Graph Neural Networks: A Review of Methods and Applications

Abstract

Lots of learning tasks require dealing with graph data which contains rich relation information among elements. Modeling physics systems, learning molecular fingerprints, predicting protein interface, and classifying diseases demand a model to learn from graph inputs. In other domains such as learning from non-structural data like texts and images, reasoning on extracted structures (like the dependency trees of sentences and the scene graphs of images) is an important research topic which also needs graph reasoning models. Graph neural networks (GNNs) are neural models that capture the dependence of graphs via message passing between the nodes of graphs. In recent years, variants of GNNs such as graph convolutional network (GCN), graph attention network (GAT), graph recurrent network (GRN) have demonstrated ground-breaking performances on many deep learning tasks. In this survey, we propose a general design pipeline for GNN models and discuss the variants of each component, systematically categorize the applications, and propose four open problems for future research.

arXiv commentPublished at AI Open 2021

References in corpus (73)

• Efficient Estimation of Word Representations in Vector Space
• The Emerging Field of Signal Processing on Graphs: Extending High-Dimensional Data Analysis to Networks and Other Irregular Domains
• Inductive Representation Learning on Large Graphs
• Neural Message Passing for Quantum Chemistry
• Geometric deep learning: going beyond Euclidean data
• Graph Embedding Techniques, Applications, and Performance: A Survey
• Molecular Graph Convolutions: Moving Beyond Fingerprints
• Quantum-Chemical Insights from Deep Tensor Neural Networks
• Modeling polypharmacy side effects with graph convolutional networks
• Deep Convolutional Networks on Graph-Structured Data
• Cluster-GCN: An Efficient Algorithm for Training Deep and Large Graph Convolutional Networks
• Fast Graph Representation Learning with PyTorch Geometric
• Simplifying Graph Convolutional Networks
• Graph Convolutional Matrix Completion
• Learning Combinatorial Optimization Algorithms over Graphs
• Adversarial Attacks on Neural Networks for Graph Data
• Representation Learning on Graphs with Jumping Knowledge Networks
• Variational Graph Auto-Encoders
• Pitfalls of Graph Neural Network Evaluation
• Interaction Networks for Learning about Objects, Relations and Physics
• Predicting multicellular function through multi-layer tissue networks
• Graph Transformer Networks
• Discriminative Embeddings of Latent Variable Models for Structured Data
• GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models
• MolGAN: An implicit generative model for small molecular graphs
• Dynamic Graph Convolutional Networks
• FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling
• Learning Deep Generative Models of Graphs
• Few-Shot Learning with Graph Neural Networks
• Jointly Multiple Events Extraction via Attention-based Graph Information Aggregation
• Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search
• Adversarial Attack and Defense on Graph Data: A Survey
• Neural Combinatorial Optimization with Reinforcement Learning
• GaAN: Gated Attention Networks for Learning on Large and Spatiotemporal Graphs
• Exact Combinatorial Optimization with Graph Convolutional Neural Networks
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
• Graph Matching Networks for Learning the Similarity of Graph Structured Objects
• Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN
• Adaptive Sampling Towards Fast Graph Representation Learning
• GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
• NetGAN: Generating Graphs via Random Walks
• Attention, Learn to Solve Routing Problems!
• Order Matters: Sequence to sequence for sets
• Strategies for Pre-training Graph Neural Networks
• A Compositional Object-Based Approach to Learning Physical Dynamics
• Learning Conditioned Graph Structures for Interpretable Visual Question Answering
• Universal Invariant and Equivariant Graph Neural Networks
• HATS: A Hierarchical Graph Attention Network for Stock Movement Prediction
• MR-GNN: Multi-Resolution and Dual Graph Neural Network for Predicting Structured Entity Interactions
• A Fair Comparison of Graph Neural Networks for Graph Classification
• GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding
• DeepGCNs: Can GCNs Go as Deep as CNNs?
• Traffic Graph Convolutional Recurrent Neural Network: A Deep Learning Framework for Network-Scale Traffic Learning and Forecasting
• Unifying Graph Convolutional Neural Networks and Label Propagation
• Invariant and Equivariant Graph Networks
• Layer-Dependent Importance Sampling for Training Deep and Large Graph Convolutional Networks
• Understanding the Representation Power of Graph Neural Networks in Learning Graph Topology
• Constrained Generation of Semantically Valid Graphs via Regularizing Variational Autoencoders
• Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approach
• Discovering objects and their relations from entangled scene representations
• Transferability of Spectral Graph Convolutional Neural Networks
• Relational inductive bias for physical construction in humans and machines
• Explainability Techniques for Graph Convolutional Networks
• Signed Graph Convolutional Network
• Dynamically Fused Graph Network for Multi-hop Reasoning
• Active Learning for Graph Embedding
• Graph Convolution over Pruned Dependency Trees Improves Relation Extraction
• A Graph-to-Sequence Model for AMR-to-Text Generation
• Exploring Graph Neural Networks for Stock Market Predictions with Rolling Window Analysis
• Bayesian Semi-supervised Learning with Graph Gaussian Processes
• Interpretable Structure-Evolving LSTM
• N-ary Relation Extraction using Graph State LSTM

Cited by in corpus (342)

• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges
• Convergence of Edge Computing and Deep Learning: A Comprehensive Survey
• Graph Neural Network for Traffic Forecasting: A Survey
• Simplifying Graph Convolutional Networks
• A Comprehensive Survey on Graph Anomaly Detection with Deep Learning
• GNNExplainer: Generating Explanations for Graph Neural Networks
• Spatial-Temporal Graph ODE Networks for Traffic Flow Forecasting
• E-GraphSAGE: A Graph Neural Network based Intrusion Detection System for IoT
• Self-Attention Graph Pooling
• Foundations and modelling of dynamic networks using Dynamic Graph Neural Networks: A survey
• TUDataset: A collection of benchmark datasets for learning with graphs
• How to Build a Graph-Based Deep Learning Architecture in Traffic Domain: A Survey
• An Overview of Deep Semi-Supervised Learning
• Learning to Dispatch for Job Shop Scheduling via Deep Reinforcement Learning
• Deep Learning for Generic Object Detection: A Survey
• Fi-GNN: Modeling Feature Interactions via Graph Neural Networks for CTR Prediction
• DGL-LifeSci: An Open-Source Toolkit for Deep Learning on Graphs in Life Science
• DeepGCNs: Making GCNs Go as Deep as CNNs
• Metrics for Graph Comparison: A Practitioner's Guide
• KST-GCN: A Knowledge-Driven Spatial-Temporal Graph Convolutional Network for Traffic Forecasting
• Deep Learning on Graphs: A Survey
• Graph Neural Networks: Taxonomy, Advances and Trends
• HDMI: High-order Deep Multiplex Infomax
• Examining COVID-19 Forecasting using Spatio-Temporal Graph Neural Networks
• Linked Dynamic Graph CNN: Learning on Point Cloud via Linking Hierarchical Features
• Universal Invariant and Equivariant Graph Neural Networks
• Graph Convolutional Networks for Graphs Containing Missing Features
• Hierarchical Graph Pooling with Structure Learning
• How to Find Your Friendly Neighborhood: Graph Attention Design with Self-Supervision
• RouteNet-Fermi: Network Modeling with Graph Neural Networks
• DeepAID: Interpreting and Improving Deep Learning-based Anomaly Detection in Security Applications
• Self-supervised Learning on Graphs: Deep Insights and New Direction
• Hardware Acceleration of Sparse and Irregular Tensor Computations of ML Models: A Survey and Insights
• DeepGCNs: Can GCNs Go as Deep as CNNs?
• Machine Learning on Graphs: A Model and Comprehensive Taxonomy
• Deep learning of thermodynamics-aware reduced-order models from data
• A Note on Over-Smoothing for Graph Neural Networks
• Graph Neural Networks for Particle Reconstruction in High Energy Physics detectors
• A Survey on The Expressive Power of Graph Neural Networks
• Towards Deeper Graph Neural Networks with Differentiable Group Normalization
• Kriging Convolutional Networks
• Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological View
• Deep Learning for Sequential Recommendation: Algorithms, Influential Factors, and Evaluations
• GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
• K-Core based Temporal Graph Convolutional Network for Dynamic Graphs
• Measuring and Improving the Use of Graph Information in Graph Neural Networks
• Residual Correlation in Graph Neural Network Regression
• Automated Machine Learning on Graphs: A Survey
• Representation Learning for Dynamic Graphs: A Survey
• Accurate Learning of Graph Representations with Graph Multiset Pooling
• Anomaly Detection in Dynamic Graphs: A Comprehensive Survey
• Trans4E: Link Prediction on Scholarly Knowledge Graphs
• Graph Kernels: State-of-the-Art and Future Challenges
• DIG: A Turnkey Library for Diving into Graph Deep Learning Research
• Implicit Graph Neural Networks
• Multilayer Network Analysis for Improved Credit Risk Prediction
• Uncertainty Aware Semi-Supervised Learning on Graph Data
• Towards Reusable Surrogate Models: Graph-Based Transfer Learning on Trusses
• Relational Deep Feature Learning for Heterogeneous Face Recognition
• Graph Structure Learning for Robust Graph Neural Networks
• DiffNet++: A Neural Influence and Interest Diffusion Network for Social Recommendation
• MagNet: A Neural Network for Directed Graphs
• Coordinated Sum-Rate Maximization in Multicell MU-MIMO with Deep Unrolling
• Automating Botnet Detection with Graph Neural Networks
• EEG-Based Emotion Recognition Using Regularized Graph Neural Networks
• GResNet: Graph Residual Network for Reviving Deep GNNs from Suspended Animation
• Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization
• Subgraph Neural Networks
• AEGCN: An Autoencoder-Constrained Graph Convolutional Network
• Continuous Graph Neural Networks
• Neural ranking models for document retrieval
• Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies
• Hypergraph Convolution and Hypergraph Attention
• GINNs: Graph-Informed Neural Networks for Multiscale Physics
• Precise Learning of Source Code Contextual Semantics via Hierarchical Dependence Structure and Graph Attention Networks
• Graph neural network-based fault diagnosis: a review
• Self-Supervised Hypergraph Convolutional Networks for Session-based Recommendation
• Cell Complex Neural Networks
• Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks
• Dynamic Graph Convolutional Networks Using the Tensor M-Product
• Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree
• Path Integral Based Convolution and Pooling for Graph Neural Networks
• Self-Supervised Multi-Channel Hypergraph Convolutional Network for Social Recommendation
• Graph Star Net for Generalized Multi-Task Learning
• Incorporating Symbolic Domain Knowledge into Graph Neural Networks
• Edge-Featured Graph Attention Network
• Discrete and continuous representations and processing in deep learning: Looking forward
• Semantic and Relational Spaces in Science of Science: Deep Learning Models for Article Vectorisation
• Can Graph Neural Networks Count Substructures?
• Interpreting and Unifying Graph Neural Networks with An Optimization Framework
• A Review of Machine Learning Applications for the Proton Magnetic Resonance Spectroscopy Workflow
• Language-Conditioned Graph Networks for Relational Reasoning
• Representation, learning, and planning algorithms for geometric task and motion planning
• A Unified Lottery Ticket Hypothesis for Graph Neural Networks
• A Review of Graph Neural Networks and Their Applications in Power Systems
• Probing triple Higgs coupling with machine learning at the LHC
• Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering
• Solving the single-track train scheduling problem via Deep Reinforcement Learning
• Graph Policy Network for Transferable Active Learning on Graphs
• Understanding and Resolving Performance Degradation in Graph Convolutional Networks
• Bayesian graph convolutional neural networks via tempered MCMC
• Reliable Graph Neural Networks via Robust Aggregation
• Hybrid Quantum-Classical Graph Convolutional Network
• A Technique for Determining Relevance Scores of Process Activities using Graph-based Neural Networks
• Deep Learning for Scene Classification: A Survey
• Understanding the Role of Scene Graphs in Visual Question Answering
• Structured Citation Trend Prediction Using Graph Neural Networks
• A Joint Graph and Image Convolution Network for Automatic Brain Tumor Segmentation
• Building powerful and equivariant graph neural networks with structural message-passing
• Graph Element Networks: adaptive, structured computation and memory
• An Introduction to Electrocatalyst Design using Machine Learning for Renewable Energy Storage
• Graph Condensation for Graph Neural Networks
• Leveraging the Capabilities of Connected and Autonomous Vehicles and Multi-Agent Reinforcement Learning to Mitigate Highway Bottleneck Congestion
• Beyond Graph Neural Networks with Lifted Relational Neural Networks
• Structured Object-Aware Physics Prediction for Video Modeling and Planning
• Explaining Deep Graph Networks with Molecular Counterfactuals
• Improved Constraints on Effective Top Quark Interactions using Edge Convolution Networks
• Edge Representation Learning with Hypergraphs
• Deep Learning in Protein Structural Modeling and Design
• Enhancing Social Recommendation with Adversarial Graph Convolutional Networks
• AST-GCN: Attribute-Augmented Spatiotemporal Graph Convolutional Network for Traffic Forecasting
• Decoding Dark Matter Substructure without Supervision
• Multi-Stage Self-Supervised Learning for Graph Convolutional Networks on Graphs with Few Labels
• Evaluating Deep Graph Neural Networks
• Multi-Label Image Classification with Contrastive Learning
• SWAG: Item Recommendations using Convolutions on Weighted Graphs
• Incomplete Graph Representation and Learning via Partial Graph Neural Networks
• Learning to Drop: Robust Graph Neural Network via Topological Denoising
• Be More with Less: Hypergraph Attention Networks for Inductive Text Classification
• Constructions in combinatorics via neural networks
• Graph Neural Networks for reconstruction and classification in KM3NeT
• GraphZoom: A multi-level spectral approach for accurate and scalable graph embedding
• Insights from Graph Theory on the Morphologies of Actomyosin Networks with Multilinkers
• HGKT: Introducing Hierarchical Exercise Graph for Knowledge Tracing
• Learning Cross-Domain Representation with Multi-Graph Neural Network
• Node Similarity Preserving Graph Convolutional Networks
• DRIFT: Deep Reinforcement Learning for Functional Software Testing
• NODE-SELECT: A Graph Neural Network Based On A Selective Propagation Technique
• Active Learning of Abstract Plan Feasibility
• Categorical Normalizing Flows via Continuous Transformations
• Higher-order Weighted Graph Convolutional Networks
• Modular Design Patterns for Hybrid Learning and Reasoning Systems: a taxonomy, patterns and use cases
• Graph Neural Networks Inspired by Classical Iterative Algorithms
• Meta-Learning with Graph Neural Networks: Methods and Applications
• HAR-GCNN: Deep Graph CNNs for Human Activity Recognition From Highly Unlabeled Mobile Sensor Data
• Track Seeding and Labelling with Embedded-space Graph Neural Networks
• Deep Graph Similarity Learning: A Survey
• Text Level Graph Neural Network for Text Classification
• Learning to simulate and design for structural engineering
• Contrastive Graph Neural Network Explanation
• Webly Supervised Image Classification with Metadata: Automatic Noisy Label Correction via Visual-Semantic Graph
• Graph neural network for 3D classification of ambiguities and optical crosstalk in scintillator-based neutrino detectors
• Recursive Graphical Neural Networks for Text Classification
• Memory-Based Graph Networks
• A Novel Genetic Algorithm with Hierarchical Evaluation Strategy for Hyperparameter Optimisation of Graph Neural Networks
• A Tailored Convolutional Neural Network for Nonlinear Manifold Learning of Computational Physics Data using Unstructured Spatial Discretizations
• Graph Generative Models for Fast Detector Simulations in High Energy Physics
• GraphConfRec: A Graph Neural Network-Based Conference Recommender System
• DyGCN: Dynamic Graph Embedding with Graph Convolutional Network
• Optimization of Graph Neural Networks with Natural Gradient Descent
• Learning the Relation between Code Features and Code Transforms with Structured Prediction
• Multi-task Batch Reinforcement Learning with Metric Learning
• Build2Vec: Building Representation in Vector Space
• RepGN:Object Detection with Relational Proposal Graph Network
• ActiveHNE: Active Heterogeneous Network Embedding
• Edge-Enhanced Graph Convolution Networks for Event Detection with Syntactic Relation
• Rubik: A Hierarchical Architecture for Efficient Graph Learning
• Graph Convolutional Networks with EigenPooling
• CoCoSum: Contextual Code Summarization with Multi-Relational Graph Neural Network
• EnGN: A High-Throughput and Energy-Efficient Accelerator for Large Graph Neural Networks
• Transient Chaos in BERT
• Lifelong Graph Learning
• Graph Convolutional Neural Networks via Motif-based Attention
• flexgrid2vec: Learning Efficient Visual Representations Vectors
• MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning
• Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection
• Field-level simulation-based inference with galaxy catalogs: the impact of systematic effects
• Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
• Self-Enhanced GNN: Improving Graph Neural Networks Using Model Outputs
• A Hierarchy of Graph Neural Networks Based on Learnable Local Features
• Relational Graph Representation Learning for Open-Domain Question Answering
• Relational Graph Learning on Visual and Kinematics Embeddings for Accurate Gesture Recognition in Robotic Surgery
• Tiered Latent Representations and Latent Spaces for Molecular Graphs
• Decentralized Inference with Graph Neural Networks in Wireless Communication Systems
• Label-GCN: An Effective Method for Adding Label Propagation to Graph Convolutional Networks
• EPNE: Evolutionary Pattern Preserving Network Embedding
• Scalable Self-Supervised Representation Learning from Spatiotemporal Motion Trajectories for Multimodal Computer Vision
• Utilising Graph Machine Learning within Drug Discovery and Development
• Adaptive-Step Graph Meta-Learner for Few-Shot Graph Classification
• Reachability Embeddings: Scalable Self-Supervised Representation Learning from Mobility Trajectories for Multimodal Geospatial Computer Vision
• Black-box Gradient Attack on Graph Neural Networks: Deeper Insights in Graph-based Attack and Defense
• Graph Signal Processing -- Part III: Machine Learning on Graphs, from Graph Topology to Applications
• Categorical Representation Learning: Morphism is All You Need
• Message Passing Neural Processes
• SMASH: Sparse Matrix Atomic Scratchpad Hashing
• High-resolution rainfall-runoff modeling using graph neural network
• Distributionally Robust Semi-Supervised Learning Over Graphs
• Scaling Graph-based Deep Learning models to larger networks
• Predicting drug-target interaction using 3D structure-embedded graph representations from graph neural networks
• Traffic4cast 2020 -- Graph Ensemble Net and the Importance of Feature And Loss Function Design for Traffic Prediction
• Meta-GCN: A Dynamically Weighted Loss Minimization Method for Dealing with the Data Imbalance in Graph Neural Networks
• Natural Language QA Approaches using Reasoning with External Knowledge
• Policy-GNN: Aggregation Optimization for Graph Neural Networks
• EvoNet: A Neural Network for Predicting the Evolution of Dynamic Graphs
• Neural Packet Classification
• Preserve, Promote, or Attack? GNN Explanation via Topology Perturbation
• Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks
• Quaternion Graph Neural Networks
• Graph convolutions that can finally model local structure
• Unifying Neural Learning and Symbolic Reasoning for Spinal Medical Report Generation
• Dynamic Graph Representation for Partially Occluded Biometrics
• GraphTER: Unsupervised Learning of Graph Transformation Equivariant Representations via Auto-Encoding Node-wise Transformations
• Scalable Attack on Graph Data by Injecting Vicious Nodes
• Contextualized Graph Attention Network for Recommendation with Item Knowledge Graph
• Generalization bounds for graph convolutional neural networks via Rademacher complexity
• Tree Structure-Aware Graph Representation Learning via Integrated Hierarchical Aggregation and Relational Metric Learning
• Spectral Temporal Graph Neural Network for Trajectory Prediction
• Dynamic Spatiotemporal Graph Neural Network with Tensor Network
• Understanding the Basis of Graph Convolutional Neural Networks via an Intuitive Matched Filtering Approach
• Graph Neural Processes: Towards Bayesian Graph Neural Networks
• A Fast Graph Neural Network-Based Method for Winner Determination in Multi-Unit Combinatorial Auctions
• Explain Graph Neural Networks to Understand Weighted Graph Features in Node Classification
• Exploiting Heterogeneous Graph Neural Networks with Latent Worker/Task Correlation Information for Label Aggregation in Crowdsourcing
• Exploiting Spiking Dynamics with Spatial-temporal Feature Normalization in Graph Learning
• Self-supervised Auxiliary Learning for Graph Neural Networks via Meta-Learning
• Fast Training of Sparse Graph Neural Networks on Dense Hardware
• GraphTTS: graph-to-sequence modelling in neural text-to-speech
• A Framework for End-to-End Learning on Semantic Tree-Structured Data
• GraLSP: Graph Neural Networks with Local Structural Patterns
• Using Local Knowledge Graph Construction to Scale Seq2Seq Models to Multi-Document Inputs
• CPR-GCN: Conditional Partial-Residual Graph Convolutional Network in Automated Anatomical Labeling of Coronary Arteries
• Financial Crime & Fraud Detection Using Graph Computing: Application Considerations & Outlook
• PyTorch-Direct: Enabling GPU Centric Data Access for Very Large Graph Neural Network Training with Irregular Accesses
• Machine Learning for Robotic Manipulation
• Towards Scale-Invariant Graph-related Problem Solving by Iterative Homogeneous Graph Neural Networks
• FedGraph: Federated Graph Learning with Intelligent Sampling
• Act Like a Radiologist: Towards Reliable Multi-view Correspondence Reasoning for Mammogram Mass Detection
• SF-SGL: Solver-Free Spectral Graph Learning from Linear Measurements
• Adversarial methods to reduce simulation bias in neutrino interaction event filtering at Liquid Argon Time Projection Chambers
• Multimodal and Contrastive Learning for Click Fraud Detection
• Accurate Prediction of Free Solvation Energy of Organic Molecules via Graph Attention Network and Message Passing Neural Network from Pairwise Atomistic Interactions
• A Genetic Algorithm with Tree-structured Mutation for Hyperparameter Optimisation of Graph Neural Networks
• The Atlas for the Aspiring Network Scientist
• Message Passing Adaptive Resonance Theory for Online Active Semi-supervised Learning
• New Ideas and Trends in Deep Multimodal Content Understanding: A Review
• Towards a predictive spatio-temporal representation of brain data
• GraphPB: Graphical Representations of Prosody Boundary in Speech Synthesis
• Improving Reliable Navigation under Uncertainty via Predictions Informed by Non-Local Information
• Explicit Pairwise Factorized Graph Neural Network for Semi-Supervised Node Classification
• Graph Belief Propagation Networks
• Temporal Reasoning Graph for Activity Recognition
• Inferring halo masses with Graph Neural Networks
• Structure-Aware Label Smoothing for Graph Neural Networks
• Attentional Graph Convolutional Networks for Knowledge Concept Recommendation in MOOCs in a Heterogeneous View
• Recurrent Attention Walk for Semi-supervised Classification
• Learning with Molecules beyond Graph Neural Networks
• GmCN: Graph Mask Convolutional Network
• SCR-Graph: Spatial-Causal Relationships based Graph Reasoning Network for Human Action Prediction
• When to Talk: Chatbot Controls the Timing of Talking during Multi-turn Open-domain Dialogue Generation
• Deep Generative Modeling in Network Science with Applications to Public Policy Research
• Comparisons of Graph Neural Networks on Cancer Classification Leveraging a Joint of Phenotypic and Genetic Features
• Graph Attention Multi-Agent Fleet Autonomy for Advanced Air Mobility
• Flexible dual-branched message passing neural network for quantum mechanical property prediction with molecular conformation
• Learning to Dynamically Coordinate Multi-Robot Teams in Graph Attention Networks
• AppQ: Warm-starting App Recommendation Based on View Graphs
• Graph Computing for Financial Crime and Fraud Detection: Trends, Challenges and Outlook
• Structure-Aware Human-Action Generation
• Deep Neural Network for 3D Surface Segmentation based on Contour Tree Hierarchy
• Particle Track Reconstruction using Geometric Deep Learning
• Neural Topic Modeling by Incorporating Document Relationship Graph
• Learning Robust Representations with Graph Denoising Policy Network
• Symmetry-adapted graph neural networks for constructing molecular dynamics force fields
• UCNN: A Convolutional Strategy on Unstructured Mesh
• Embedding Symbolic Temporal Knowledge into Deep Sequential Models
• Graph Neural Networks to Predict Customer Satisfaction Following Interactions with a Corporate Call Center
• ConvDySAT: Deep Neural Representation Learning on Dynamic Graphs via Self-Attention and Convolutional Neural Networks
• Semiparametric Nonlinear Bipartite Graph Representation Learning with Provable Guarantees
• Deep Multi-attribute Graph Representation Learning on Protein Structures
• Graph Convolution Networks for Probabilistic Modeling of Driving Acceleration
• Data-Driven Construction of Data Center Graph of Things for Anomaly Detection
• InteractionNet: Modeling and Explaining of Noncovalent Protein-Ligand Interactions with Noncovalent Graph Neural Network and Layer-Wise Relevance Propagation
• Neural Stochastic Block Model & Scalable Community-Based Graph Learning
• A Unified Framework for Cross-Domain and Cross-System Recommendations
• Scene Context Based Semantic Segmentation for 3D LiDAR Data in Dynamic Scene
• Context-Aware Graph Attention Networks
• Eigen-GNN: A Graph Structure Preserving Plug-in for GNNs
• Towards Robust Pattern Recognition: A Review
• Graph Convolutional Networks in Feature Space for Image Deblurring and Super-resolution
• Graph Neural Networks for Node-Level Predictions
• AHINE: Adaptive Heterogeneous Information Network Embedding
• End-to-End Learning from Complex Multigraphs with Latent-Graph Convolutional Networks
• GCCN: Global Context Convolutional Network
• Generalized Constraints as A New Mathematical Problem in Artificial Intelligence: A Review and Perspective
• Combinatorial Learning of Graph Edit Distance via Dynamic Embedding
• Analyzing the Performance of Graph Neural Networks with Pipe Parallelism
• Approximate Fixed-Points in Recurrent Neural Networks
• A Weighted Heterogeneous Graph Based Dialogue System
• Meta Graph Attention on Heterogeneous Graph with Node-Edge Co-evolution
• Co-embedding of Nodes and Edges with Graph Neural Networks
• Anomaly Detection for Aggregated Data Using Multi-Graph Autoencoder
• Learning Fine-Grained Segmentation of 3D Shapes without Part Labels
• Graph Feature Gating Networks
• A Graph Neural Network Approach for Product Relationship Prediction
• Implicit vs Unfolded Graph Neural Networks
• Fully Linear Graph Convolutional Networks for Semi-Supervised Learning and Clustering
• Exploring Graph Classification Techniques Under Low Data Constraints: A Comprehensive Study
• Automated Graph Learning via Population Based Self-Tuning GCN
• PatentMiner: Patent Vacancy Mining via Context-enhanced and Knowledge-guided Graph Attention
• Integrated Node Encoder for Labelled Textual Networks
• Towards Better Graph Representation: Two-Branch Collaborative Graph Neural Networks for Multimodal Marketing Intention Detection
• Graph Convolutional Network with Generalized Factorized Bilinear Aggregation
• Training Graph Neural Networks by Graphon Estimation
• Meta-Aggregator: Learning to Aggregate for 1-bit Graph Neural Networks
• Learning Graph Neural Networks with Approximate Gradient Descent
• Inducing Optimal Attribute Representations for Conditional GANs
• Automatic design of novel potential 3CL${}^{\text{pro}}$ and PL${}^{\text{pro}}$ inhibitors
• ParaVS: A Simple, Fast, Efficient and Flexible Graph Neural Network Framework for Structure-Based Virtual Screening
• Relate and Predict: Structure-Aware Prediction with Jointly Optimized Neural DAG
• Deep Graph Matching under Quadratic Constraint
• Graph Convolutional Network for Swahili News Classification
• Spatio-Temporal Sparsification for General Robust Graph Convolution Networks
• Applications of Common Information to Computing Functions
• Deep Clustering with Measure Propagation
• Relevant Region Prediction for Crowd Counting
• DeGNN: Characterizing and Improving Graph Neural Networks with Graph Decomposition
• Graph Neural Network for Hamiltonian-Based Material Property Prediction
• Material characterization and precise finite element analysis of fiber reinforced thermoplastic composites for 4D printing
• CAGE: Context-Aware Grasping Engine
• Structural Landmarking and Interaction Modelling: on Resolution Dilemmas in Graph Classification
• Fast Haar Transforms for Graph Neural Networks
• DeepDrawing: A Deep Learning Approach to Graph Drawing
• Learning and Reasoning with the Graph Structure Representation in Robotic Surgery
• Automated Intracranial Artery Labeling using a Graph Neural Network and Hierarchical Refinement
• Learn to Propagate Reliably on Noisy Affinity Graphs
• Can NetGAN be improved on short random walks?
• Brushing Feature Values in Immersive Graph Visualization Environment
• A Metamodel and Framework for AGI
• CANet: Cross-disease Attention Network for Joint Diabetic Retinopathy and Diabetic Macular Edema Grading
• Community-preserving Graph Convolutions for Structural and Functional Joint Embedding of Brain Networks
• Regularizing Semi-supervised Graph Convolutional Networks with a Manifold Smoothness Loss
• A New Clustering neural network for Chinese word segmentation
• Joint Use of Node Attributes and Proximity for Semi-Supervised Classification on Graphs