Recommendation Algorithms based on GNNs
• Graph link prediction in computer networks using Poisson matrix factorisation
• SNoRe: Scalable Unsupervised Learning of Symbolic Node Representations
• Error Approximation and Bias Correction in Dynamic Problems using a Recurrent Neural Network/Finite Element Hybrid Model
• Graph neural network-based structural classification of glass-forming liquids and its interpretation via self-attention mechanism
• Graph Reinforcement Learning for Power Grids: A Comprehensive Survey
• Physics-Informed Graph-Mesh Networks for PDEs: A hybrid approach for complex problems
• Learning Dense Features for Point Cloud Registration Using a Graph Attention Network
• Heterogeneous Data Fusion Considering Spatial Correlations using Graph Convolutional Networks and its Application in Air Quality Prediction
• Synergistic Graph Fusion via Encoder Embedding
• Vehicle-group-based Crash Risk Prediction and Interpretation on Highways
• Relational Reasoning Networks
• A Study on Quantum Graph Neural Networks Applied to Molecular Physics
• Local and Global Context-Based Pairwise Models for Sentence Ordering
• QT-Routenet: Improved GNN generalization to larger 5G networks by fine-tuning predictions from queueing theory
• Learning Stochastic Graph Neural Networks with Constrained Variance
• Analysis of Gene Regulatory Networks from Gene Expression Using Graph Neural Networks
• Predicting and Understanding Turn-Taking Behavior in Open-Ended Group Activities in Virtual Reality
• Generating Topological Structure of Floorplans from Room Attributes
• CaEGCN: Cross-Attention Fusion based Enhanced Graph Convolutional Network for Clustering
• DeepGANTT: A Scalable Deep Learning Scheduler for Backscatter Networks
• Voucher Abuse Detection with Prompt-based Fine-tuning on Graph Neural Networks
• Hyperdimensional Representation Learning for Node Classification and Link Prediction
• EOSnet: Embedded Overlap Structures for Graph Neural Networks in Predicting Material Properties
• Scalar Field Prediction on Meshes Using Interpolated Multi-Resolution Convolutional Neural Networks
• Sequential Recommendation in Online Games with Multiple Sequences, Tasks and User Levels
• Towards Multimodal Graph Large Language Model
• Dealing with Sparse Rewards Using Graph Neural Networks
• IMMENSE: Inductive Multi-perspective User Classification in Social Networks
• It Is Time To Steer: A Scalable Framework for Analysis-driven Attack Graph Generation
• Meta-GPS++: Enhancing Graph Meta-Learning with Contrastive Learning and Self-Training
• Domain-informed neural networks for interaction localization within astroparticle experiments
• Improvement Graph Convolution Collaborative Filtering with Weighted addition input
• Enhancing Function Name Prediction using Votes-Based Name Tokenization and Multi-Task Learning
• MQ-GNN: A Multi-Queue Pipelined Architecture for Scalable and Efficient GNN Training
• You Do (Not) Belong Here: Detecting DPI Evasion Attacks with Context Learning
• Generating Post-hoc Explanations for Skip-gram-based Node Embeddings by Identifying Important Nodes with Bridgeness
• Graph Coordinates and Conventional Neural Networks -- An Alternative for Graph Neural Networks
• SpotV2Net: Multivariate Intraday Spot Volatility Forecasting via Vol-of-Vol-Informed Graph Attention Networks
• Low Cost Carriers induce specific and identifiable delay propagation patterns: an analysis of the EU and US systems
• Graph convolutional network as a fast statistical emulator for numerical ice sheet modeling
• Normal Transformer: Extracting Surface Geometry from LiDAR Points Enhanced by Visual Semantics
• Encoder Embedding for General Graph and Node Classification
• A Comprehensive Benchmark on Spectral GNNs: The Impact on Efficiency, Memory, and Effectiveness
• Detecting Masquerade Attacks in Controller Area Networks Using Graph Machine Learning
• Learning to Compare Hardware Designs for High-Level Synthesis
• Hierarchical Graph Neural Network for Compressed Speech Steganalysis
• A Hybrid GNN-LSE Method for Fast, Robust, and Physically-Consistent AC Power Flow
• SiameseDuo++: Active Learning from Data Streams with Dual Augmented Siamese Networks
• Learning on heterogeneous graphs using high-order relations
• Unified Dual-Intent Translation for Joint Modeling of Search and Recommendation
• Learning Graph Neural Networks using Exact Compression
• Partition Pooling for Convolutional Graph Network Applications in Particle Physics
• Graph Convolutional Neural Networks Sensitivity under Probabilistic Error Model
• A Graph-Neural-Network-Entropy model of vital node identification on network attack and propagation
• SurGrID: Controllable Surgical Simulation via Scene Graph to Image Diffusion
• Predicting Feynman periods in ${\varphi }^4$-theory
• Semantic Graph Neural Network with Multi-measure Learning for Semi-supervised Classification
• QuadConv: Quadrature-Based Convolutions with Applications to Non-Uniform PDE Data Compression
• Incremental Learning with Concept Drift Detection and Prototype-based Embeddings for Graph Stream Classification
• Enhancing lattice kinetic schemes for fluid dynamics with Lattice-Equivariant Neural Networks
• Deep Spectral Meshes: Multi-Frequency Facial Mesh Processing with Graph Neural Networks
• A Local Perspective-based Model for Overlapping Community Detection
• BaSeNet: A Learning-based Mobile Manipulator Base Pose Sequence Planning for Pickup Tasks
• SMARTQUERY: An Active Learning Framework for Graph Neural Networks through Hybrid Uncertainty Reduction
• Learning to Simulate Aerosol Dynamics with Graph Neural Networks
• Hazard-Responsive Digital Twin for Climate-Driven Urban Resilience and Equity
• Whole-Graph Representation Learning For the Classification of Signed Networks
• Top-philic Machine Learning
• INFLECT-DGNN: Influencer Prediction with Dynamic Graph Neural Networks
• Few Edges Are Enough: Few-Shot Network Attack Detection with Graph Neural Networks
• An Aspect Performance-aware Hypergraph Neural Network for Review-based Recommendation
• DAGPrompT: Pushing the Limits of Graph Prompting with a Distribution-aware Graph Prompt Tuning Approach
• Finding Counterfactual Evidences for Node Classification
• Attention-driven Graph Clustering Network
• Polynomial Selection in Spectral Graph Neural Networks: An Error-Sum of Function Slices Approach
• Hybrid Quantum Classical Graph Neural Networks for Particle Track Reconstruction
• NodeImport: Imbalanced Node Classification with Node Importance Assessment
• Transformers Meet Relational Databases
• Efficient Learning-based Graph Simulation for Temporal Graphs
• Bingo: Radix-based Bias Factorization for Random Walk on Dynamic Graphs
• Graph-Based Methods for Discrete Choice
• Pre-training for Recommendation Unlearning
• Position-Sensing Graph Neural Networks: Proactively Learning Nodes Relative Positions
• DART-Vetter: A Deep LeARning Tool for automatic triage of exoplanet candidates
• Graph-Based Physics-Guided Urban PM2.5 Air Quality Imputation with Constrained Monitoring Data
• SEP-GCN: Leveraging Similar Edge Pairs with Temporal and Spatial Contexts for Location-Based Recommender Systems
• Multiframe Detection via Graph Neural Networks: A Link Prediction Approach
• Synthetic graphs for link prediction benchmarking
• Structure-Enhanced Protein Instruction Tuning: Towards General-Purpose Protein Understanding with LLMs
• Segmentation of EM showers for neutrino experiments with deep graph neural networks
• Structurally Flexible Neural Networks: Evolving the Building Blocks for General Agents
• Code Revert Prediction with Graph Neural Networks: A Case Study at J.P. Morgan Chase
• Multi-representations Space Separation based Graph-level Anomaly-aware Detection
• Refined Graph Encoder Embedding via Self-Training and Latent Community Recovery
• KGTN-ens: Few-Shot Image Classification with Knowledge Graph Ensembles
• STGDPM:Vessel Trajectory Prediction with Spatio-Temporal Graph Diffusion Probabilistic Model
• A unifying primary framework for quantum graph neural networks from quantum graph states
• Random Projection Forest Initialization for Graph Convolutional Networks
• "I see models being a whole other thing": An Empirical Study of Pre-Trained Model Naming Conventions and A Tool for Enhancing Naming Consistency
• Self-supervised Graph Representation Learning for Black Market Account Detection
• Embedding Graphs on Grassmann Manifold
• Generalized Embedding Machines for Recommender Systems
• EmbAssi: Embedding Assignment Costs for Similarity Search in Large Graph Databases
• Edge-Wise Graph-Instructed Neural Networks
• Multi-Level Attention Pooling for Graph Neural Networks: Unifying Graph Representations with Multiple Localities
• Evaluating the Predictive Features of Person-Centric Knowledge Graph Embeddings: Unfolding Ablation Studies
• An encoding of argumentation problems using quadratic unconstrained binary optimization
• A Generative Framework for Predictive Modeling of Multiple Chronic Conditions Using Graph Variational Autoencoder and Bandit-Optimized Graph Neural Network
• Community detection robustness of graph neural networks
• Graph Neural Networks Based Anomalous RSSI Detection
• GNSS Positioning using Cost Function Regulated Multilateration and Graph Neural Networks
• A Hierarchical Framework with Spatio-Temporal Consistency Learning for Emergence Detection in Complex Adaptive Systems
• Sheaf4Rec: Sheaf Neural Networks for Graph-based Recommender Systems
• Advancing biological super-resolution microscopy through deep learning: a brief review
• ML-based identification of the interface regions for coupling local and nonlocal models
• Efficient quantification on large-scale networks
• Predicting Scientific Impact Through Diffusion, Conformity, and Contribution Disentanglement
• Neural RELAGGS
• Efficient interpolation of molecular properties across chemical compound space with low-dimensional descriptors
• REDELEX: A Framework for Relational Deep Learning Exploration
• Attributed Graph Clustering with Multi-Scale Weight-Based Pairwise Coarsening and Contrastive Learning
• Edged Weisfeiler-Lehman Algorithm
• Leveraging Vulnerabilities in Temporal Graph Neural Networks via Strategic High-Impact Assaults
• DeBUGCN -- Detecting Backdoors in CNNs Using Graph Convolutional Networks
• Efficient and Robust Continual Graph Learning for Graph Classification in Biology
• Fast Polypharmacy Side Effect Prediction Using Tensor Factorisation
• Capturing and Anticipating User Intents in Data Analytics via Knowledge Graphs
• End-to-end analysis using image classification
• Focus Where It Matters: Graph Selective State Focused Attention Networks
• Unlearning Inversion Attacks for Graph Neural Networks
• Learning Feature Encoder with Synthetic Anomalies for Weakly Supervised Graph Anomaly Detection
• Reservoir-Based Graph Convolutional Networks
• Graph Self-Supervised Learning with Learnable Structural and Positional Encodings
• A Deep Learning Based Resource Allocator for Communication Networks with Dynamic User Utility Demands
• Imbalanced Graph-Level Anomaly Detection via Counterfactual Augmentation and Feature Learning
• Riemannian Graph Tokenizer for Structural Knowledge Transfer
• Pattern-Based Graph Classification: Comparison of Quality Measures and Importance of Preprocessing
• Partition-wise Graph Filtering: A Unified Perspective Through the Lens of Graph Coarsening
• PHLP: Sole Persistent Homology for Link Prediction - Interpretable Feature Extraction
• Electron-Informed Coarse-Graining Molecular Representation Learning for Real-World Molecular Physics
• Spatially-informed transformers: Injecting geostatistical covariance biases into self-attention for spatio-temporal forecasting
• Hypergraph Neural Sheaf Diffusion: A Symmetric Simplicial Set Framework for Higher-Order Learning
• Knowledge Graphs Meet Graph Neural Networks: A Comprehensive Survey
• HyperGraphX: Graph Transductive Learning with Hyperdimensional Computing and Message Passing
• Toward Efficient Testing of Graph Neural Networks via Test Input Prioritization
• A method for the systematic generation of graph XAI benchmarks via Weisfeiler-Leman coloring
• Untrained Graph Neural Networks for Denoising
• SeaPearl: A Constraint Programming Solver guided by Reinforcement Learning
• Equivalence between spectral properties of graphs with and without loops
• A Structural Feature-Based Approach for Comprehensive Graph Classification
• Proxy Reconstruction Pre-training for Ramp Flow Prediction at Highway Interchanges
• Rethinking Client-oriented Federated Graph Learning
• Curriculum Guided Personalized Subgraph Federated Learning
• Lightweight Spatio-Temporal Attention Network with Graph Embedding and Rotational Position Encoding for Traffic Forecasting
• A Method to Predict Semantic Relations on Artificial Intelligence Papers
• LEON: Location Embeddings from OSM Neighborhoods via Hexagonal Graph Masked Autoencoders
• Interacting Particle Systems on Networks: joint inference of the network and the interaction kernel
• Exploitation of Hidden Context in Dynamic Movement Forecasting: A Neural Network Journey from Recurrent to Graph Neural Networks and General Purpose Transformers
• An Empirical Evaluation of Rewiring Approaches in Graph Neural Networks
• AIRES: Accelerating Out-of-Core GCNs via Algorithm-System Co-Design
• Reachability-Based Formal Verification of Graph Neural Networks with Node and Edge Features
• Classification of vertices on social networks by multiple approaches