Graph Attention Networks

2017/10/30 by Petar Veličković, Veličković, Petar, Guillem Cucurull +9 · 2 voices · 765 citations
#stat.ML #cs.AI #cs.LG #cs.SI

paper · pdf · doi:10.48550/arxiv.1710.10903

Abstract

We present graph attention networks (GATs), novel neural network architectures that operate on graph-structured data, leveraging masked self-attentional layers to address the shortcomings of prior methods based on graph convolutions or their approximations. By stacking layers in which nodes are able to attend over their neighborhoods' features, we enable (implicitly) specifying different weights to different nodes in a neighborhood, without requiring any kind of costly matrix operation (such as inversion) or depending on knowing the graph structure upfront. In this way, we address several key challenges of spectral-based graph neural networks simultaneously, and make our model readily applicable to inductive as well as transductive problems. Our GAT models have achieved or matched state-of-the-art results across four established transductive and inductive graph benchmarks: the Cora, Citeseer and Pubmed citation network datasets, as well as a protein-protein interaction dataset (wherein test graphs remain unseen during training).

Cited by

• Task-driven Heterophilic Graph Structure Learning
• Domain matters: Towards domain-informed evaluation for link prediction
• Graph Neural Networks with Transformer Fusion of Brain Connectivity Dynamics and Tabular Data for Forecasting Future Tobacco Use
• With Great Context Comes Great Prediction Power: Classifying Objects via Geo-Semantic Scene Graphs
• Debugging Tabular Log as Dynamic Graphs
• BLISS: Bandit Layer Importance Sampling Strategy for Efficient Training of Graph Neural Networks
• Multi-Head Spectral-Adaptive Graph Anomaly Detection
• Interpretable and Adaptive Node Classification on Heterophilic Graphs via Combinatorial Scoring and Hybrid Learning
• Pruning Graphs by Adversarial Robustness Evaluation to Strengthen GNN Defenses
• Focus Is All You Need: Adaptive Goal-aware Attention Orchestration for Multi-Agent Graph Systems
• Unsupervised Graph Representation Learning with Complementary View Alignment
• Backend-Aware Graph Learning for Denoising Outcome Distributions in Quantum Program Testing
• ParasGB: A Graph Benchmark Suite for Parasitic Estimation on AMS Circuits
• HeAD-CP: Heterophily-Aware Diffused Conformal Prediction Sets for Graph Neural Networks
• AuthentiCity: A Multi-Source Provenance-Aware Knowledge Graph and Benchmark for 3D City Models
• Multi-Phonation Graph Learning with Self-Supervised Speech Embeddings for ALS Detection and Progression Prediction
• Zhinv: Real-time hub-height wind field reconstruction using only local sparse observations
• AMPBench-MT: A Homology-Controlled Benchmark for Antimicrobial Peptide Potency, Spectrum, and Safety Prediction
• Eliminating Propagation Delay: Attention-Based Spatial-Temporal Fusion Graph Convolution Network for Traffic Flow Prediction
• Domain-Prior-Regularized Graph Modeling for Anomaly Detection in Cyber-Physical Systems
• Spatial Prediction of Soil Microplastics and Organic Matter Using Graph Attention Networks
• Reading Without a Reader: Large Language Models Collapse Reading and Writing into a Single Entangled Code
• Plain Transformers are Surprisingly Powerful Link Predictors
• TextBridgeGNN: Pre-training Graph Neural Network for Cross-Domain Recommendation via Text-Guided Transfer
• SparScene: Efficient Traffic Scene Representation via Sparse Graph Learning for Large-Scale Trajectory Generation
• Beyond Context: Large Language Models Failure to Grasp Users Intent
• Semantic Refinement with LLMs for Graph Representations
• A Multi-fidelity Double-Delta Wing Dataset and Empirical Scaling Laws for GNN-based Aerodynamic Field Surrogate
• DGSAN: Dual-Graph Spatiotemporal Attention Network for Pulmonary Nodule Malignancy Prediction
• From GNNs to Symbolic Surrogates via Kolmogorov-Arnold Networks for Delay Prediction
• A Community-Enhanced Graph Representation Model for Link Prediction
• A Novel Graph-Sequence Learning Model for Inductive Text Classification
• Jensen-Shannon Divergence Message-Passing for Rich-Text Graph Representation Learning
• GraphFire-X: Physics-Informed Graph Attention Networks and Structural Gradient Boosting for Building-Scale Wildfire Preparedness at the Wildland-Urban Interface
• MAPI-GNN: Multi-Activation Plane Interaction Graph Neural Network for Multimodal Medical Diagnosis
• Kolmogorov-Arnold Graph Neural Networks Applied to Inorganic Nanomaterials Dataset
• Learning Continuous Solvent Effects from Transient Flow Data: A Graph Neural Network Benchmark on Catechol Rearrangement
• ChemATP: A Training-Free Chemical Reasoning Framework for Large Language Models
• Hyperbolic Graph Embeddings: a Survey and an Evaluation on Anomaly Detection
• Learning to Design City-scale Transit Routes
• Text2Graph VPR: A Text-to-Graph Expert System for Explainable Place Recognition in Changing Environments
• Feature-Enhanced Graph Neural Networks for Classification of Synthetic Graph Generative Models: A Benchmarking Study
• APC-GNN++: An Adaptive Patient-Centric GNN with Context-Aware Attention and Mini-Graph Explainability for Diabetes Classification
• AutoSchA: Automatic Hierarchical Music Representations via Multi-Relational Node Isolation
• Toward Efficient Testing of Graph Neural Networks via Test Input Prioritization
• FairExpand: Individual Fairness on Graphs with Partial Similarity Information
• On Swarm Leader Identification using Probing Policies
• Through the PRISm: Importance-Aware Scene Graphs for Image Retrieval
• Grad: Guided Relation Diffusion Generation for Graph Augmentation in Graph Fraud Detection
• Systemic Risk Radar: A Multi-Layer Graph Framework for Early Market Crash Warning
• Deep learning directed synthesis of fluid ferroelectric materials
• Microsoft Academic Graph Information Retrieval for Research Recommendation and Assistance
• Graph Neural Networks for Source Detection: A Review and Benchmark Study
• Sharpness-aware Federated Graph Learning
• Coarse-to-Fine Open-Set Graph Node Classification with Large Language Models
• A Multimodal Approach to Alzheimer's Diagnosis: Geometric Insights from Cube Copying and Cognitive Assessments
• Graph Neural Networks for Interferometer Simulations
• How Smoothing is N-simplicial Attention?
• Machine learning for RNA-targeting drug design
• ScamSweeper: Detecting Illegal Accounts in Web3 Scams via Transactions Analysis
• 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
• ParaFormer: A Generalized PageRank Graph Transformer for Graph Representation Learning
• A Graph-Based Forensic Framework for Inferring Hardware Noise of Cloud Quantum Backend
• Beyond MMD: Evaluating Graph Generative Models with Geometric Deep Learning
• Topologically-Stabilized Graph Neural Networks: Empirical Robustness Across Domains
• LightTopoGAT: Enhancing Graph Attention Networks with Topological Features for Efficient Graph Classification
• CORE: Contrastive Masked Feature Reconstruction on Graphs
• Enhancing Node-Level Graph Domain Adaptation by Alleviating Local Dependency
• Towards Practical Large-scale Dynamical Heterogeneous Graph Embedding: Cold-start Resilient Recommendation
• From Small to Large: Generalization Bounds for Transformers on Variable-Size Inputs
• Understanding When Graph Convolutional Networks Help: A Diagnostic Study on Label Scarcity and Structural Properties
• Network-Wide Traffic Volume Estimation from Speed Profiles using a Spatio-Temporal Graph Neural Network with Directed Spatial Attention
• Modeling Authorial Style in Urdu Novels Using Character Interaction Graphs and Graph Neural Networks
• A Graph Attention Network-Based Framework for Reconstructing Missing LiDAR Beams
• Bridging Data and Physics: A Graph Neural Network-Based Hybrid Twin Framework
• GraphPerf-RT: A Graph-Driven Performance Model for Hardware-Aware Scheduling of OpenMP Codes
• Advancing Cache-Based Few-Shot Classification via Patch-Driven Relational Gated Graph Attention
• Can Graphs Improve Tabular Foundation Models?
• Fully Inductive Node Representation Learning via Graph View Transformation
• Personalized Pricing in Social Networks with Individual and Group Fairness Considerations
• GLOW: Graph-Language Co-Reasoning for Agentic Workflow Performance Prediction
• Neural Ranging Inertial Odometry
• Supervised Learning of Random Neural Architectures Structured by Latent Random Fields on Compact Boundaryless Multiply-Connected Manifolds
• Better Prevent than Tackle: Valuing Defense in Soccer Based on Graph Neural Networks
• HypeR Adaptivity: Joint hr-Adaptive Meshing via Hypergraph Multi-Agent Deep Reinforcement Learning
• Representation of the structure of graphs by sequences of instructions
• A Simulation Framework for Studying Recommendation-Network Co-evolution in Social Platforms
• M3Net: A Multi-Metric Mixture of Experts Network Digital Twin with Graph Neural Networks
• Drawback of Enforcing Equivariance and its Compensation via the Lens of Expressive Power
• CLARGA: Multimodal Graph Representation Learning over Arbitrary Sets of Modalities
• BugSweeper: Function-Level Detection of Smart Contract Vulnerabilities Using Graph Neural Networks
• Can TabPFN Compete with GNNs for Node Classification via Graph Tabularization?
• Beyond Detection: A Comprehensive Benchmark and Study on Representation Learning for Fine-Grained Webshell Family Classification
• Solving Oversmoothing in GNNs via Nonlocal Message Passing: Algebraic Smoothing and Depth Scalability
• gHAWK: Local and Global Structure Encoding for Scalable Training of Graph Neural Networks on Knowledge Graphs
• Understanding the Failure Modes of Transformers through the Lens of Graph Neural Networks
• PINE: Pipeline for Important Node Exploration in Attributed Networks
• Mitigating Bias in Graph Hyperdimensional Computing
• Edged Weisfeiler-Lehman Algorithm
• Measuring Over-smoothing beyond Dirichlet energy
• Mitigating Structural Overfitting: A Distribution-Aware Rectification Framework for Missing Feature Imputation
• The Impact of Data Characteristics on GNN Evaluation for Detecting Fake News
• 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
• Empowering GNNs for Domain Adaptation via Denoising Target Graph
• Physics-Informed Graph Neural Network with Frequency-Aware Learning for Optical Aberration Correction
• Sepsis Prediction Using Graph Convolutional Networks over Patient-Feature-Value Triplets
• PVLS: A Learning-based Parameter Prediction Technique for Variational Quantum Linear Solvers
• Probabilistic Dynamic Line Rating with Line Graph Convolutional LSTM
• Explainable Graph Representation Learning via Graph Pattern Analysis
• Exploring Topological Bias in Heterogeneous Graph Neural Networks
• Detection of Intoxicated Individuals from Facial Video Sequences via a Recurrent Fusion Model
• Procedural Mistake Detection via Action Effect Modeling
• VS-Graph: Scalable and Efficient Graph Classification Using Hyperdimensional Computing
• ProteinPNet: Prototypical Part Networks for Concept Learning in Spatial Proteomics
• Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation
• GraphMatch: Fusing Language and Graph Representations in a Dynamic Two-Sided Work Marketplace
• Conformal Correction for Efficiency May be at Odds with Entropy
• Dynamic Configuration of On-Street Parking Spaces using Multi Agent Reinforcement Learning
• Layered Division and Global Allocation for Community Detection in Multilayer Network
• Tracing Footsteps of Similar Cities: Modeling Urban Economic Vitality with Dynamic Inter-City Graph Embeddings
• A Multi-View Multi-Timescale Hypergraph-Empowered Spatiotemporal Framework for EV Charging Forecasting
• Cross-View Topology-Aware Graph Representation Learning
• QGShap: Quantum Acceleration for Faithful GNN Explanations
• Mofasa: A Step Change in Metal-Organic Framework Generation
• Morphling: Fast, Fused, and Flexible GNN Training at Scale
• Learning to Reconstruct: A Differentiable Approach to Muon Tracking at the LHC
• End-to-end Deep Reinforcement Learning for Stochastic Multi-objective Optimization in C-VRPTW
• Heuristic algorithms for the stochastic critical node detection problem
• Efficiently Learning Branching Networks for Multitask Algorithmic Reasoning
• Approximate Bayesian Inference on Mechanisms of Network Growth and Evolution
• Generalized Graph Transformer Variational Autoencoder
• Graph Data Augmentation with Contrastive Learning on Covariate Distribution Shift
• TrendGNN: Towards Understanding of Epidemics, Beliefs, and Behaviors
• Graph-Attention Network with Adversarial Domain Alignment for Robust Cross-Domain Facial Expression Recognition
• GCMCG: A Clustering-Aware Graph Attention and Expert Fusion Network for Multi-Paradigm, Multi-task, and Cross-Subject EEG Decoding
• Polynomial Neural Sheaf Diffusion: A Spectral Filtering Approach on Cellular Sheaves
• Tree Matching Networks for Natural Language Inference: Parameter-Efficient Semantic Understanding via Dependency Parse Trees
• HyperADRs: A Hierarchical Hypergraph Framework for Drug-Gene-ADR Prediction
• ARM-Explainer -- Explaining and improving graph neural network predictions for the maximum clique problem using node features and association rule mining
• Intelligent Neural Networks: From Layered Architectures to Graph-Organized Intelligence
• ParaGate: Parasitic-Driven Domain Adaptation Transfer Learning for Netlist Performance Prediction
• Model-Agnostic Fairness Regularization for GNNs with Incomplete Sensitive Information
• ARPGNet: Appearance- and Relation-aware Parallel Graph Attention Fusion Network for Facial Expression Recognition
• PISA: Prioritized Invariant Subgraph Aggregation
• Enhanced Graph Convolutional Network with Chebyshev Spectral Graph and Graph Attention for Autism Spectrum Disorder Classification
• A decoupled alignment kernel for peptide membrane permeability predictions
• Odin: Oriented Dual-module Integration for Text-rich Network Representation Learning
• The Final-Stage Bottleneck: A Systematic Dissection of the R-Learner for Network Causal Inference
• Are Graph Transformers Necessary? Efficient Long-Range Message Passing with Fractal Nodes in MPNNs
• Accelerating Materials Discovery: Learning a Universal Representation of Chemical Processes for Cross-Domain Property Prediction
• SA²GFM: Enhancing Robust Graph Foundation Models with Structure-Aware Semantic Augmentation
• Knowledge Completes the Vision: A Multimodal Entity-aware Retrieval-Augmented Generation Framework for News Image Captioning
• Accumulated Local Effects and Graph Neural Networks for link prediction
• E2E-GRec: An End-to-End Joint Training Framework for Graph Neural Networks and Recommender Systems
• Short-Range Oversquashing
• LLM-Driven Transient Stability Assessment: From Automated Simulation to Neural Architecture Design
• Towards A Tri-View Diffusion Framework for Recommendation
• InF-ATPG: Intelligent FFR-Driven ATPG with Advanced Circuit Representation Guided Reinforcement Learning
• Cross-Contrastive Clustering for Multimodal Attributed Graphs with Dual Graph Filtering
• Rethinking Semi-Supervised Node Classification with Self-Supervised Graph Clustering
• Hierarchical Spatio-Temporal Attention Network with Adaptive Risk-Aware Decision for Forward Collision Warning in Complex Scenarios
• Collaborate sim and real: Robot Bin Packing Learning in Real-world and Physical Engine
• Decoupling and Damping: Structurally-Regularized Gradient Matching for Multimodal Graph Condensation
• Rethinking Message Passing Neural Networks with Diffusion Distance-guided Stress Majorization
• Resolving Node Identifiability in Graph Neural Processes via Laplacian Spectral Encodings
• Hypergraph Contrastive Learning for both Homophilic and Heterophilic Hypergraphs
• ActDistill: General Action-Guided Self-Derived Distillation for Efficient Vision-Language-Action Models
• Towards Efficient LLM-aware Heterogeneous Graph Learning
• CroTad: A Contrastive Reinforcement Learning Framework for Online Trajectory Anomaly Detection
• Aggregating Direct and Indirect Neighbors through Graph Linear Transformations
• NutriScreener: Retrieval-Augmented Multi-Pose Graph Attention Network for Malnourishment Screening
• PersonalizedRouter: Personalized LLM Routing via Graph-based User Preference Modeling
• When Structure Doesn't Help: LLMs Do Not Read Text-Attributed Graphs as Effectively as We Expected
• Rotation-Parameterized Graph Fractional Fourier Transform: Definition, Properties, and Optimal Filtering
• Graph Neural Networks for Surgical Scene Segmentation
• Dynamic Multiple-Parameter Joint Time-Vertex Fractional Fourier Transform and its Intelligent Filtering Methods
• Gauge-Equivariant Graph Networks via Self-Interference Cancellation
• GCL-OT: Graph Contrastive Learning with Optimal Transport for Heterophilic Text-Attributed Graphs
• Graph Query Networks for Object Detection with Automotive Radar
• BrainHGT: A Hierarchical Graph Transformer for Interpretable Brain Network Analysis
• Neurocircuitry-Inspired Hierarchical Graph Causal Attention Networks for Explainable Depression Identification
• 3D-Guided Scalable Flow Matching for Generating Volumetric Tissue Spatial Transcriptomics from Serial Histology
• Complex-Weighted Convolutional Networks: Provable Expressiveness via Complex Diffusion
• InteractiveGNNExplainer: A Visual Analytics Framework for Multi-Faceted Understanding and Probing of Graph Neural Network Predictions
• Transformer-Based Multi-Agent Reinforcement Learning for Networked Systems with Long-Range Interactions
• Self-Adaptive Graph Mixture of Models
• Connectivity-Guided Sparsification of 2-FWL GNNs: Preserving Full Expressivity with Improved Efficiency
• Efficient Curvature-aware Graph Network
• Hierarchical Frequency-Decomposition Graph Neural Networks for Road Network Representation Learning
• VISAGNN: Versatile Staleness-Aware Efficient Training on Large-Scale Graphs
• Echoless Label-Based Pre-computation for Memory-Efficient Heterogeneous Graph Learning
• ViTE: Virtual Graph Trajectory Expert Router for Pedestrian Trajectory Prediction
• A Code Smell Refactoring Approach using GNNs
• Graph Attention Network for Predicting Duration of Large-Scale Power Outages Induced by Natural Disasters
• A Systematic Study of Model Extraction Attacks on Graph Foundation Models
• MP-GFormer: A 3D-Geometry-Aware Dynamic Graph Transformer Approach for Machining Process Planning
• Enhancing Graph Representations with Neighborhood-Contextualized Message-Passing
• DialogGraph-LLM: Graph-Informed LLMs for End-to-End Audio Dialogue Intent Recognition
• Graph Neural Networks, Deep Reinforcement Learning and Probabilistic Topic Modeling for Strategic Multiagent Settings
• Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners
• GraphSB: Boosting Imbalanced Node Classification on Graphs through Structural Balance
• MIRNet: Integrating Constrained Graph-Based Reasoning with Pre-training for Diagnostic Medical Imaging
• Spatio-Temporal Data Enhanced Vision-Language Model for Traffic Scene Understanding
• Rethinking Graph Super-resolution: Dual Frameworks for Topological Fidelity
• CO2-Meter: A Comprehensive Carbon Footprint Estimator for LLMs on Edge Devices
• SENCA-st: Integrating Spatial Transcriptomics and Histopathology with Cross Attention Shared Encoder for Region Identification in Cancer Pathology
• One Model for All: Universal Pre-training for EEG based Emotion Recognition across Heterogeneous Datasets and Paradigms
• BDD2Seq: Enabling Scalable Reversible-Circuit Synthesis via Graph-to-Sequence Learning
• HiLoMix: Robust High- and Low-Frequency Graph Learning Framework for Mixing Address Association
• Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics
• LOw-cOst yet High-Performant Sparse Matrix-Matrix Multiplication on Arm SME Architectures
• Gate-level boolean evolutionary geometric attention neural networks
• Stuart-Landau Oscillatory Graph Neural Network
• Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric
• Combining LLM Semantic Reasoning with GNN Structural Modeling for Multi-View Multi-Label Feature Selection
• Enhancing Logical Expressiveness in Graph Neural Networks via Path-Neighbor Aggregation
• Versatile and Risk-Sensitive Cardiac Diagnosis via Graph-Based ECG Signal Representation
• ACGraph: An Efficient Asynchronous Out-of-Core Graph Processing Framework
• A Circular Argument : Does RoPE need to be Equivariant for Vision?
• ARAC: Adaptive Regularized Multi-Agent Soft Actor-Critic in Graph-Structured Adversarial Games
• KAT-GNN: A Knowledge-Augmented Temporal Graph Neural Network for Risk Prediction in Electronic Health Records
• CGLE: Class-label Graph Link Estimator for Link Prediction
• OntoTune: Ontology-Driven Learning for Query Optimization with Convolutional Models
• Beyond Fixed Depth: Adaptive Graph Neural Networks for Node Classification Under Varying Homophily
• Adaptive Initial Residual Connections for GNNs with Theoretical Guarantees
• MG-HGNN: A Heterogeneous GNN Framework for Indoor Wi-Fi Fingerprint-Based Localization
• Learning Time-Varying Graph Signals via Koopman
• How Wide and How Deep? Mitigating Over-Squashing of GNNs via Channel Capacity Constrained Estimation
• Adaptive Multi-view Graph Contrastive Learning via Fractional-order Neural Diffusion Networks
• Reperio-rPPG: Relational Temporal Graph Neural Networks for Periodicity Learning in Remote Physiological Measurement
• Impacts of Data Splitting Strategies on Parameterized Link Prediction Algorithms
• Sign language recognition from skeletal data using graph and recurrent neural networks
• DGTN: Graph-Enhanced Transformer with Diffusive Attention Gating Mechanism for Enzyme DDG Prediction
• Building Specialized Software-Assistant ChatBot with Graph-Based Retrieval-Augmented Generation
• Optimizing Classification of Infrequent Labels by Reducing Variability in Label Distribution
• wa-hls4ml: A Benchmark and Surrogate Models for hls4ml Resource and Latency Estimation
• Ada-FCN: Adaptive Frequency-Coupled Network for fMRI-Based Brain Disorder Classification
• DeNoise: Learning Robust Graph Representations for Unsupervised Graph-Level Anomaly Detection
• GNN-MoE: Context-Aware Patch Routing using GNNs for Parameter-Efficient Domain Generalization
• GraphCliff: Short-Long Range Gating for Subtle Differences but Critical Changes
• Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks
• A Transferable Machine Learning Approach to Predict Quantum Circuit Parameters for Electronic Structure Problems
• GRAVER: Generative Graph Vocabularies for Robust Graph Foundation Models Fine-tuning
• Enhancing composition-based materials property prediction by cross-modal knowledge transfer
• GMoPE:A Prompt-Expert Mixture Framework for Graph Foundation Models
• Emotion Recognition in Multi-Speaker Conversations through Speaker Identification, Knowledge Distillation, and Hierarchical Fusion
• QAGT-MLP: An Attention-Based Graph Transformer for Small and Large-Scale Quantum Error Mitigation
• Scaling Multi-Agent Environment Co-Design with Diffusion Models
• An Interdisciplinary and Cross-Task Review on Missing Data Imputation
• Digital Twin-Driven Pavement Health Monitoring and Maintenance Optimization Using Graph Neural Networks
• Benchmark-Ready 3D Anatomical Shape Classification
• Object Detection as an Optional Basis: A Graph Matching Network for Cross-View UAV Localization
• Evolving Graph Learning for Out-of-Distribution Generalization in Non-stationary Environments
• Optimizing Multi-Lane Intersection Performance in Mixed Autonomy Environments
• SLIP: Structural-aware Language-Image Pretraining for Vision-Language Alignment
• Rethinking LLM Human Simulation: When a Graph is What You Need
• Predictive Auxiliary Learning for Belief-based Multi-Agent Systems
• G2rammar: Bilingual Grammar Modeling for Enhanced Text-attributed Graph Learning
• X-TRACK: Physics-Aware xLSTM for Realistic Vehicle Trajectory Prediction
• Traceable Drug Recommendation over Medical Knowledge Graphs
• Multi-Modal Feature Fusion for Spatial Morphology Analysis of Traditional Villages via Hierarchical Graph Neural Networks
• Relation-Aware Bayesian Optimization of DBMS Configurations Guided by Affinity Scores
• Spectral Neural Graph Sparsification
• HEIR: Learning Graph-Based Motion Hierarchies
• Developing a Multi-task Ensemble Geometric Deep Network for Supply Chain Sustainability and Risk Management
• Learning Geometry: A Framework for Building Adaptive Manifold Models through Metric Optimization
• Fixed-point graph convolutional networks against adversarial attacks
• Fourier Neural Operators for Two-Phase, 2D Mold-Filling Problems Related to Metal Casting
• Transformers Provably Learn Directed Acyclic Graphs via Kernel-Guided Mutual Information
• Beyond Leakage and Complexity: Towards Realistic and Efficient Information Cascade Prediction
• When Prompts Ignore Structure: Graph-Based Attribute Reasoning for Calibrated VLMs
• AgentGFM: A Graph Foundation Model with Node-Agent Information-Flow Control
• Generalization of Graph Neural Network Models for Distribution Grid Fault Detection
• Surrogate Assisted Diversity Estimation in Neural Ensemble Search
• MANDO-LLM: Heterogeneous Graph Transformers with Large Language Models for Smart Contract Vulnerability Detection
• Bridging the Divide: End-to-End Sequence-Graph Learning
• H3M-SSMoEs: Hypergraph-based Multimodal Learning with LLM Reasoning and Style-Structured Mixture of Experts
• MaGNet: A Mamba Dual-Hypergraph Network for Stock Prediction via Temporal-Causal and Global Relational Learning
• Resource Allocation in Hybrid Radio-Optical IoT Networks using GNN with Multi-task Learning
• MIC-BEV: Multi-Infrastructure Camera Bird's-Eye-View Transformer with Relation-Aware Fusion for 3D Object Detection
• From Cross-Task Examples to In-Task Prompts: A Graph-Based Pseudo-Labeling Framework for In-context Learning
• MAGNET: A Multi-Graph Attentional Network for Code Clone Detection
• HyperGraphX: Graph Transductive Learning with Hyperdimensional Computing and Message Passing
• DynBERG: Dynamic BERT-based Graph neural network for financial fraud detection
• Classifying irritable bowel syndrome using spatio-temporal graph convolution networks on brain functional MRI data
• Scaffold-Aware Generative Augmentation and Reranking for Enhanced Virtual Screening
• Image Categorization and Search via a GAT Autoencoder and Representative Models
• Connectome-Guided Automatic Learning Rates for Deep Networks
• Toward General Digraph Contrastive Learning: A Dual Spatial Perspective
• Adaptive Dual Prompting: Hierarchical Debiasing for Fairness-aware Graph Neural Networks
• QoSGMAA: A Robust Multi-Order Graph Attention and Adversarial Framework for Sparse QoS Prediction
• Manifold Approximation leads to Robust Kernel Alignment
• Sound Logical Explanations for Mean Aggregation Graph Neural Networks
• FastJAM: a Fast Joint Alignment Model for Images
• Logical GANs: Adversarial Learning through Ehrenfeucht Fraisse Games
• If You Want to Be Robust, Be Wary of Initialization
• Enhancing Graph Classification Robustness with Singular Pooling
• DynaCausal: Dynamic Causality-Aware Root Cause Analysis for Distributed Microservices
• JiuTian Chuanliu: A Large Spatiotemporal Model for General-purpose Dynamic Urban Sensing
• A roadmap for curvature-based geometric data analysis and learning
• Pedagogy-driven Evaluation of Generative AI-powered Intelligent Tutoring Systems
• Cross-Paradigm Graph Backdoor Attacks with Promptable Subgraph Triggers
• Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval
• Toward Robust Signed Graph Learning through Joint Input-Target Denoising
• GraphTOP: Graph Topology-Oriented Prompting for Graph Neural Networks
• Beyond Augmentation: Leveraging Inter-Instance Relation in Self-Supervised Representation Learning
• Does Homophily Help in Robust Test-time Node Classification?
• TrajGATFormer: A Graph-Based Transformer Approach for Worker and Obstacle Trajectory Prediction in Off-site Construction Environments
• Dynamic Graph Neural Network for Data-Driven Physiologically Based Pharmacokinetic Modeling
• A Hybrid GNN-LSE Method for Fast, Robust, and Physically-Consistent AC Power Flow
• Foundation of Intelligence: Review of Math Word Problems from Human Cognition Perspective
• HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passing
• Estimating Treatment Effects in Networks using Domain Adversarial Training
• Relieving the Over-Aggregating Effect in Graph Transformers
• Adaptive Graph Mixture of Residual Experts: Unsupervised Learning on Diverse Graphs with Heterogeneous Specialization
• Large Language Models Meet Text-Attributed Graphs: A Survey of Integration Frameworks and Applications
• Attention Enhanced Entity Recommendation for Intelligent Monitoring in Cloud Systems
• Generalizable Reasoning through Compositional Energy Minimization
• MolBridge: Atom-Level Joint Graph Refinement for Robust Drug-Drug Interaction Event Prediction
• Learning Decentralized Routing Policies via Graph Attention-based Multi-Agent Reinforcement Learning in Lunar Delay-Tolerant Networks
• Crisis-Resilient Portfolio Management via Graph-based Spatio-Temporal Learning
• TAMI: Taming Heterogeneity in Temporal Interactions for Temporal Graph Link Prediction
• GRACE: Graph Neural Networks for Locus-of-Care Prediction under Extreme Class Imbalance
• HGraphScale: Hierarchical Graph Learning for Autoscaling Microservice Applications in Container-based Cloud Computing
• InvDec: Inverted Decoder for Multivariate Time Series Forecasting with Separated Temporal and Variate Modeling
• Quantifying Distributional Invariance in Causal Subgraph for IRM-Free Graph Generalization
• Learning Noise-Resilient and Transferable Graph-Text Alignment via Dynamic Quality Assessment
• From Newborn to Impact: Bias-Aware Citation Prediction
• Online Handwritten Signature Verification Based on Temporal-Spatial Graph Attention Transformer
• Bridging Earth and Space: A Survey on HAPS for Non-Terrestrial Networks
• Enhancing Graph Neural Networks: A Mutual Learning Approach
• An Active Diffusion Neural Network for Graphs
• Benchmarking Fairness-aware Graph Neural Networks in Knowledge Graphs
• 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
• PDE-Free Mass-Constrained Learning of Complex Systems with Hidden States: The crowd dynamics case
• Deeper with Riemannian Geometry: Overcoming Oversmoothing and Oversquashing for Graph Foundation Models
• Model Metamers Reveal Invariances in Graph Neural Networks
• Robustness in Text-Attributed Graph Learning: Insights, Trade-offs, and New Defenses
• Fighter: Unveiling the Graph Convolutional Nature of Transformers in Time Series Modeling
• Explainable Heterogeneous Anomaly Detection in Financial Networks via Adaptive Expert Routing
• Graph4MM: Weaving Multimodal Learning with Structural Information
• EventFormer: A Node-graph Hierarchical Attention Transformer for Action-centric Video Event Prediction
• ProtoMol: Enhancing Molecular Property Prediction via Prototype-Guided Multimodal Learning
• PassREfinder-FL: Privacy-Preserving Credential Stuffing Risk Prediction via Graph-Based Federated Learning for Representing Password Reuse between Websites
• SADCHER: Scheduling using Attention-based Dynamic Coalitions of Heterogeneous Robots in Real-Time
• Capturing Context-Aware Route Choice Semantics for Trajectory Representation Learning
• An insight into the rare Z→ b bγ at the HL-LHC
• Stealthy Dual-Trigger Backdoors: Attacking Prompt Tuning in LM-Empowered Graph Foundation Models
• DARTS-GT: Differentiable Architecture Search for Graph Transformers with Quantifiable Instance-Specific Interpretability Analysis
• RoBCtrl: Attacking GNN-Based Social Bot Detectors via Reinforced Manipulation of Bots Control Interaction
• T3former: Temporal Graph Classification with Topological Machine Learning
• Inferred global dense residue transition graphs from primary structure sequences enable protein interaction prediction via directed graph convolutional neural networks
• Interpretable Neuropsychiatric Diagnosis via Concept-Guided Graph Neural Networks
• Rethinking Graph Domain Adaptation: A Spectral Contrastive Perspective
• 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
• CAMNet: Leveraging Cooperative Awareness Messages for Vehicle Trajectory Prediction
• Heterogeneous Graph Representation of Stiffened Panels with Non-Uniform Boundary Conditions and Loads
• A Hierarchical Quantized Tokenization Framework for Task-Adaptive Graph Representation Learning
• Leveraging Teleconnections with Physics-Informed Graph Attention Networks for Long-Range Extreme Rainfall Forecasting in Thailand
• Unveiling the Vulnerability of Graph-LLMs: An Interpretable Multi-Dimensional Adversarial Attack on TAGs
• SDGraph: Multi-Level Sketch Representation Learning by Sparse-Dense Graph Architecture
• Graph Few-Shot Learning via Adaptive Spectrum Experts and Cross-Set Distribution Calibration
• Can Representation Gaps Be the Key to Enhancing Robustness in Graph-Text Alignment?
• MIARec: Mutual-influence-aware Heterogeneous Network Embedding for Scientific Paper Recommendation
• Enhanced Pre-training of Graph Neural Networks for Million-Scale Heterogeneous Graphs
• Integrating Sequential and Relational Modeling for User Events: Datasets and Prediction Tasks
• Qiboml: towards the orchestration of quantum-classical machine learning
• An Encoder-Integrated PhoBERT with Graph Attention for Vietnamese Token-Level Classification
• Dynamic Network-Based Two-Stage Time Series Forecasting for Affiliate Marketing
• Multi-View Graph Feature Propagation for Privacy Preservation and Feature Sparsity
• Event-Aware Prompt Learning for Dynamic Graphs
• FUSE: Fast Semi-Supervised Node Embedding Learning via Structural and Label-Aware Optimization
• Graph Neural Network-Based Multicast Routing for On-Demand Streaming Services in 6G Networks
• Causal Disentanglement Learning for Accurate Anomaly Detection in Multivariate Time Series
• PruneGCRN: Minimizing and explaining spatio-temporal problems through node pruning
• HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations
• LLMAtKGE: Large Language Models as Explainable Attackers against Knowledge Graph Embeddings
• Glance for Context: Learning When to Leverage LLMs for Node-Aware GNN-LLM Fusion
• Structured Spectral Graph Representation Learning for Multi-label Abnormality Analysis from 3D CT Scans
• Structure Over Signal: A Globalized Approach to Multi-relational GNNs for Stock Prediction
• A Graph-Attentive LSTM Model for Malicious URL Detection
• Stock Prediction via a Dual Relation Fusion Network incorporating Static and Dynamic Relations
• Trustworthy Retrosynthesis: Eliminating Hallucinations with a Diverse Ensemble of Reaction Scorers
• GraphTARIF: Linear Graph Transformer with Augmented Rank and Improved Focus
• On the Problem of Consistent Anomalies in Zero-Shot Industrial Anomaly Detection
• Controllable Graph Generation with Diffusion Models via Inference-Time Tree Search Guidance
• GrifFinNet: A Graph-Relation Integrated Transformer for Financial Predictions
• RainSeer: Fine-Grained Rainfall Reconstruction via Physics-Guided Modeling
• Bridging Semantics & Structure for Software Vulnerability Detection using Hybrid Network Models
• B2N3D: Progressive Learning from Binary to N-ary Relationships for 3D Object Grounding
• Preference-driven Knowledge Distillation for Few-shot Node Classification
• Structured Cooperative Multi-Agent Reinforcement Learning: a Bayesian Network Perspective
• Interpretable Graph-Language Modeling for Detecting Youth Illicit Drug Use
• Are LLMs Better GNN Helpers? Rethinking Robust Graph Learning under Deficiencies with Iterative Refinement
• Detecting LLM-Generated Spam Reviews by Integrating Language Model Embeddings and Graph Neural Network
• NG-Router: Graph-Supervised Multi-Agent Collaboration for Nutrition Question Answering
• HeSRN: Representation Learning On Heterogeneous Graphs via Slot-Aware Retentive Network
• InterCorpRel-LLM: Enhancing Financial Relational Understanding with Graph-Language Models
• Deep Learning to Identify the Spatio-Temporal Cascading Effects of Train Delays in a High-Density Network
• Beyond Pairwise Connections: Extracting High-Order Functional Brain Network Structures under Global Constraints
• Physics-Informed High-order Graph Dynamics Identification Learning for Predicting Complex Networks Long-term Dynamics
• SHERLOCK: Towards Dynamic Knowledge Adaptation in LLM-enhanced E-commerce Risk Management
• A Multimodal Approach to SME Credit Scoring Integrating Transaction and Ownership Networks
• When LLM Agents Meet Graph Optimization: An Automated Data Quality Improvement Approach
• Spatio-Temporal Graph Convolutional Networks for EV Charging Demand Forecasting Using Real-World Multi-Modal Data Integration
• Spatial Deconfounder: Interference-Aware Deconfounding for Spatial Causal Inference
• gLSTM: Mitigating Over-Squashing by Increasing Storage Capacity
• Do We Really Need SFT? Prompt-as-Policy over Knowledge Graphs for Cold-start Next POI Recommendation
• Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models
• From Noisy to Native: LLM-driven Graph Restoration for Test-Time Graph Domain Adaptation
• FedBook: A Unified Federated Graph Foundation Codebook with Intra-domain and Inter-domain Knowledge Modeling
• Alignment, Mining and Fusion: Representation Alignment with Hard Negative Mining and Selective Knowledge Fusion for Medical Visual Question Answering
• Struc-EMB: The Potential of Structure-Aware Encoding in Language Embeddings
• Decoding Positive Selection in Mycobacterium tuberculosis with Phylogeny-Guided Graph Attention Models
• MolGA: Molecular Graph Adaptation with Pre-trained 2D Graph Encoder
• GTCN-G: A Residual Graph-Temporal Fusion Network for Imbalanced Intrusion Detection
• Introspection in Learned Semantic Scene Graph Localisation
• TGM: a Modular and Efficient Library for Machine Learning on Temporal Graphs
• MoRE-GNN: Multi-omics Data Integration with a Heterogeneous Graph Autoencoder
• Heterogeneous Point Set Transformers for Segmentation of Multiple View Particle Detectors
• Multimodal Trajectory Representation Learning for Travel Time Estimation
• Soft-Evidence Fused Graph Neural Network for Cancer Driver Gene Identification across Multi-View Biological Graphs
• When Does Global Attention Help? A Unified Empirical Study on Atomistic Graph Learning
• QGraphLIME - Explaining Quantum Graph Neural Networks
• AgentRouter: A Knowledge-Graph-Guided LLM Router for Collaborative Multi-Agent Question Answering
• TopInG: Topologically Interpretable Graph Learning via Persistent Rationale Filtration
• Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI
• ONNX-Net: Towards Universal Representations and Instant Performance Prediction for Neural Architectures
• GILT: An LLM-Free, Tuning-Free Graph Foundational Model for In-Context Learning
• Toward a Unified Geometry Understanding: Riemannian Diffusion Framework for Graph Generation and Prediction
• Fractional Heat Kernel for Semi-Supervised Graph Learning with Small Training Sample Size
• Glocal Information Bottleneck for Time Series Imputation
• Score-based generative emulation of impact-relevant Earth system model outputs
• Diffusion-Assisted Distillation for Self-Supervised Graph Representation Learning with MLPs
• ICEPool: Enhancing Graph Pooling Networks with Inter-cluster Connectivity
• Toward Uncertainty-Aware and Generalizable Neural Decoding for Quantum LDPC Codes
• VBM-NET: Visual Base Pose Learning for Mobile Manipulation using Equivariant TransporterNet and GNNs
• On the Convergence and Size Transferability of Continuous-depth Graph Neural Networks
• Triplet-Structured Knowledge Integration for Multi-Turn Medical Reasoning
• BrainIB++: Leveraging Graph Neural Networks and Information Bottleneck for Functional Brain Biomarkers in Schizophrenia
• Hybrid-Collaborative Augmentation and Contrastive Sample Adaptive-Differential Awareness for Robust Attributed Graph Clustering
• VisitHGNN: Heterogeneous Graph Neural Networks for Modeling Point-of-Interest Visit Patterns
• RTFF: Random-to-Target Fabric Flattening Policy using Dual-Arm Manipulator
• LEAP: Local ECT-Based Learnable Positional Encodings for Graphs
• Graph2Region: Efficient Graph Similarity Learning with Structure and Scale Restoration
• GDLNN: Marriage of Programming Language and Neural Networks for Accurate and Easy-to-Explain Graph Classification
• Graph Integrated Multimodal Concept Bottleneck Model
• VDW-GNNs: Vector diffusion wavelets for geometric graph neural networks
• Atlas-free Brain Network Transformer
• Attention over Scene Graphs: Indoor Scene Representations Toward CSAI Classification
• MC-GNNAS-Dock: Multi-criteria GNN-based Algorithm Selection for Molecular Docking
• Items Proxy Bridging: Enabling Frictionless Critiquing in Knowledge Graph Recommendations
• GeoLink: Empowering Remote Sensing Foundation Model with OpenStreetMap Data
• MAPLE: Multi-scale Attribute-enhanced Prompt Learning for Few-shot Whole Slide Image Classification
• Cooperative Autonomous Driving in Diverse Behavioral Traffic: A Heterogeneous Graph Reinforcement Learning Approach
• Biologically inspired neural network layer with homeostatic regulation and adaptive repair mechanisms
• Identifying obfuscated code through graph-based semantic analysis of binary code
• AttentionViG: Cross-Attention-Based Dynamic Neighbor Aggregation in Vision GNNs
• AlphaSAGE: Structure-Aware Alpha Mining via GFlowNets for Robust Exploration
• Spatial-Functional awareness Transformer-based graph archetype contrastive learning for Decoding Visual Neural Representations from EEG
• Community detection robustness of graph neural networks
• Prompting Robot Teams with Natural Language
• Graph Optimization Foundation Model: Tokenizing Graph via A Language-Model Paradigm
• From Headlines to Holdings: Deep Learning for Smarter Portfolio Decisions
• SynthPert: Enhancing LLM Biological Reasoning via Synthetic Reasoning Traces for Cellular Perturbation Prediction
• VN-EGNN: E(3)- and SE(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification
• Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks
• Unifying Agent Interaction and World Information for Multi-agent Coordination
• Controllable Generation of Large-Scale 3D Urban Layouts with Semantic and Structural Guidance
• NeuSO: Neural Optimizer for Subgraph Queries
• Knowledge Homophily in Large Language Models
• A Modality-Tailored Graph Modeling Framework for Urban Region Representation via Contrastive Learning
• StrucADT: Generating Structure-controlled 3D Point Clouds with Adjacency Diffusion Transformer
• Graph Neural Networks with Diversity-aware Neighbor Selection and Dynamic Multi-scale Fusion for Multivariate Time Series Forecasting
• Multi-Scale Spatial-Temporal Hypergraph Network with Lead-Lag Structures for Stock Time Series Forecasting
• Pure Node Selection for Imbalanced Graph Node Classification
• GraphIFE: Rethinking Graph Imbalance Node Classification via Invariant Learning
• Node Classification via Simplicial Interaction with Augmented Maximal Clique Selection
• QuadEnhancer: Leveraging Quadratic Transformations to Enhance Deep Neural Networks
• Mind the Links: Cross-Layer Attention for Link Prediction in Multiplex Networks
• Graph Your Own Prompt
• CrediBench: Building Web-Scale Network Datasets for Information Integrity
• Neighborhood Sampling Does Not Learn the Same Graph Neural Network
• Patient-specific Biomolecular Instruction Tuning
• Physics-informed GNN for medium-high voltage AC power flow with edge-aware attention and line search correction operator
• One Prompt Fits All: Universal Graph Adaptation for Pretrained Models
• Wavelet-Induced Rotary Encodings: RoPE Meets Graphs
• SHAKE-GNN: Scalable Hierarchical Kirchhoff-Forest Graph Neural Network
• Brain PathoGraph Learning
• Triple-BERT: Do We Really Need MARL for Order Dispatch on Ride-Sharing Platforms?
• GraphPFN: A Prior-Data Fitted Graph Foundation Model
• Rebuild AC Power Flow Models with Graph Attention Networks
• A Causality-Aware Spatiotemporal Model for Multi-Region and Multi-Pollutant Air Quality Forecasting
• SlideMamba: Entropy-Based Adaptive Fusion of GNN and Mamba for Enhanced Representation Learning in Digital Pathology
• EvoMail: Self-Evolving Cognitive Agents for Adaptive Spam and Phishing Email Defense
• FracAug: Fractional Augmentation boost Graph-level Anomaly Detection under Limited Supervision
• GALAX: Graph-Augmented Language Model for Explainable Reinforcement-Guided Subgraph Reasoning in Precision Medicine
• Mesh Interpolation Graph Network for Dynamic and Spatially Irregular Global Weather Forecasting
• GraphUniverse: Synthetic Graph Generation for Evaluating Inductive Generalization
• Exact Subgraph Isomorphism Network with Mixed L_0,2 Norm Constraint for Predictive Graph Mining
• Enhancing Molecular Property Prediction with Knowledge from Large Language Models
• Feature Augmentation of GNNs for ILPs: Local Uniqueness Suffices
• Personalized Federated Dictionary Learning for Modeling Heterogeneity in Multi-site fMRI Data
• Spatio-Temporal Directed Graph Learning for Account Takeover Fraud Detection
• Graph Variate Neural Networks
• SSTAG: Structure-Aware Self-Supervised Learning Method for Text-Attributed Graphs
• MIXRAG : Mixture-of-Experts Retrieval-Augmented Generation for Textual Graph Understanding and Question Answering
• Train Small, Deploy Large: Zero-Shot GNN Transfer Through Geometric Renormalization
• Persistent Gaussian Perturbations Prevent Oversmoothing in Recurrent Graph Neural Networks
• Same Graph Cross-Task Transfer in GNNs: Protocols and Predictors
• Graph Neural Multilevel Preconditioners for Iterative Solvers
• Schreier-Coset Graph Rewiring
• TuningIQA: Fine-Grained Blind Image Quality Assessment for Livestreaming Camera Tuning
• GRIPHIN: grids of pharmacophore interaction fields for affinity prediction
• SR2P: an efficient stacking method to predict protein abundance from gene expression in spatial transcriptomics data
• HLG: Comprehensive 3D Room Construction via Hierarchical Layout Generation
• SGAligner++: Cross-Modal Language-Aided 3D Scene Graph Alignment
• Graph-Radiomic Learning (GrRAiL) Descriptor to Characterize Imaging Heterogeneity in Confounding Tumor Pathologies
• Bridging Computational Social Science and Deep Learning: Cultural Dissemination-Inspired Graph Neural Networks
• Enhancing LLM-Based Social Bot via an Adversarial Learning Framework
• Estimating Heterogeneous Causal Effect on Networks via Orthogonal Learning
• Heterogeneous co-occurrence embedding for visual information exploration
• Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inference
• Periodic Graph-Enhanced Multivariate Time Series Anomaly Detector
• Policy Gradient with Self-Attention for Model-Free Distributed Nonlinear Multi-Agent Games
• A Graph-Neural-Network-Entropy model of vital node identification on network attack and propagation
• MSGAT-GRU: A Multi-Scale Graph Attention and Recurrent Model for Spatiotemporal Road Accident Prediction
• Quantum Graph Attention Network: A Novel Quantum Multi-Head Attention Mechanism for Graph Learning
• Word2VecGD: Neural Graph Drawing with Cosine-Stress Optimization
• Graph Enhanced Trajectory Anomaly Detection
• Unlocking Hidden Potential in Point Cloud Networks with Attention-Guided Grouping-Feature Coordination
• TF-DWGNet: A Directed Weighted Graph Neural Network with Tensor Fusion for Multi-Omics Cancer Subtype Classification
• Automated Cyber Defense with Generalizable Graph-based Reinforcement Learning Agents
• Bridging Graph and State-Space Modeling for Intensive Care Unit Length of Stay Prediction
• Subteaming and Adaptive Formation Control for Coordinated Multi-Robot Navigation
• Compose by Focus: Scene Graph-based Atomic Skills
• Gumbel-MPNN: Graph Rewiring with Gumbel-Softmax
• Multimodal Representation Learning Conditioned on Semantic Relations
• Attention Beyond Neighborhoods: Reviving Transformer for Graph Clustering
• No Modality Left Behind: Adapting to Missing Modalities via Knowledge Distillation for Brain Tumor Segmentation
• Exploring the Global-to-Local Attention Scheme in Graph Transformers: An Empirical Study
• A Multi-Scale Graph Neural Process with Cross-Drug Co-Attention for Drug-Drug Interactions Prediction
• Extracting Interpretable Higher-Order Topological Features across Multiple Scales for Alzheimer's Disease Classification
• Synthesizing Attitudes, Predicting Actions (SAPA): Behavioral Theory-Guided LLMs for Ridesourcing Mode Choice Modeling
• Towards Pre-trained Graph Condensation via Optimal Transport
• Hierarchical Learning for Maze Navigation: Emergence of Mental Representations via Second-Order Learning
• State Space Models over Directed Graphs
• Understanding and Tackling Over-Dilution in Graph Neural Networks
• Local-Canonicalization Equivariant Graph Neural Networks for Sample-Efficient and Generalizable Swarm Robot Control
• Property-Isometric Variational Autoencoders for Sequence Modeling and Design
• GRATE: a Graph transformer-based deep Reinforcement learning Approach for Time-efficient autonomous robot Exploration
• A Graph Machine Learning Approach for Detecting Topological Patterns in Transactional Graphs
• Multimodal Hate Detection Using Dual-Stream Graph Neural Networks
• Enhancing Video Large Language Models with Structured Multi-Video Collaborative Reasoning
• Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs
• Learning from Heterophilic Graphs: A Spectral Theory Perspective on the Impact of Self-Loops and Parallel Edges
• Dynamic Relational Priming Improves Transformer in Multivariate Time Series
• Draw a Portrait of Your Graph Data: An Instance-Level Profiling Framework for Graph-Structured Data
• Asterisk Operator
• Two Birds with One Stone: Enhancing Uncertainty Quantification and Interpretability with Graph Functional Neural Process
• Visualization and Analysis of the Loss Landscape in Graph Neural Networks
• Anomaly Detection in Industrial Control Systems Based on Cross-Domain Representation Learning
• SpaPool: Soft Partition Assignment Pooling for__Graph Neural Networks
• Dynamic Span Interaction and Graph-Aware Memory for Entity-Level Sentiment Classification
• AdaSTI: Conditional Diffusion Models with Adaptive Dependency Modeling for Spatio-Temporal Imputation
• 3DViT-GAT: A Unified Atlas-Based 3D Vision Transformer and Graph Learning Framework for Major Depressive Disorder Detection Using Structural MRI Data
• Quantum Graph Attention Networks: Trainable Quantum Encoders for Inductive Graph Learning
• Enhancing Electromagnetic Calorimeter Signal Reconstruction with Machine Learning-Based Noise Discrimination
• GCN-TULHOR: Trajectory-User Linking Leveraging GCNs and Higher-Order Spatial Representations
• Weakly Supervised Vulnerability Localization via Multiple Instance Learning
• Optimal message passing for molecular prediction is simple, attentive and spatial
• Outlier-Resistant Heterogeneous Treatment Effect Estimation in HDLSS Settings via GAT--CVAE Framework
• Why does your graph neural network fail on some graphs? Insights from exact generalisation error
• Explainable Fraud Detection with GNNExplainer and Shapley Values
• MoSE: Unveiling Structural Patterns in Graphs via Mixture of Subgraph Experts
• Constructing a Question-Answering Simulator through the Distillation of LLMs
• JFRFFNet: A Data-Model Co-Driven Graph Signal Denoising Model with Partial Prior Information
• Universal Graph Learning for Power System Reconfigurations: Transfer Across Topology Variations
• Improving Greenland Bed Topography Mapping with Uncertainty-Aware Graph Learning on Sparse Radar Data
• BALI: Enhancing Biomedical Language Representations through Knowledge Graph and Language Model Alignment
• DR-CircuitGNN: Training Acceleration of Heterogeneous Circuit Graph Neural Network on GPUs
• Attention Maps in 3D Shape Classification for Dental Stage Estimation with Class Node Graph Attention Networks
• NestGNN: A Graph Neural Network Framework Generalizing the Nested Logit Model for Travel Mode Choice
• Bringing Graphs to the Table: Zero-shot Node Classification via Tabular Foundation Models
• AI-based response assessment and prediction in longitudinal imaging for brain metastases treated with stereotactic radiosurgery
• Beyond the Pre-Service Horizon: Infusing In-Service Behavior for Improved Financial Risk Forecasting
• PAC-Bayesian Generalization Bounds for Graph Convolutional Networks on Inductive Node Classification
• Using Reinforcement Learning to Optimize the Global and Local Crossing Number
• A Spatiotemporal Adaptive Local Search Method for Tracking Congestion Propagation in Dynamic Networks
• Asynchronous Message Passing for Addressing Oversquashing in Graph Neural Networks
• Data-Efficient Time-Dependent PDE Surrogates: Graph Neural Simulators vs. Neural Operators
• DRDCAE-STGNN: An End-to-End Discrimina-tive Autoencoder with Spatio-Temporal Graph Learning for Motor Imagery Classification
• From Eigenmodes to Proofs: Integrating Graph Spectral Operators with Symbolic Interpretable Reasoning
• Exploring Urban Factors with Autoencoders: Relationship Between Static and Dynamic Features
• SEASONED: Semantic-Enhanced Self-Counterfactual Explainable Detection of Adversarial Exploiter Contracts
• MSRFormer: Road Network Representation Learning using Multi-scale Feature Fusion of Heterogeneous Spatial Interactions
• RoboBallet: Planning for Multi-Robot Reaching with Graph Neural Networks and Reinforcement Learning
• Safeguarding Graph Neural Networks against Topology Inference Attacks
• Inferring the Graph Structure of Images for Graph Neural Networks
• An Interpretable Ensemble Framework for Multi-Omics Dementia Biomarker Discovery Under HDLSS Conditions
• Explicit and Implicit Data Augmentation for Social Event Detection
• TEn-CATG:Text-Enriched Audio-Visual Video Parsing with Multi-Scale Category-Aware Temporal Graph
• KGBERT4Eth: A Feature-Complete Transformer Powered by Knowledge Graph for Multi-Task Ethereum Fraud Detection
• Structured Information Matters: Explainable ICD Coding with Patient-Level Knowledge Graphs
• Resource-Aware Neural Network Pruning Using Graph-based Reinforcement Learning
• LayoutGKN: Graph Similarity Learning of Floor Plans
• NeuroKoop: Neural Koopman Fusion of Structural-Functional Connectomes for Identifying Prenatal Drug Exposure in Adolescents
• Decentralised self-organisation of pivoting cube ensembles using geometric deep learning
• Exploring a Graph-based Approach to Offline Reinforcement Learning for Sepsis Treatment
• HydroGAT: Distributed Heterogeneous Graph Attention Transformer for Spatiotemporal Flood Prediction
• HiGraph: A Large-Scale Hierarchical Graph Dataset for Malware Analysis
• StructCoh: Structured Contrastive Learning for Context-Aware Text Semantic Matching
• Causal Representation Learning from Network Data
• DSGC-Net: A Dual-Stream Graph Convolutional Network for Crowd Counting via Feature Correlation Mining
• STA-GANN: A Valid and Generalizable Spatio-Temporal Kriging Approach
• ST-Hyper: Learning High-Order Dependencies Across Multiple Spatial-Temporal Scales for Multivariate Time Series Forecasting
• TransGAT: Transformer-Based Graph Neural Networks for Multi-Dimensional Automated Essay Scoring
• Superposition in Graph Neural Networks
• HePGA: A Heterogeneous Processing-in-Memory based GNN Training Accelerator
• Unifying Adversarial Perturbation for Graph Neural Networks
• Efficient Graph Knowledge Distillation from GNNs to Kolmogorov--Arnold Networks via Self-Attention Dynamic Sampling
• Multi-Ontology Integration with Dual-Axis Propagation for Medical Concept Representation
• Structure-Preserving Medical Image Generation from a Latent Graph Representation
• GSTBench: A Benchmark Study on the Transferability of Graph Self-Supervised Learning
• Graph-Based Feature Augmentation for Predictive Tasks on Relational Datasets
• ATM-GAD: Adaptive Temporal Motif Graph Anomaly Detection for Financial Transaction Networks
• Deep Learning Based Concurrency Bug Detection and Localization
• Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks
• A Graph Talks, But Who's Listening? Rethinking Evaluations for Graph-Language Models
• BridgeShield: Enhancing Security for Cross-chain Bridge Applications via Heterogeneous Graph Mining
• Multi-View Graph Convolution Network for Internal Talent Recommendation Based on Enterprise Emails
• Turning Tabular Foundation Models into Graph Foundation Models
• Bounds on Perfect Node Classification: A Convex Graph Clustering Perspective
• GRASPED: Graph Anomaly Detection using Autoencoder with Spectral Encoder and Decoder (Full Version)
• Parameter-Free Structural-Diversity Message Passing for Graph Neural Networks
• Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses
• ALSA: Anchors in Logit Space for Out-of-Distribution Accuracy Estimation
• Memorization in Graph Neural Networks
• Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks
• MOCHA: Discovering Multi-Order Dynamic Causality in Temporal Point Processes
• Enhancing Chemical Explainability Through Counterfactual Masking
• EvoFormer: Learning Dynamic Graph-Level Representations with Structural and Temporal Bias Correction
• Training Transformers for Mesh-Based Simulations
• CITE: A Comprehensive Benchmark for Heterogeneous Text-Attributed Graphs on Catalytic Materials
• Fragment-Wise Interpretability in Graph Neural Networks via Molecule Decomposition and Contribution Analysis
• Fast Graph Neural Network for Image Classification
• Graph Structure Learning with Temporal Graph Information Bottleneck for Inductive Representation Learning
• TransLLM: A Unified Multi-Task Foundation Framework for Urban Transportation via Learnable Prompting
• Statistical Arbitrage in Options Markets by Graph Learning and Synthetic Long Positions
• MissionHD: Hyperdimensional Refinement of Distribution-Deficient Reasoning Graphs for Video Anomaly Detection
• On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks
• Addressing Graph Anomaly Detection via Causal Edge Separation and Spectrum
• Accelerating Image Classification with Graph Convolutional Neural Networks using Voronoi Diagrams
• CaPGNN: Optimizing Parallel Graph Neural Network Training with Joint Caching and Resource-Aware Graph Partitioning
• Electromagnetic Signal Modulation Recognition based on Subgraph Embedding Learning
• SVDformer: Direction-Aware Spectral Graph Embedding Learning via SVD and Transformer
• DegDiT: Controllable Audio Generation with Dynamic Event Graph Guided Diffusion Transformer
• A Dual-Attention Graph Network for fMRI Data Classification
• Scaling Multi-Agent Epistemic Planning through GNN-Derived Heuristics
• Consiglieres in the Shadow: Understanding the Use of Uncensored Large Language Models in Cybercrimes
• IPGPhormer: Interpretable Pathology Graph-Transformer for Survival Analysis
• CRoC: Context Refactoring Contrast for Graph Anomaly Detection with Limited Supervision
• Contrastive Multi-View Graph Hashing
• DHG-Bench: A Comprehensive Benchmark for Deep Hypergraph Learning
• Modeling Relational Logic Circuits for And-Inverter Graph Convolutional Network
• Towards Faithful Class-level Self-explainability in Graph Neural Networks by Subgraph Dependencies
• Hierarchical Graph Feature Enhancement with Adaptive Frequency Modulation for Visual Recognition
• Enhancing Interactive Voting-Based Map Matching: Improving Efficiency and Robustness for Heterogeneous GPS Trajectories
• Graph Neural Diffusion via Generalized Opinion Dynamics
• Aligning the Spectrum: Hybrid Graph Pre-training and Prompt Tuning across Homophily and Heterophily
• Hybrid-Hierarchical Fashion Graph Attention Network for Compatibility-Oriented and Personalized Outfit Recommendation
• FreeGAD: A Training-Free yet Effective Approach for Graph Anomaly Detection
• GCRPNet: Graph-Enhanced Contextual and Regional Perception Network for Salient Object Detection in Optical Remote Sensing Images
• Reasoning in Computer Vision: Taxonomy, Models, Tasks, and Methodologies
• X-Node: Self-Explanation is All We Need
• Hierarchical Graph Attention Network for No-Reference Omnidirectional Image Quality Assessment
• Explainable Attention-Guided Stacked Graph Neural Networks for Malware Detection
• Time-Aware and Transition-Semantic Graph Neural Networks for Interpretable Predictive Business Process Monitoring
• Implicit Hypergraph Neural Networks: A Stable Framework for Higher-Order Relational Learning with Provable Guarantees
• RicciFlowRec: A Geometric Root Cause Recommender Using Ricci Curvature on Financial Graphs
• Solving Approximation Tasks with Greedy Deep Kernel Methods
• Hybrid Node-Destroyer Model with Large Neighborhood Search for Solving the Capacitated Vehicle Routing Problem
• Edge-Selector Model Applied for Local Search Neighborhood for Solving Vehicle Routing Problems
• Agentic Graph Neural Networks for Wireless Communications and Networking Towards Edge General Intelligence: A Survey
• Urban-STA4CLC: Urban Theory-Informed Spatio-Temporal Attention Model for Predicting Post-Disaster Commercial Land Use Change
• GRAVITY: A Controversial Graph Representation Learning for Vertex Classification
• Chi-Geometry: A Library for Benchmarking Chirality Prediction of GNNs
• Differentiated Information Mining: A Semi-supervised Learning Framework for GNNs
• C-MAG: Cascade Multimodal Attributed Graphs for Supply Chain Link Prediction
• Learning to Select MCP Algorithms: From Traditional ML to Dual-Channel GAT-MLP
• Exploring Content and Social Connections of Fake News with Explainable Text and Graph Learning
• LoSemB: Logic-Guided Semantic Bridging for Inductive Tool Retrieval
• ImageDDI: Image-enhanced Molecular Motif Sequence Representation for Drug-Drug Interaction Prediction
• Topological Feature Compression for Molecular Graph Neural Networks
• MOTGNN: Interpretable Graph Neural Networks for Multi-Omics Disease Classification
• HSA-Net: Hierarchical and Structure-Aware Framework for Efficient and Scalable Molecular Language Modeling
• Enhancing Rumor Detection Methods with Propagation Structure Infused Language Model
• From Nodes to Narratives: Explaining Graph Neural Networks with LLMs and Graph Context
• BrainATCL: Adaptive Temporal Brain Connectivity Learning for Functional Link Prediction and Age Estimation
• ScamDetect: Towards a Robust, Agnostic Framework to Uncover Threats in Smart Contracts
• Energy Efficient Task Offloading in UAV-Enabled MEC Using a Fully Decentralized Deep Reinforcement Learning Approach
• Geometry-Aware Spiking Graph Neural Network
• A Stage-Aware Mixture of Experts Framework for Neurodegenerative Disease Progression Modelling
• Transferring Social Network Knowledge from Multiple GNN Teachers to Kolmogorov-Arnold Networks
• From buildings to blocks: Graph contrastive learning for integrated urban architectural morphology classification
• Graph is a Natural Regularization: Revisiting Vector Quantization for Graph Representation Learning
• Adaptive Heterogeneous Graph Neural Networks: Bridging Heterophily and Heterogeneity
• Hypergraph Neural Network with State Space Models for Node Classification
• DART: Dual Adaptive Refinement Transfer for Open-Vocabulary Multi-Label Recognition
• A Graph-Based Framework for Exploring Mathematical Patterns in Physics: A Proof of Concept
• When Deepfake Detection Meets Graph Neural Network:a Unified and Lightweight Learning Framework
• CT-GRAPH: Hierarchical Graph Attention Network for Anatomy-Guided CT Report Generation
• Graph-based Event Log Repair
• TANGO: Graph Neural Dynamics via Learned Energy and Tangential Flows
• An Effective Approach for Node Classification in Textual Graphs
• SPA++: Generalized Graph Spectral Alignment for Versatile Domain Adaptation
• Functional Connectivity Graph Neural Networks
• Adversarial Attacks and Defenses on Graph-aware Large Language Models (LLMs)
• PriceFM: Foundation Model for Probabilistic Electricity Price Forecasting
• Multi-Stage Knowledge-Distilled VGAE and GAT for Robust Controller-Area-Network Intrusion Detection
• A Scalable Pretraining Framework for Link Prediction with Efficient Adaptation
• BadTime: An Effective Backdoor Attack on Multivariate Long-Term Time Series Forecasting
• The Ubiquitous Sparse Matrix-Matrix Products
• NAEx: A Plug-and-Play Framework for Explaining Network Alignment
• R2GenKG: Hierarchical Multi-modal Knowledge Graph for LLM-based Radiology Report Generation
• Online Continual Graph Learning
• Full-History Graphs with Edge-Type Decoupled Networks for Temporal Reasoning
• Momentum-integrated Multi-task Stock Recommendation with Converge-based Optimization
• Adaptive Riemannian Graph Neural Networks
• Causality and Interpretability for Electrical Distribution System faults
• Contextual Graph Transformer: A Small Language Model for Enhanced Engineering Document Information Extraction
• mCardiacDx: Radar-Driven Contactless Monitoring and Diagnosis of Arrhythmia
• Federated Graph Unlearning
• Forecasting West Nile virus with deep graph encoders
• Learning Unified System Representations for Microservice Tail Latency Prediction
• MHARFedLLM: Multimodal Human Activity Recognition Using Federated Large Language Model
• R²-CoD: Understanding Text-Graph Complementarity in Relational Reasoning via Knowledge Co-Distillation
• Explaining GNN Explanations with Edge Gradients
• Nested Graph Pseudo-Label Refinement for Noisy Label Domain Adaptation Learning
• GeoMoE: Divide-and-Conquer Motion Field Modeling with Mixture-of-Experts for Two-View Geometry
• Similarity-Based Self-Construct Graph Model for Predicting Patient Criticalness Using Graph Neural Networks and EHR Data
• Learning Network Dismantling Without Handcrafted Inputs
• Sheaf Graph Neural Networks via PAC-Bayes Spectral Optimization
• Invariant Graph Transformer for Out-of-Distribution Generalization
• FMIP: Joint Continuous-Integer Flow For Mixed-Integer Linear Programming
• Causal-Inspired Multi-Agent Decision-Making via Graph Reinforcement Learning
• MPFSR-Enhanced GNNs: Spectral Graph Neural Networks Enhancement Through Learnable Multiple-Parameter Graph Fractional Fourier Transforms
• On the Expressiveness of Softmax Attention: A Recurrent Neural Network Perspective
• INSPIRE-GNN: Intelligent Sensor Placement to Improve Sparse Bicycling Network Prediction via Reinforcement Learning Boosted Graph Neural Networks
• HGCN(O): A Self-Tuning GCN HyperModel Toolkit for Outcome Prediction in Event-Sequence Data
• Benchmarking Fraud Detectors on Private Graph Data
• Alpha-Z divergence unveils further distinct phenotypic traits of human brain connectivity fingerprint
• Multi-modal Relational Item Representation Learning for Inferring Substitutable and Complementary Items
• GDAIP: A Graph-Based Domain Adaptive Framework for Individual Brain Parcellation
• Hierarchical Graph Neural Network for Compressed Speech Steganalysis
• DGP: A Dual-Granularity Prompting Framework for Fraud Detection with Graph-Enhanced LLMs
• Trainable Joint Time-Vertex Fractional Fourier Transform
• GraphTorque: Torque-Driven Rewiring Graph Neural Network
• Graph neural networks for residential location choice: connection to classical logit models
• Transformers as Unrolled Inference in Probabilistic Laplacian Eigenmaps: An Interpretation and Potential Improvements

Discussions

• There's also a name for GNNs that do use attention: arxiv.org/abs/1710.10903 [bsky, 10 points, 1 comments]
• Interesting arxiv.org/abs/1710.10903 [bsky, 0 points, 0 comments]

Related

• Focus Where It Matters: Graph Selective State Focused Attention Networks
• A Bird's-Eye Tutorial of Graph Attention Architectures
• A Regularized Attention Mechanism for Graph Attention Networks
• Understanding Attention and Generalization in Graph Neural Networks
• Learnable Graph Convolutional Attention Networks