A Comprehensive Survey on Graph Neural Networks

2019/01/03 by Zonghan Wu, Shirui Pan, Fengwen Chen +3 · 1 voice · 9,532 citations
Computer Science · Mathematics · #Advanced Graph Neural Networks #Artificial neural network #Benchmark (surveying) #Convolutional neural network #Deep learning #Feature learning #Graph #Graph Theory and Algorithms #Labeled data #Machine Learning in Healthcare #Training set #cs.LG #stat.ML

paper · pdf · doi:10.1109/tnnls.2020.2978386

published in IEEE Transactions on Neural Networks and Learning Systems 32(1), 4-24 (Institute of Electrical and Electronics Engineers) · Minor revision (updated tables and references)

openalex created_date 2019/01/11 · arxiv created 2019/12/04 · openalex publication_date 2020/03/24 · arxiv updated 2020/03/27 · openalex updated_date 2026/08/06

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 the existing machine learning algorithms. Recently, many studies on extending deep learning approaches for graph data have emerged. In this article, 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 GNNs into four categories, namely, recurrent GNNs, convolutional GNNs, graph autoencoders, and spatial-temporal GNNs. We further discuss the applications of GNNs across various domains and summarize the open-source codes, benchmark data sets, and model evaluation of GNNs. Finally, we propose potential research directions in this rapidly growing field.

Citations

• Gradient-based learning applied to document recognition
• DeepWalk
• Quantum-chemical insights from deep tensor neural networks

Cited by

• Graph Neural Network Force Fields (GPTFF-mol) for Organic Molecules from Optimization Trajectories (OpenGEM26)
• Graph Neural Network-based Algorithm Selection for the Traveling Salesman Problem: A Systematic Study of Cost and Rank Losses under Distinct Budget Regimes
• Robust Belief-State Policy Learning for Quantum Network Routing Under Decoherence and Time-Varying Conditions
• Finite-Agent Stochastic Differential Games on Large Graphs: II. Graph-Based Architectures
• Octopus v4: Graph of language models
• HCIG: A Hierarchical Cross-Modal Incongruity Graph Network for Multimodal Sarcasm and Cyberbullying Detection
• Approximating SPR Distance Between Phylogenetic Trees with Graph Neural Networks
• Learning Structural Manipulability in Gate-Level Netlists Using Graph Neural Networks
• UniSAGE: Unifying Static and Dynamic Attributes with Hyper-Structure
• Robust GNN Watermarking via Implicit Perception of Topological Invariants
• Vulnerability Detection via Multiple-Graph-Based Code Representation
• Adaptive Fusion Graph Network for 3D Strain Field Prediction in Solid Rocket Motor Grains
• Identifying obfuscated code through graph-based semantic analysis of binary code
• Thyroid endocrine disruption and hepatotoxicity induced by bisphenol AF: Integrated zebrafish embryotoxicity test and deep learning
• GNN-based Multi-Agent Control of Traffic Shockwaves in Sparse Vehicular Ad-hoc Networks
• A Systematic Literature Review of Machine Learning Approaches for Migrating Monolithic Systems to Microservices
• Robust Interpretation of Historical Documents in Knowledge Graphs Through Query Inference and Execution
• Domain-Prior-Regularized Graph Modeling for Anomaly Detection in Cyber-Physical Systems
• Spatial Prediction of Soil Microplastics and Organic Matter Using Graph Attention Networks
• Graph Neural Networks for Predicting Solvability of Finite Groups
• A2QTGN: Adaptive Amplitude Quantum-Integrated Temporal Graph Network for Dynamic Link Prediction
• TextBridgeGNN: Pre-training Graph Neural Network for Cross-Domain Recommendation via Text-Guided Transfer
• Semantic Refinement with LLMs for Graph Representations
• A Novel Graph-Sequence Learning Model for Inductive Text Classification
• MAPI-GNN: Multi-Activation Plane Interaction Graph Neural Network for Multimodal Medical Diagnosis
• AL-GNN: Privacy-Preserving and Replay-Free Continual Graph Learning via Analytic Learning
• Toward Efficient Testing of Graph Neural Networks via Test Input Prioritization
• FairExpand: Individual Fairness on Graphs with Partial Similarity Information
• Spatially-informed transformers: Injecting geostatistical covariance biases into self-attention for spatio-temporal forecasting
• Hypernetworks That Evolve Themselves
• Graph Neural Networks for Source Detection: A Review and Benchmark Study
• ATLAS: Adaptive Topology-based Learning at Scale for Homophilic and Heterophilic Graphs
• A Roadmap for Applying Graph Neural Networks to Numerical Data: Insights from Cementitious Materials
• A Graph-Based Forensic Framework for Inferring Hardware Noise of Cloud Quantum Backend
• GraphPerf-RT: A Graph-Driven Performance Model for Hardware-Aware Scheduling of OpenMP Codes
• Exploring Spatial-Temporal Representation via Star Graph for mmWave Radar-based Human Activity Recognition
• Personalized Pricing in Social Networks with Individual and Group Fairness Considerations
• A Survey on Hypergraph Representation Learning
• Attacking and Securing Community Detection: A Game-Theoretic Framework
• Representation of the structure of graphs by sequences of instructions
• A self-supervised detection method for mixed urban functions based on trajectory temporal image
• Self-Supervised Learning on Molecular Graphs: A Systematic Investigation of Masking Design
• Mitigating Bias in Graph Hyperdimensional Computing
• Edged Weisfeiler-Lehman Algorithm
• Graph Convolutional Long Short-Term Memory Attention Network for Post-Stroke Compensatory Movement Detection Based on Skeleton Data
• Learning Thermoelectric Transport from Crystal Structures via Multiscale Graph Neural Network
• Learning-based Link Prediction Methods Integrating Network Topological Features and Embedding Representations
• The Graph-Embedded Hazard Model (GEHM): Stochastic Network Survival Dynamics on Economic Graphs
• Learning Invariant Graph Representations Through Redundant Information
• Task-Specific Trust Evaluation for Multi-Hop Collaborator Selection via GNN-Aided Distributed Agentic AI
• Advanced Unsupervised Learning: A Comprehensive Overview of Multi-View Clustering Techniques
• Vision and Causal Learning Based Channel Estimation for THz Communications
• RGE-GCN: Recursive Gene Elimination with Graph Convolutional Networks for RNA-seq based Early Cancer Detection
• Large Language Models as Generalist Policies for Network Optimization
• FGC-Comp: Adaptive Neighbor-Grouped Attribute Completion for Graph-based Anomaly Detection
• Domain-Decomposed Graph Neural Network Surrogate Modeling for Ice Sheets
• QGShap: Quantum Acceleration for Faithful GNN Explanations
• City-Conditioned Memory for Multi-City Traffic and Mobility Forecasting
• Uncertainty Quantification for Deep Regression using Contextualised Normalizing Flows
• ARES: Anomaly Recognition Model For Edge Streams
• Time Extrapolation with Graph Convolutional Autoencoder and Tensor Train Decomposition
• ParaGate: Parasitic-Driven Domain Adaptation Transfer Learning for Netlist Performance Prediction
• Rethinking Message Passing Neural Networks with Diffusion Distance-guided Stress Majorization
• Resolving Node Identifiability in Graph Neural Processes via Laplacian Spectral Encodings
• Robust and Generalizable GNN Fine-Tuning via Uncertainty-aware Adapter Learning
• R2PS: Worst-Case Robust Real-Time Pursuit Strategies under Partial Observability
• QoS-Aware Dynamic CU Selection in O-RAN with Graph-Based Reinforcement Learning
• CubeletWorld: A New Abstraction for Scalable 3D Modeling
• Gauge-Equivariant Graph Networks via Self-Interference Cancellation
• Graph Neural Networks for Vehicular Social Networks: Trends, Challenges, and Opportunities
• Meta-SimGNN: Adaptive and Robust WiFi Localization Across Dynamic Configurations and Diverse Scenarios
• Neurocircuitry-Inspired Hierarchical Graph Causal Attention Networks for Explainable Depression Identification
• A survey of heterogeneous graph neural networks for cybersecurity anomaly detection
• GRAPHTEXTACK: A Realistic Black-Box Node Injection Attack on LLM-Enhanced GNNs
• Graph Neural Networks, Deep Reinforcement Learning and Probabilistic Topic Modeling for Strategic Multiagent Settings
• GraphSB: Boosting Imbalanced Node Classification on Graphs through Structural Balance
• Beyond empirical models: Discovering new constitutive laws in solids with graph-based equation discovery
• TomoGraphView: 3D Medical Image Classification with Omnidirectional Slice Representations and Graph Neural Networks
• An ultrafast plenoptic-camera system for high-resolution 3D particle tracking in unsegmented scintillators
• Dual-Kernel Graph Community Contrastive Learning
• Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics
• Generalizable Insights for Graph Transformers in Theory and Practice
• Enhancing Logical Expressiveness in Graph Neural Networks via Path-Neighbor Aggregation
• Adaptive Graph Learning with Transformer for Multi-Reservoir Inflow Prediction
• Correcting False Alarms from Unseen: Adapting Graph Anomaly Detectors at Test Time
• Reperio-rPPG: Relational Temporal Graph Neural Networks for Periodicity Learning in Remote Physiological Measurement
• Enhancing Robustness of Graph Neural Networks through p-Laplacian
• Denoised Recommendation Model with Collaborative Signal Decoupling
• DeNoise: Learning Robust Graph Representations for Unsupervised Graph-Level Anomaly Detection
• Predicting Microbial Interactions Using Graph Neural Networks
• Simple and Behavior-Driven Augmentation for Recommendation with Rich Collaborative Signals
• Penetrating the Hostile: Detecting DeFi Protocol Exploits through Cross-Contract Analysis
• Multi-Modal Feature Fusion for Spatial Morphology Analysis of Traditional Villages via Hierarchical Graph Neural Networks
• MDAS-GNN: Multi-Dimensional Spatiotemporal GNN with Spatial Diffusion for Urban Traffic Risk Forecasting
• A Survey of Heterogeneous Graph Neural Networks for Cybersecurity Anomaly Detection
• Topology-Aware Active Learning on Graphs
• Graph Network-based Structural Simulator: Graph Neural Networks for Structural Dynamics
• Transformers Provably Learn Directed Acyclic Graphs via Kernel-Guided Mutual Information
• Enhancing Graph Neural Networks via auxiliary training for semi-supervised node classification
• A Serial MRI–based Deep Learning Model to Predict Survival in Patients with Locoregionally Advanced Nasopharyngeal Carcinoma
• Network feature-based phenotyping of leaf venation robustly reconstructs the latent space
• Fuzzy Logic in Surveillance Big Video Data Analysis
• A Survey of Imbalanced Learning on Graphs: Problems, Techniques, and Future Directions
• An Explainable Artificial Intelligence Approach Using Graph Learning to Predict Intensive Care Unit Length of Stay
• Modern machine‐learning for binding affinity estimation of protein–ligand complexes: Progress, opportunities, and challenges
• Biologically inspired neural network layer with homeostatic regulation and adaptive repair mechanisms
• GL4SDA: Predicting snoRNA-disease associations using GNNs and LLM embeddings
• Douglas Weighted Dirichlet Spaces: Analytic and Probabilistic Aspects
• Editorial for “Associating Knee Osteoarthritis Progression with Temporal‐Regional Graph Convolutional Network Analysis on MR Images”
• Path reliability-based graph attention networks
• Learning Fair Graph Representations with Multi-view Information Bottleneck
• Predicting electric vehicle charging demand using a heterogeneous spatio-temporal graph convolutional network
• SHA-256 Infused Embedding-Driven Generative Modeling of High-Energy Molecules in Low-Data Regimes
• MIC-BEV: Multi-Infrastructure Camera Bird's-Eye-View Transformer with Relation-Aware Fusion for 3D Object Detection
• HyperGraphX: Graph Transductive Learning with Hyperdimensional Computing and Message Passing
• Graph-Attentive MAPPO for Dynamic Retail Pricing
• AI in soil moisture remote sensing
• Image Categorization and Search via a GAT Autoencoder and Representative Models
• Toward General Digraph Contrastive Learning: A Dual Spatial Perspective
• A Re-node Self-training Approach for Deep Graph-based Semi-supervised Classification on Multi-view Image Data
• Hazard-Responsive Digital Twin for Climate-Driven Urban Resilience and Equity
• Sound Logical Explanations for Mean Aggregation Graph Neural Networks
• Pedagogy-driven Evaluation of Generative AI-powered Intelligent Tutoring Systems
• Dynamic Graph Neural Network for Data-Driven Physiologically Based Pharmacokinetic Modeling
• Hierarchical Graph Networks for Accurate Weather Forecasting via Lightweight Training
• Pruning and Quantization Impact on Graph Neural Networks
• A Hybrid GNN-LSE Method for Fast, Robust, and Physically-Consistent AC Power Flow
• Parameter-Free Hypergraph Neural Network for Few-Shot Node Classification
• Understanding Network Behaviors through Natural Language Question-Answering
• Adaptive Graph Mixture of Residual Experts: Unsupervised Learning on Diverse Graphs with Heterogeneous Specialization
• MolBridge: Atom-Level Joint Graph Refinement for Robust Drug-Drug Interaction Event Prediction
• Empowering Targeted Neighborhood Search via Hyper Tour for Large-Scale TSP
• GRACE: Graph Neural Networks for Locus-of-Care Prediction under Extreme Class Imbalance
• Image augmentation with invertible networks in interactive satellite image change detection
• Towards Unsupervised Open-Set Graph Domain Adaptation via Dual Reprogramming
• Mamba4Net: Distilled Hybrid Mamba Large Language Models For Networking
• Graph4MM: Weaving Multimodal Learning with Structural Information
• Capturing Context-Aware Route Choice Semantics for Trajectory Representation Learning
• Message Passing on the Edge: Towards Scalable and Expressive GNNs
• AGNES: Adaptive Graph Neural Network and Dynamic Programming Hybrid Framework for Real-Time Nanopore Seed Chaining
• A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning
• Causal Inspired Multi Modal Recommendation
• Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs
• Graph Few-Shot Learning via Adaptive Spectrum Experts and Cross-Set Distribution Calibration
• A Comprehensive Survey of Dynamic Graph Neural Networks: Models, Frameworks, Benchmarks, Experiments and Challenges
• An Encoder-Integrated PhoBERT with Graph Attention for Vietnamese Token-Level Classification
• Event-Aware Prompt Learning for Dynamic Graphs
• Learning the Structure of Connection Graphs
• Representing Data in Robotic Tactile Perception -- A Review
• A Graph-Attentive LSTM Model for Malicious URL Detection
• CAPSim: A Fast CPU Performance Simulator Using Attention-based Predictor
• On the Problem of Consistent Anomalies in Zero-Shot Industrial Anomaly Detection
• Interpretable Graph-Language Modeling for Detecting Youth Illicit Drug Use
• Open Biomedical Network Benchmark A Python Toolkit for Benchmarking Datasets with Biomedical Networks
• Deep Learning to Identify the Spatio-Temporal Cascading Effects of Train Delays in a High-Density Network
• Spatio-Temporal Graph Convolutional Networks for EV Charging Demand Forecasting Using Real-World Multi-Modal Data Integration
• TinyGraphEstimator: Adapting Lightweight Language Models for Graph Structure Inference
• Estimating Fair Graphs from Graph-Stationary Data
• HTMformer: Hybrid Time and Multivariate Transformer for Time Series Forecasting
• Label-frugal satellite image change detection with generative virtual exemplar learning
• Hierarchical attention graph learning with LLM enhancement for molecular solubility prediction
• A survey on neural-symbolic learning systems
• Reasoning by Exploration: A Unified Approach to Retrieval and Generation over Graphs
• When Does Global Attention Help? A Unified Empirical Study on Atomistic Graph Learning
• Efficient Learning-based Graph Simulation for Temporal Graphs
• QGraphLIME - Explaining Quantum Graph Neural Networks
• Unsupervised Active Learning via Natural Feature Progressive Framework
• Hybrid-Balance GFlowNet for Solving Vehicle Routing Problems
• Fractional Heat Kernel for Semi-Supervised Graph Learning with Small Training Sample Size
• Toward Uncertainty-Aware and Generalizable Neural Decoding for Quantum LDPC Codes
• A Hybrid GNN-IZR Framework for Fast and Empirically Robust AC Power Flow Analysis in Radial Distribution Systems
• VBM-NET: Visual Base Pose Learning for Mobile Manipulation using Equivariant TransporterNet and GNNs
• Comparative analysis on artificial intelligence methods for DTI and DTBA prediction in drug repurposing
• Cross-Modal Reconstruction Pretraining for Ramp Flow Prediction at Highway Interchanges
• Adaptive Node Feature Selection For Graph Neural Networks
• GDLNN: Marriage of Programming Language and Neural Networks for Accurate and Easy-to-Explain Graph Classification
• Neighbor-aware informal settlement mapping with graph convolutional networks
• Stealthy Yet Effective: Distribution-Preserving Backdoor Attacks on Graph Classification
• Leveraging Vulnerabilities in Temporal Graph Neural Networks via Strategic High-Impact Assaults
• Single-Core Superscalar Optimization of Clifford Neural Layers
• AI Methods for Antimicrobial Peptides: Progress and Challenges
• An adaptive semantic retrieval framework for digital libraries integrating graph neural networks, ontology, and user behavior
• G-reasoner: Foundation Models for Unified Reasoning over Graph-structured Knowledge
• Pure Node Selection for Imbalanced Graph Node Classification
• From What to Why: A Multi-Agent System for Evidence-based Chemical Reaction Condition Reasoning
• Rotational equivariant graph neural networks via local eigenbasis transformations
• Time series predictions in unmonitored sites: a survey of machine learning techniques in water resources
• Neighborhood Sampling Does Not Learn the Same Graph Neural Network
• SHAKE-GNN: Scalable Hierarchical Kirchhoff-Forest Graph Neural Network
• SlideMamba: Entropy-Based Adaptive Fusion of GNN and Mamba for Enhanced Representation Learning in Digital Pathology
• Enhancing Molecular Property Prediction with Knowledge from Large Language Models
• Beyond adjacency: Graph encoding with reachability and shortest paths
• Unmasking Fake Careers: Detecting Machine-Generated Career Trajectories via Multi-layer Heterogeneous Graphs
• Analog Courant Numbers and their Role in Analog Computing
• Expediting field-effect transistor chemical sensor design with neuromorphic spiking graph neural networks
• Structurally Flexible Neural Networks: Evolving the Building Blocks for General Agents
• Deep learning in-depth analysis of crystal graph convolutional neural networks: A new era in materials discovery and its applications
• Improving genome-scale metabolic models of incomplete genomes with deep learning
• Bridging Computational Social Science and Deep Learning: Cultural Dissemination-Inspired Graph Neural Networks
• Climate-Adaptive and Cascade-Constrained Machine Learning Prediction for Sea Surface Height under Greenhouse Warming
• Periodic Graph-Enhanced Multivariate Time Series Anomaly Detector
• A Graph-Neural-Network-Entropy model of vital node identification on network attack and propagation
• Quantum Graph Attention Network: A Novel Quantum Multi-Head Attention Mechanism for Graph Learning
• SeaPearl: A Constraint Programming Solver guided by Reinforcement Learning
• Causality-Induced Positional Encoding for Transformer-Based Representation Learning of Non-Sequential Features
• TF-DWGNet: A Directed Weighted Graph Neural Network with Tensor Fusion for Multi-Omics Cancer Subtype Classification
• Compose by Focus: Scene Graph-based Atomic Skills
• Physics-Informed GCN-LSTM Framework for Long-Term Forecasting of 2D and 3D Microstructure Evolution
• Hierarchical Self-Attention: Generalizing Neural Attention Mechanics to Multi-Scale Problems
• Local-Canonicalization Equivariant Graph Neural Networks for Sample-Efficient and Generalizable Swarm Robot Control
• An End-to-End Differentiable, Graph Neural Network-Embedded Pore Network Model for Permeability Prediction
• JANUS: A Dual-Constraint Generative Framework for Stealthy Node Injection Attacks
• Zero-shot Graph Reasoning via Retrieval Augmented Framework with LLMs
• A Graph Machine Learning Approach for Detecting Topological Patterns in Transactional Graphs
• Multimodal Hate Detection Using Dual-Stream Graph Neural Networks
• EEG-Based Emotion Recognition Using Regularized Graph Neural Networks
• SpaPool: Soft Partition Assignment Pooling for__Graph Neural Networks
• Efficient Hate Speech Detection: Evaluating 38 Models from Traditional Methods to Transformers
• Enhancing Electromagnetic Calorimeter Signal Reconstruction with Machine Learning-Based Noise Discrimination
• EATSA-GNN: Edge-Aware and Two-Stage attention for enhancing graph neural networks based on teacher–student mechanisms for graph node classification
• M4GN: Mesh-based Multi-segment Hierarchical Graph Network for Dynamic Simulations
• Why does your graph neural network fail on some graphs? Insights from exact generalisation error
• Database Views as Explanations for Relational Deep Learning
• Deploying AI for Signal Processing education: Selected challenges and intriguing opportunities
• Hybrid AWD-GCN-BiGRU model for edge-optimized dissolved oxygen prediction in recirculating aquaculture systems
• Data-Efficient Time-Dependent PDE Surrogates: Graph Neural Simulators vs. Neural Operators
• Multi-Stage Graph Neural Networks for Data-Driven Prediction of Natural Convection in Enclosed Cavities
• Distributed Link Sparsification for Scalable Scheduling Using Graph Neural Networks (Journal Version)
• QCA-MolGAN: Quantum Circuit Associative Molecular GAN with Multi-Agent Reinforcement Learning
• A Node-Aware Dynamic Quantization Approach for Graph Collaborative Filtering
• Explicit and Implicit Data Augmentation for Social Event Detection
• Joint Modeling of Entities and Discourse Relations for Coherence Assessment
• Temporal social network modeling of mobile connectivity data with graph neural networks
• Fast and Accurate RFIC Performance Prediction via Pin Level Graph Neural Networks and Probabilistic Flow
• Second-Order Tensorial Partial Differential Equations on Graphs
• Power Grid Control with Graph-Based Distributed Reinforcement Learning
• Ultra Fast Warm Start Solution for Graph Recommendations
• Flow Matters: Directional and Expressive GNNs for Heterophilic Graphs
• Graph Convolutional Network With Pattern-Spatial Interactive and Regional Awareness for Traffic Forecasting
• Curriculum Guided Personalized Subgraph Federated Learning
• PowerGrow: Feasible Co-Growth of Structures and Dynamics for Power Grid Synthesis
• Automated Bug Triaging using Instruction-Tuned Large Language Models
• Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses
• Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks
• Why Relational Graphs Will Save the Next Generation of Vision Foundation Models?
• Statistical Arbitrage in Options Markets by Graph Learning and Synthetic Long Positions
• Efficient Knowledge Graph Unlearning with Zeroth-order Information
• SVDformer: Direction-Aware Spectral Graph Embedding Learning via SVD and Transformer
• DegDiT: Controllable Audio Generation with Dynamic Event Graph Guided Diffusion Transformer
• Scaling Multi-Agent Epistemic Planning through GNN-Derived Heuristics
• Defining and Benchmarking a Data-Centric Design Space for Brain Graph Construction
• Don't be Afraid of Cell Complexes! An Introduction from an Applied Perspective
• AI Models for Depressive Disorder Detection and Diagnosis: A Review
• Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition
• From Heuristics to Data: Quantifying Site Planning Layout Indicators with Deep Learning and Multi-Modal Data
• Graph Neural Diffusion via Generalized Opinion Dynamics
• Hybrid-Hierarchical Fashion Graph Attention Network for Compatibility-Oriented and Personalized Outfit Recommendation
• Graph Learning via Logic-Based Weisfeiler-Leman Variants and Tabularization
• FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detection
• Taking the next step with generative artificial intelligence: The transformative role of multimodal large language models in science education
• CitySeg: A 3D Open Vocabulary Semantic Segmentation Foundation Model in City-scale Scenarios
• Implicit Hypergraph Neural Networks: A Stable Framework for Higher-Order Relational Learning with Provable Guarantees
• Solving Approximation Tasks with Greedy Deep Kernel Methods
• GRAVITY: A Controversial Graph Representation Learning for Vertex Classification
• Differentiated Information Mining: A Semi-supervised Learning Framework for GNNs
• BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks
• Efficient and Scalable Self-Healing Databases Using Meta-Learning and Dependency-Driven Recovery
• Pinching-Antenna Systems (PASS): A Tutorial
• MOTGNN: Interpretable Graph Neural Networks for Multi-Omics Disease Classification
• Deep Learning for School Dropout Detection: A Comparison of Tabular and Graph-Based Models for Predicting At-Risk Students
• Learning Geometric-Aware Quadrature Rules for Functional Minimization
• Graph-based Event Log Repair
• Functional Connectivity Graph Neural Networks
• Comparing Normalization Methods for Portfolio Optimization with Reinforcement Learning
• GaitAdapt: Continual Learning for Evolving Gait Recognition
• A Comprehensive Data-centric Overview of Federated Graph Learning
• GEDAN: Learning the Edit Costs for Graph Edit Distance
• Neovascularization Segmentation via a Multilateral Interaction-Enhanced Graph Convolutional Network
• Solved in Unit Domain: JacobiNet for Differentiable Coordinate-Transformed PINNs
• Federated Graph Unlearning
• Forecasting West Nile virus with deep graph encoders
• RelMap: Reliable Spatiotemporal Sensor Data Visualization via Imputative Spatial Interpolation
• Neighbor-Sampling Based Momentum Stochastic Methods for Training Graph Neural Networks
• Invariant Graph Transformer for Out-of-Distribution Generalization
• MPFSR-Enhanced GNNs: Spectral Graph Neural Networks Enhancement Through Learnable Multiple-Parameter Graph Fractional Fourier Transforms
• INSPIRE-GNN: Intelligent Sensor Placement to Improve Sparse Bicycling Network Prediction via Reinforcement Learning Boosted Graph Neural Networks
• Hybrid Hypergraph Networks for Multimodal Sequence Data Classification
• Hierarchical Graph Neural Network for Compressed Speech Steganalysis
• Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects
• BuildSTG: A Multi-building Energy Load Forecasting Method using Spatio-Temporal Graph Neural Network
• Attributed Graph Clustering with Multi-Scale Weight-Based Pairwise Coarsening and Contrastive Learning
• Who Owns This Sample: Cross-Client Membership Inference Attack in Federated Graph Neural Networks
• Feature Construction Using Network Control Theory and Rank Encoding for Graph Machine Learning
• NAICS-Aware Graph Neural Networks for Large-Scale POI Co-visitation Prediction: A Multi-Modal Dataset and Methodology
• PBiLoss: Popularity-Aware Regularization to Improve Fairness in Graph-Based Recommender Systems
• Geometric Multi-color Message Passing Graph Neural Networks for Blood-brain Barrier Permeability Prediction
• Financial Regulation and AI: A Faustian Bargain?
• Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors
• GIIFT: Graph-guided Inductive Image-free Multimodal Machine Translation
• Deep Learning for Blood-Brain Barrier Permeability Prediction: From Discriminative Models to Mechanism-Aware Design
• Logical Characterizations of GNNs with Mean Aggregation
• ViGText: Deepfake Image Detection with Vision-Language Model Explanations and Graph Neural Networks
• Graph Attention Networks for Detecting Epilepsy from EEG Signals Using Accessible Hardware in Low-Resource Settings
• Research on the application of graph data structure and graph neural network in node classification/clustering tasks
• Integrated Radio Sensing Capabilities for 6G Networks: AI/ML Perspective
• Exploring multi-dimensional interests for session-based recommendation
• C-DOG: Multi-View Multi-instance Feature Association Using Connected δ-Overlap Graphs
• When Speed meets Accuracy: an Efficient and Effective Graph Model for Temporal Link Prediction
• Toward Sustainable Polymer Design: A Molecular Dynamics-Informed Machine Learning Approach for Vitrimers
• Graph Neural Networks Powered by Encoder Embedding for Improved Node Learning
• How did we get there? AI applications to biological networks and sequences
• DualEquiNet: A Dual-Space Hierarchical Equivariant Network for Large Biomolecules
• A Survey on Recommender Systems Using Graph Neural Network
• H²GFM: Towards unifying Homogeneity and Heterogeneity on Text-Attributed Graphs
• A Graph Sufficiency Perspective for Neural Networks
• Adapting to Heterophilic Graph Data with Structure-Guided Neighbor Discovery
• WGLE:Backdoor-free and Multi-bit Black-box Watermarking for Graph Neural Networks
• Forecasting Coccidioidomycosis (Valley Fever) in Arizona: A Graph Neural Network Approach
• Effects of relational graph modularity and depth on the learning performance of neural networks
• Differentially Private Relational Learning with Entity-level Privacy Guarantees
• Heterogeneous Graph Prompt Learning via Adaptive Weight Pruning
• Noise Filtering Algorithm Based on Graph Neural Network for STCF Drift Chamber
• Context Pooling: Query-specific Graph Pooling for Generic Inductive Link Prediction in Knowledge Graphs
• Deep-Learning-Based Pre-Layout Parasitic Capacitance Prediction on SRAM Designs
• On the under-reaching phenomenon in message-passing neural PDE solvers: revisiting the CFL condition
• Beyond Feature and Structure Alignment: Learning Transferable Propagation Knowledge for Graph Foundation Models
• Universal Embeddings of Tabular Data
• DESIGN: Encrypted GNN Inference via Server-Side Input Graph Pruning
• PLACE: Prompt Learning for Attributed Community Search in Large Graphs
• PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs
• Graph Neural Networks as a Substitute for Transformers in Single-Cell Transcriptomics
• Combining Graph Neural Networks and Mixed Integer Linear Programming for Molecular Inference under the Two-Layered Model
• Simplifying Graph Kernels for Efficient
• S2FGL: Spatial Spectral Federated Graph Learning
• Enhancing Swarms Durability to Threats via Graph Signal Processing and GNN-based Generative Modeling
• Learning for mismatch removal via graph attention networks
• MEmilio -- A high performance Modular EpideMIcs simuLatIOn software for multi-scale and comparative simulations of infectious disease dynamics
• AIRES: Accelerating Out-of-Core GCNs via Algorithm-System Co-Design
• Learning for routing: A guided review of recent developments and future directions
• Reconciling Attribute and Structural Anomalies for Improved Graph Anomaly Detection
• Feature Prediction in Quantum Graph Recurrent Neural Networks with Applications in Information Hiding
• Quantum Graph Transformer for NLP Sentiment Classification
• Convergent Privacy Framework for Multi-layer GNNs through Contractive Message Passing
• Task-Agnostic Contrastive Pretraining for Relational Deep Learning
• REDELEX: A Framework for Relational Deep Learning Exploration
• Accelerating GNN Training through Locality-aware Dropout and Merge
• Domain Knowledge in Artificial Intelligence: Using Conceptual Modeling to Increase Machine Learning Accuracy and Explainability
• Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs
• Higher-Order Graph Databases
• Residual Reweighted Conformal Prediction for Graph Neural Networks
• RPHunter: Unveiling Rug Pull Schemes in Crypto Token via Code-and-Transaction Fusion Analysis
• Graphs Meet AI Agents: Taxonomy, Progress, and Future Opportunities
• CEGA: A Cost-Effective Approach for Graph-Based Model Extraction and Acquisition
• AI-based Approach in Early Warning Systems: Focus on Emergency Communication Ecosystem and Citizen Participation in Nordic Countries
• Metapath-based Hyperbolic Contrastive Learning for Heterogeneous Graph Embedding
• PyTorch-based Geometric Learning with Non-CUDA Processing Units: Experiences from Intel Gaudi-v2 HPUs
• Pattern-Based Graph Classification: Comparison of Quality Measures and Importance of Preprocessing
• SEP-GCN: Leveraging Similar Edge Pairs with Temporal and Spatial Contexts for Location-Based Recommender Systems
• Spatiotemporal dynamic network for regional maritime vessel flow prediction amid COVID-19
• Automated Decision-Making on Networks with LLMs through Knowledge-Guided Evolution
• Dynamic Graph Condensation
• MALM: A Multi-Information Adapter for Large Language Models to Mitigate Hallucination
• Directed Acyclic Graph Convolutional Networks
• TrustGLM: Evaluating the Robustness of GraphLLMs Against Prompt, Text, and Structure Attacks
• Graph-Based Physics-Guided Urban PM2.5 Air Quality Imputation with Constrained Monitoring Data
• Towards Multimodal Graph Large Language Model
• Domain-Adversarial Anatomical Graph Networks for Cross-User Human Activity Recognition
• Model-Driven Graph Contrastive Learning
• Deep Learning Reforms Image Matching: A Survey and Outlook
• UniPTMs: The First Unified Multi-type PTM Site Prediction Model via Master-Slave Architecture-Based Multi-Stage Fusion Strategy and Hierarchical Contrastive Loss
• Graph topology estimation of power grids using pairwise mutual information of time series data
• Piecewise Constant Spectral Graph Neural Network
• Cold Start Similar Artists Ranking with Gravity-Inspired Graph Autoencoders
• Regional optimization of new-energy bus charging stations using a hybrid model integrating graph convolutional networks and simulated annealing
• Forecasting UK Consumer Price Inflation with RaGNAR: Random Generalised Network Autoregressive Processes
• Sheaves Reloaded: A Directional Awakening
• Combining social relations and interaction data in Recommender System with Graph Convolution Collaborative Filtering
• Learning Binarized Representations with Pseudo-positive Sample Enhancement for Efficient Graph Collaborative Filtering
• MLaGA: Multimodal Large Language and Graph Assistant
• MVAN: Multi-View Attention Networks for Fake News Detection on Social Media
• Retrieval-Augmented Generation of Ontologies from Relational Databases
• Unlearning Inversion Attacks for Graph Neural Networks
• Beyond Attention: Learning Spatio-Temporal Dynamics with Emergent Interpretable Topologies
• Goal-Aware Identification and Rectification of Misinformation in Multi-Agent Systems
• Subgraph Gaussian Embedding Contrast for Self-Supervised Graph Representation Learning
• Pre-training for Recommendation Unlearning
• Rethinking Federated Graph Learning: A Data Condensation Perspective
• Geometric Hyena Networks for Large-scale Equivariant Learning
• The quest for the GRAph Level autoEncoder (GRALE)
• Learnable Kernel Density Estimation for Graphs
• Identifying Super Spreaders in Multilayer Networks
• A survey of out‐of‐distribution generalization for graph machine learning from a causal view
• Graph Wave Networks
• Towards Effective Federated Multimodal Graph Learning via Navigating Multifaceted Heterogeneity
• An Out-Of-Distribution Membership Inference Attack Approach for Cross-Domain Graph Attacks
• The pointer network for reward maximisation in multi-target space mission sequence selection
• Learning Optimal Multimodal Information Bottleneck Representations
• Meta Pruning via Graph Metanetworks : A Universal Meta Learning Framework for Network Pruning
• Message-Passing State-Space Models: Improving Graph Learning with Modern Sequence Modeling
• FS-DAG: Few Shot Domain Adapting Graph Networks for Visually Rich Document Understanding
• On the use of Graphs for Satellite Image Time Series
• MetaSTH-Sleep: Towards Effective Few-Shot Sleep Stage Classification for Health Management with Spatial-Temporal Hypergraph Enhanced Meta-Learning
• Privacy-Aware Cyberterrorism Network Analysis using Graph Neural Networks and Federated Learning
• Graph Attention Network for Optimal User Association in Wireless Networks
• Refined Modeling of Arctic Circumpolar Building Stock Increases Estimated Mid‐Century Permafrost Degradation Damages
• NeuBM: Mitigating Model Bias in Graph Neural Networks through Neutral Input Calibration
• SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps
• Multi-Scale Harmonic Encoding for Feature-Wise Graph Message Passing
• Oral Imaging for Malocclusion Issues Assessments: OMNI Dataset, Deep Learning Baselines and Benchmarking
• Partition-wise Graph Filtering: A Unified Perspective Through the Lens of Graph Coarsening
• A deep neural network: mechanistic hybrid model to predict pharmacokinetics in rat
• Surrogate Modeling of 3D Rayleigh-Benard Convection with Equivariant Autoencoders
• Graph Neural Networks Based Anomalous RSSI Detection
• Unsupervised Learning of Local Updates for Maximum Independent Set in Dynamic Graphs
• Towards Effective Federated Graph Foundation Model via Mitigating Knowledge Entanglement
• A method for the systematic generation of graph XAI benchmarks via Weisfeiler-Leman coloring
• Synthetic graphs for link prediction benchmarking
• SenseFlow: A Physics-Informed and Self-Ensembling Iterative Framework for Power Flow Estimation
• AH-UGC: Adaptive and Heterogeneous-Universal Graph Coarsening
• Lightweight Spatio-Temporal Attention Network with Graph Embedding and Rotational Position Encoding for Traffic Forecasting
• Prediction of Bank Credit Ratings using Heterogeneous Topological Graph Neural Networks
• Understanding the Capabilities of Molecular Graph Neural Networks in Materials Science Through Multimodal Learning and Physical Context Encoding
• Relation-Aware Graph Foundation Model
• Finding Counterfactual Evidences for Node Classification
• Halting Recurrent GNNs and the Graded μ-Calculus
• On the Development of Descriptor-Based Machine Learning Models for Thermodynamic Properties: Part 2—Applicability Domain and Outliers
• HP-JEPA: Hierarchical Partitioning for Multi-Resolution Graph Joint-Embedding Predictive Learning
• Rethinking Irregular Time Series Forecasting: A Simple yet Effective Baseline
• GNN-Suite: a Graph Neural Network Benchmarking Framework for Biomedical Informatics
• Negative Metric Learning for Graphs
• Schreier-Coset Graph Propagation
• Network models to enhance the translational impact of cross-species studies
• Learning Kronecker-Structured Graphs from Smooth Signals
• SAR-GTR: Attributed Scattering Information Guided SAR Graph Transformer Recognition Algorithm
• Open Your Eyes: Vision Enhances Message Passing Neural Networks in Link Prediction
• GPML: Graph Processing for Machine Learning
• Next Word Suggestion using Graph Neural Network
• HYGMA: Hypergraph Coordination Networks with Dynamic Grouping for Multi-Agent Reinforcement Learning
• Deep Learning for On-Street Parking Violation Prediction
• QSeer: A Quantum-Inspired Graph Neural Network for Parameter Initialization in Quantum Approximate Optimization Algorithm Circuits
• Learn to Think: Bootstrapping LLM Reasoning Capability Through Graph Representation Learning
• Hypergraph Neural Sheaf Diffusion: A Symmetric Simplicial Set Framework for Higher-Order Learning
• Multi-Modal Molecular Representation Learning via Structure Awareness
• GraphComp: Extreme Error-bounded Compression of Scientific Data via Temporal Graph Autoencoders
• Graph-Based Adversarial Domain Generalization with Anatomical Correlation Knowledge for Cross-User Human Activity Recognition
• K-STEMIT: Knowledge-Informed Spatio-Temporal Efficient Multi-Branch Graph Neural Network for Subsurface Stratigraphy Thickness Estimation from Radar Data
• Physics-Assisted and Topology-Informed Deep Learning for Weather Prediction
• Deep Learning for Spatio-Temporal Data Mining: A Survey
• Amplifying Your Social Media Presence: Personalized Influential Content Generation with LLMs
• Graph neural network-based structural classification of glass-forming liquids and its interpretation via self-attention mechanism
• Spectral methods: crucial for machine learning, natural for quantum computers?
• Multi-Hierarchical Fine-Grained Feature Mapping Driven by Feature Contribution for Molecular Odor Prediction
• H2CGL: Modeling dynamics of citation network for impact prediction
• Automated Tensor-Relational Decomposition for Large-Scale Sparse Tensor Computation
• SeLR: Sparsity-enhanced Lagrangian Relaxation for Computation Offloading at the Edge
• Stock Market Prediction Using Node Transformer Architecture Integrated with BERT Sentiment Analysis
• BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning
• MoDE-Boost: Boosting Shared Mobility Demand with Edge-Ready Prediction Models
• Graph Neural Planning and Predictive Control for Multi-Robot Communication-Constrained Unlabeled Motion Planning
• Unified Multi-Domain Graph Pre-training for Homogeneous and Heterogeneous Graphs via Domain-Specific Expert Encoding
• Scalable Multi-Task Learning for Particle Collision Event Reconstruction with Heterogeneous Graph Neural Networks
• FedHERO: A Federated Learning Approach for Node Classification Task on Heterophilic Graphs
• Evaluating Effects of Augmented SELFIES for Molecular Understanding Using QK-LSTM
• Quantifying the Noise of Structural Perturbations on Graph Adversarial Attacks
• Differentiable biology: using deep learning for biophysics-based and data-driven modeling of molecular mechanisms
• High-order Graph Neural Networks with Common Neighbor Awareness for Link Prediction
• Synthetic Pattern Generation and Detection of Financial Activities using Graph Autoencoders
• TAG-HGT: A Scalable and Cost-Effective Framework for Inductive Cold-Start Academic Recommendation
• When Should Graph Attention Be Sparse? Learning a Per-Edge Tsallis Index
• NodeJEPA: Structure-Conditioned Latent Prediction for Node-Level Graph Self-Supervised Learning
• Graphusion: Latent Diffusion for Graph Generation
• Sparsity-Aware Communication for Distributed Graph Neural Network Training
• Unifying Physics- and Data-Driven Modeling via Novel Causal Spatiotemporal Graph Neural Network for Interpretable Epidemic Forecasting
• Topology-Aware Reasoning over Incomplete Knowledge Graph with Graph-Based Soft Prompting
• p2pGNN: A Decentralized Graph Neural Network for Node Classification in Peer-to-Peer Networks
• A Comprehensive Survey of Synthetic Tabular Data Generation
• Bi-GRCN: A Spatio-Temporal Traffic Flow Prediction Model Based on Graph Neural Network
• Graph Convolutional Subspace Clustering: A Robust Subspace Clustering Framework for Hyperspectral Image
• Anomaly Detection on Attributed Networks via Contrastive Self-Supervised Learning
• Benchmarking machine learning models for predicting aerofoil performance
• Rhythm of Opinion: A Hawkes-Graph Framework for Dynamic Propagation Analysis
• The role of artificial intelligence for dengue prevention, control, and management: A technical narrative review
• Multi-Level Attention Pooling for Graph Neural Networks: Unifying Graph Representations with Multiple Localities
• Rethinking Client-oriented Federated Graph Learning
• A Comparison of Neural Network Architectures for Data-Driven Reduced-Order Modeling
• Device Sampling for Heterogeneous Federated Learning: Theory, Algorithms, and Implementation
• EG-Gaussian: Epipolar Geometry and Graph Network Enhanced 3D Gaussian Splatting
• Scalable Graph Neural Network Training
• Dairy Cow Rumination Detection: A Deep Learning Approach
• A multi-view graph neural network for building age prediction
• OmiEmbed: A Unified Multi-Task Deep Learning Framework for Multi-Omics Data
• Deep Neural Networks and Tabular Data: A Survey
• IMMENSE: Inductive Multi-perspective User Classification in Social Networks
• DocSAM: Unified Document Image Segmentation via Query Decomposition and Heterogeneous Mixed Learning
• Trajectory Encoding Temporal Graph Networks
• Weight-of-Thought Reasoning: Exploring Neural Network Weights for Enhanced LLM Reasoning
• Ensemble-Enhanced Graph Autoencoder with GAT and Transformer-Based Encoders for Robust Fault Diagnosis
• A review on deep learning for vision-based hand detection, hand segmentation and hand gesture recognition in human–robot interaction
• ClimateBench-M: A Multi-Modal Climate Data Benchmark with a Simple Generative Method
• Decentralizing AI Memory: SHIMI, a Semantic Hierarchical Memory Index for Scalable Agent Reasoning
• DMol: A Highly Efficient and Chemical Motif-Preserving Molecule Generation Platform

Discussions

• A Comprehensive Survey on Graph Neural Networks (2019) [hn, 19 points, 0 comments]

Related

• A Comprehensive Survey on Graph Neural Networks
• Graph Neural Networks: Methods, Applications, and Opportunities
• Deep Learning on Graphs: A Survey
• Graph Neural Networks: A Review of Methods and Applications
• Graph neural networks: A review of methods and applications