Neural Message Passing for Quantum Chemistry

Abstract

Supervised learning on molecules has incredible potential to be useful in chemistry, drug discovery, and materials science. Luckily, several promising and closely related neural network models invariant to molecular symmetries have already been described in the literature. These models learn a message passing algorithm and aggregation procedure to compute a function of their entire input graph. At this point, the next step is to find a particularly effective variant of this general approach and apply it to chemical prediction benchmarks until we either solve them or reach the limits of the approach. In this paper, we reformulate existing models into a single common framework we call Message Passing Neural Networks (MPNNs) and explore additional novel variations within this framework. Using MPNNs we demonstrate state of the art results on an important molecular property prediction benchmark; these results are strong enough that we believe future work should focus on datasets with larger molecules or more accurate ground truth labels.

14 pages

Cited by in corpus (1037)

• E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
• Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals
• Modeling polypharmacy side effects with graph convolutional networks
• Graph Neural Networks: A Review of Methods and Applications
• Graph Neural Network for Traffic Forecasting: A Survey
• Recent Advances and Applications of Deep Learning Methods in Materials Science
• PhysNet: A Neural Network for Predicting Energies, Forces, Dipole Moments and Partial Charges
• Adversarial Attacks on Neural Networks for Graph Data
• Representation Learning on Graphs with Jumping Knowledge Networks
• Molecular Contrastive Learning of Representations via Graph Neural Networks
• Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
• Less is more: sampling chemical space with active learning
• Graph Contrastive Learning with Augmentations
• DScribe: Library of Descriptors for Machine Learning in Materials Science
• Contrastive Representation Learning: A Framework and Review
• Hierarchical Graph Representation Learning with Differentiable Pooling
• Junction Tree Variational Autoencoder for Molecular Graph Generation
• Atomistic Line Graph Neural Network for Improved Materials Property Predictions
• Deep Graph Library: A Graph-Centric, Highly-Performant Package for Graph Neural Networks
• AutoAugment: Learning Augmentation Policies from Data
• Machine learning prediction errors better than DFT accuracy
• GNNExplainer: Generating Explanations for Graph Neural Networks
• Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
• DeepAffinity: Interpretable Deep Learning of Compound-Protein Affinity through Unified Recurrent and Convolutional Neural Networks
• Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
• Towards Deeper Graph Neural Networks
• DeepPurpose: a Deep Learning Library for Drug-Target Interaction Prediction
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• Session-based Social Recommendation via Dynamic Graph Attention Networks
• SchNetPack: A Deep Learning Toolbox For Atomistic Systems
• Learning to Simulate Complex Physics with Graph Networks
• Learning Deep Generative Models of Graphs
• Few-Shot Learning with Graph Neural Networks
• Predicting materials properties without crystal structure: Deep representation learning from stoichiometry
• ChemBERTa: Large-Scale Self-Supervised Pretraining for Molecular Property Prediction
• Self-Supervised Graph Transformer on Large-Scale Molecular Data
• E-GraphSAGE: A Graph Neural Network based Intrusion Detection System for IoT
• Large-Scale Optical Neural Networks based on Photoelectric Multiplication
• A Survey on Graph Kernels
• Learning Structural Node Embeddings Via Diffusion Wavelets
• Self-Attention Graph Pooling
• Scaling Graph Neural Networks with Approximate PageRank
• How Powerful are Graph Neural Networks?
• CCNet: Criss-Cross Attention for Semantic Segmentation
• SpookyNet: Learning Force Fields with Electronic Degrees of Freedom and Nonlocal Effects
• Constrained Graph Variational Autoencoders for Molecule Design
• A Generalization of Transformer Networks to Graphs
• A Comprehensive Survey of Scene Graphs: Generation and Application
• A Gentle Introduction to Deep Learning for Graphs
• Combinatorial Optimization with Graph Convolutional Networks and Guided Tree Search
• TUDataset: A collection of benchmark datasets for learning with graphs
• Improving Graph Neural Network Expressivity via Subgraph Isomorphism Counting
• Dynamic Graph CNN for Learning on Point Clouds
• WILDS: A Benchmark of in-the-Wild Distribution Shifts
• Graph-based Deep Learning for Communication Networks: A Survey
• Link Prediction Based on Graph Neural Networks
• Transformer-CNN: Fast and Reliable tool for QSAR
• Discovering Symbolic Models from Deep Learning with Inductive Biases
• Graph networks as learnable physics engines for inference and control
• SE(3)-Transformers: 3D Roto-Translation Equivariant Attention Networks
• Information-theoretic bounds on quantum advantage in machine learning
• Spatial-Temporal Transformer Networks for Traffic Flow Forecasting
• polyBERT: A chemical language model to enable fully machine-driven ultrafast polymer informatics
• Deep Reinforcement Learning meets Graph Neural Networks: exploring a routing optimization use case
• On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
• A Survey of Knowledge-Enhanced Text Generation
• Exact Combinatorial Optimization with Graph Convolutional Neural Networks
• Attention-based Graph Neural Network for Semi-supervised Learning
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• Neural Relational Inference for Interacting Systems
• Residual Gated Graph ConvNets
• Principal Neighbourhood Aggregation for Graph Nets
• Graph Convolutional Policy Network for Goal-Directed Molecular Graph Generation
• Benchmarking Graph Neural Networks
• Unveiling the potential of Graph Neural Networks for network modeling and optimization in SDN
• DGL-LifeSci: An Open-Source Toolkit for Deep Learning on Graphs in Life Science
• Learning to Predict the Cosmological Structure Formation
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• Knowledge Matters: Radiology Report Generation with General and Specific Knowledge
• Combining SchNet and SHARC: The SchNarc machine learning approach for excited-state dynamics
• Conditional molecular design with deep generative models
• GraphAF: a Flow-based Autoregressive Model for Molecular Graph Generation
• Rapid Prediction of Electron-Ionization Mass Spectrometry using Neural Networks
• ETA Prediction with Graph Neural Networks in Google Maps
• Atom2Vec: learning atoms for materials discovery
• HyperGCN: A New Method of Training Graph Convolutional Networks on Hypergraphs
• Learning from Protein Structure with Geometric Vector Perceptrons
• Inverse design of 3d molecular structures with conditional generative neural networks
• Metrics for Graph Comparison: A Practitioner's Guide
• Coarse Graining Molecular Dynamics with Graph Neural Networks
• Towards Sparse Hierarchical Graph Classifiers
• Evaluation of the MACE Force Field Architecture: from Medicinal Chemistry to Materials Science
• Fake News Detection on Social Media using Geometric Deep Learning
• SIGN: Scalable Inception Graph Neural Networks
• Missing Data Imputation with Adversarially-trained Graph Convolutional Networks
• Graph Neural Networks Exponentially Lose Expressive Power for Node Classification
• Learning a SAT Solver from Single-Bit Supervision
• LanczosNet: Multi-Scale Deep Graph Convolutional Networks
• Multi-view Graph Contrastive Representation Learning for Drug-Drug Interaction Prediction
• Learning Discrete Structures for Graph Neural Networks
• Strategies for Pre-training Graph Neural Networks
• Kohn-Sham equations as regularizer: building prior knowledge into machine-learned physics
• Molecular graph generation with Graph Neural Networks
• Multipole Graph Neural Operator for Parametric Partial Differential Equations
• A Review of Location Encoding for GeoAI: Methods and Applications
• Learning Combinatorial Optimization on Graphs: A Survey with Applications to Networking
• Machine learning on DNA-encoded libraries: A new paradigm for hit-finding
• Bayesian semi-supervised learning for uncertainty-calibrated prediction of molecular properties and active learning
• Machine learning of molecular properties: locality and active learning
• Deep Learning on Graphs: A Survey
• Adversarial Attack on Graph Structured Data
• Structured Neural Summarization
• Pre-training Molecular Graph Representation with 3D Geometry
• Graph Neural Networks: Taxonomy, Advances and Trends
• End-to-end Symmetry Preserving Inter-atomic Potential Energy Model for Finite and Extended Systems
• Few-Shot Graph Learning for Molecular Property Prediction
• Neural Operator: Graph Kernel Network for Partial Differential Equations
• InfoGraph: Unsupervised and Semi-supervised Graph-Level Representation Learning via Mutual Information Maximization
• Adversarial Graph Augmentation to Improve Graph Contrastive Learning
• Pre-training of Graph Neural Network for Modeling Effects of Mutations on Protein-Protein Binding Affinity
• Learning representations of irregular particle-detector geometry with distance-weighted graph networks
• GraphVAE: Towards Generation of Small Graphs Using Variational Autoencoders
• Composition-based Multi-Relational Graph Convolutional Networks
• Cormorant: Covariant Molecular Neural Networks
• Do Transformers Really Perform Bad for Graph Representation?
• A Survey on Graph-Based Deep Learning for Computational Histopathology
• Knowledge Graph Reasoning with Relational Digraph
• Relational Neural Expectation Maximization: Unsupervised Discovery of Objects and their Interactions
• Differentiable Graph Module (DGM) for Graph Convolutional Networks
• Using Attribution to Decode Dataset Bias in Neural Network Models for Chemistry
• Graph Neural Tangent Kernel: Fusing Graph Neural Networks with Graph Kernels
• Machine Learning on Neutron and X-Ray Scattering
• Cross-Scale Internal Graph Neural Network for Image Super-Resolution
• GNNGuard: Defending Graph Neural Networks against Adversarial Attacks
• HATS: A Hierarchical Graph Attention Network for Stock Movement Prediction
• An Efficient Lorentz Equivariant Graph Neural Network for Jet Tagging
• OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
• Supervised Community Detection with Line Graph Neural Networks
• Geom-GCN: Geometric Graph Convolutional Networks
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Understanding Pooling in Graph Neural Networks
• A Fair Comparison of Graph Neural Networks for Graph Classification
• Cross-modal Knowledge Reasoning for Knowledge-based Visual Question Answering
• Network Medicine Framework for Identifying Drug Repurposing Opportunities for COVID-19
• Message-passing neural networks for high-throughput polymer screening
• Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
• Machine learning and AI-based approaches for bioactive ligand discovery and GPCR-ligand recognition
• TeaNet: universal neural network interatomic potential inspired by iterative electronic relaxations
• Learning neural network potentials from experimental data via Differentiable Trajectory Reweighting
• Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics
• How Neural Networks Extrapolate: From Feedforward to Graph Neural Networks
• Hierarchical Generation of Molecular Graphs using Structural Motifs
• Molecule Attention Transformer
• GraphVite: A High-Performance CPU-GPU Hybrid System for Node Embedding
• Graph neural networks for laminar flow prediction around random 2D shapes
• GAG: Global Attributed Graph Neural Network for Streaming Session-based Recommendation
• E(n) Equivariant Graph Neural Networks
• FedGraphNN: A Federated Learning System and Benchmark for Graph Neural Networks
• Adaptive Propagation Graph Convolutional Network
• Session-based Recommendation with Hypergraph Attention Networks
• OrbNet Denali: A machine learning potential for biological and organic chemistry with semi-empirical cost and DFT accuracy
• End-to-End Differentiable Molecular Mechanics Force Field Construction
• Learning the exchange-correlation functional from nature with fully differentiable density functional theory
• A Deep Generative Model for Molecule Optimization via One Fragment Modification
• Informing Geometric Deep Learning with Electronic Interactions to Accelerate Quantum Chemistry
• Generative Models for Automatic Chemical Design
• Distance Encoding: Design Provably More Powerful Neural Networks for Graph Representation Learning
• Global Self-Attention as a Replacement for Graph Convolution
• What Can Neural Networks Reason About?
• Machine Learning on Graphs: A Model and Comprehensive Taxonomy
• Graph Information Bottleneck
• Filter-informed Spectral Graph Wavelet Networks for Multiscale Feature Extraction and Intelligent Fault Diagnosis
• Graph Capsule Convolutional Neural Networks
• Temporal Graph Networks for Deep Learning on Dynamic Graphs
• Adaptive Universal Generalized PageRank Graph Neural Network
• Graph Neural Network and Spatiotemporal Transformer Attention for 3D Video Object Detection from Point Clouds
• SchNetPack 2.0: A neural network toolbox for atomistic machine learning
• Graph Kernels: A Survey
• On Explainability of Graph Neural Networks via Subgraph Explorations
• On the Bottleneck of Graph Neural Networks and its Practical Implications
• Solid Harmonic Wavelet Scattering for Predictions of Molecule Properties
• Deep Graph Matching and Searching for Semantic Code Retrieval
• D-VAE: A Variational Autoencoder for Directed Acyclic Graphs
• 3D Infomax improves GNNs for Molecular Property Prediction
• A Survey on The Expressive Power of Graph Neural Networks
• Modeling Relational Data with Graph Convolutional Networks
• Graph Unrolling Networks: Interpretable Neural Networks for Graph Signal Denoising
• A Comparison of Neural Network Architectures for Data-Driven Reduced-Order Modeling
• Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast
• Deep Graph Convolutional Reinforcement Learning for Financial Portfolio Management -- DeepPocket
• TransGCN:Coupling Transformation Assumptions with Graph Convolutional Networks for Link Prediction
• Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules
• Deeply learning molecular structure-property relationships using attention- and gate-augmented graph convolutional network
• Hopfield Networks is All You Need
• Spectral Clustering with Graph Neural Networks for Graph Pooling
• NF-GNN: Network Flow Graph Neural Networks for Malware Detection and Classification
• Graph WaveNet for Deep Spatial-Temporal Graph Modeling
• GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
• GraphSAIL: Graph Structure Aware Incremental Learning for Recommender Systems
• A Graph to Graphs Framework for Retrosynthesis Prediction
• Compositional Generalization in Semantic Parsing: Pre-training vs. Specialized Architectures
• Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials
• Task Placement and Resource Allocation for Edge Machine Learning: A GNN-based Multi-Agent Reinforcement Learning Paradigm
• Scalable Graph Learning for Anti-Money Laundering: A First Look
• Generative Code Modeling with Graphs
• Recurrent Independent Mechanisms
• Learning to Represent Edits
• Learning Graph Models for Retrosynthesis Prediction
• Three-Dimensionally Embedded Graph Convolutional Network (3DGCN) for Molecule Interpretation
• Rethinking Graph Transformers with Spectral Attention
• Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data
• Graph Neural Networks for Natural Language Processing: A Survey
• Hierarchical Visualization of Materials Space with Graph Convolutional Neural Networks
• Representation Learning for Dynamic Graphs: A Survey
• Automated Machine Learning on Graphs: A Survey
• Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Data
• Edge Attention-based Multi-Relational Graph Convolutional Networks
• Equivariant graph neural networks for fast electron density estimation of molecules, liquids, and solids
• DiffMG: Differentiable Meta Graph Search for Heterogeneous Graph Neural Networks
• Probing stop pair production at the LHC with graph neural networks
• Graph Convolutional Neural Networks for Body Force Prediction
• Scene Recognition with Prototype-agnostic Scene Layout
• Reactive Dynamics and Spectroscopy of Hydrogen Transfer from Neural Network-Based Reactive Potential Energy Surfaces
• DropMessage: Unifying Random Dropping for Graph Neural Networks
• N-body Networks: a Covariant Hierarchical Neural Network Architecture for Learning Atomic Potentials
• KPGT: Knowledge-Guided Pre-training of Graph Transformer for Molecular Property Prediction
• Graph Neural Networks Accelerated Molecular Dynamics
• Temperature-transferable coarse-graining of ionic liquids with dual graph convolutional neural networks
• Graph neural networks for simulating crack coalescence and propagation in brittle materials
• Hierarchical Representation Learning in Graph Neural Networks with Node Decimation Pooling
• Graph Kernels: State-of-the-Art and Future Challenges
• PANNA: Properties from Artificial Neural Network Architectures
• Quantum Graph Neural Networks
• Detection of Topological Materials with Machine Learning
• Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node Representation Learning
• Physical Pooling Functions in Graph Neural Networks for Molecular Property Prediction
• Explainability Techniques for Graph Convolutional Networks
• Unveiling CP property of top-Higgs coupling with graph neural networks at the LHC
• Is Homophily a Necessity for Graph Neural Networks?
• Graph Neural Network Based Coarse-Grained Mapping Prediction
• DDGK: Learning Graph Representations for Deep Divergence Graph Kernels
• A Survey of Deep Learning for Scientific Discovery
• Janossy Pooling: Learning Deep Permutation-Invariant Functions for Variable-Size Inputs
• Machine Learning Prediction of Accurate Atomization Energies of Organic Molecules from Low-Fidelity Quantum Chemical Calculations
• Implicit Graph Neural Networks
• A Perspective on Deep Learning for Molecular Modeling and Simulations
• Learning Human-Object Interactions by Graph Parsing Neural Networks
• Thermodynamics-informed graph neural networks
• DIG: A Turnkey Library for Diving into Graph Deep Learning Research
• Deep Ensembles vs. Committees for Uncertainty Estimation in Neural-Network Force Fields: Comparison and Application to Active Learning
• High-Level Synthesis Performance Prediction using GNNs: Benchmarking, Modeling, and Advancing
• Identity Inference on Blockchain using Graph Neural Network
• Revisiting Over-smoothing in Deep GCNs
• Supervised deep learning in high energy phenomenology: a mini review
• A Two-Step Graph Convolutional Decoder for Molecule Generation
• AdaGNN: Graph Neural Networks with Adaptive Frequency Response Filter
• Rethinking pooling in graph neural networks
• SE-GSL: A General and Effective Graph Structure Learning Framework through Structural Entropy Optimization
• Generalization and Representational Limits of Graph Neural Networks
• Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures
• Charged particle tracking via edge-classifying interaction networks
• Rotation Invariant Graph Neural Networks using Spin Convolutions
• MoleculeNet: A Benchmark for Molecular Machine Learning
• Colmena: Scalable Machine-Learning-Based Steering of Ensemble Simulations for High Performance Computing
• Beyond Low-pass Filtering: Graph Convolutional Networks with Automatic Filtering
• On the Binding Problem in Artificial Neural Networks
• Graph Partition Neural Networks for Semi-Supervised Classification
• Graph Pooling via Coarsened Graph Infomax
• GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles
• Graph Clustering with Graph Neural Networks
• Are Powerful Graph Neural Nets Necessary? A Dissection on Graph Classification
• MAGNNETO: A Graph Neural Network-based Multi-Agent system for Traffic Engineering
• HNHN: Hypergraph Networks with Hyperedge Neurons
• Deep Coarse-grained Potentials via Relative Entropy Minimization
• TRiPOD: Human Trajectory and Pose Dynamics Forecasting in the Wild
• MT-CGCNN: Integrating Crystal Graph Convolutional Neural Network with Multitask Learning for Material Property Prediction
• Hyperbolic Attention Networks
• Reinforcement Learning Based Graph-to-Sequence Model for Natural Question Generation
• Force-Field-Enhanced Neural Network Interactions: from Local Equivariant Embedding to Atom-in-Molecule properties and long-range effects
• Automating Botnet Detection with Graph Neural Networks
• Graph Convolutional Neural Networks with Node Transition Probability-based Message Passing and DropNode Regularization
• Weisfeiler and Lehman Go Topological: Message Passing Simplicial Networks
• Subgraph Neural Networks
• GNN-FiLM: Graph Neural Networks with Feature-wise Linear Modulation
• Motif-based Graph Self-Supervised Learning for Molecular Property Prediction
• Convolutional Neural Nets in Chemical Engineering: Foundations, Computations, and Applications
• Multi-Task Representation Learning with Multi-View Graph Convolutional Networks
• How Attentive are Graph Attention Networks?
• Learning Gradient Fields for Molecular Conformation Generation
• DECOR: Degree-Corrected Social Graph Refinement for Fake News Detection
• Machine learning for molecular dynamics with strongly correlated electrons
• Message-Passing Neural Networks Learn Little's Law
• Learning the Travelling Salesperson Problem Requires Rethinking Generalization
• Graph Neural Networks for Graph Drawing
• Continuous Graph Neural Networks
• GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement
• All SMILES Variational Autoencoder
• Predicting Biomedical Interactions with Higher-Order Graph Convolutional Networks
• Computer-Aided Design as Language
• Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning Approach for Rumor Detection
• Neural 3D Morphable Models: Spiral Convolutional Networks for 3D Shape Representation Learning and Generation
• Graph Normalizing Flows
• Continuous Conditional Random Field Convolution for Point Cloud Segmentation
• Dirichlet Energy Constrained Learning for Deep Graph Neural Networks
• Adversarial Attacks and Defenses on Graphs: A Review, A Tool and Empirical Studies
• RadarGNN: Transformation Invariant Graph Neural Network for Radar-based Perception
• ML Models of Vibrating H${}_2$CO: Comparing Reproducing Kernels, FCHL and PhysNet
• CenGCN: Centralized Convolutional Networks with Vertex Imbalance for Scale-Free Graphs
• Self-Supervised Bug Detection and Repair
• ACE-HGNN: Adaptive Curvature Exploration Hyperbolic Graph Neural Network
• Hypergraph Convolution and Hypergraph Attention
• Stealing Links from Graph Neural Networks
• Generating valid Euclidean distance matrices
• A Short Tutorial on The Weisfeiler-Lehman Test And Its Variants
• Hashing-Accelerated Graph Neural Networks for Link Prediction
• On the equivalence between graph isomorphism testing and function approximation with GNNs
• Learning to Extend Molecular Scaffolds with Structural Motifs
• Heterogeneous Graph Neural Networks for Extractive Document Summarization
• SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design
• Constant Curvature Graph Convolutional Networks
• Energy-weighted Message Passing: an infra-red and collinear safe graph neural network algorithm
• Reinforced Genetic Algorithm Learning for Optimizing Computation Graphs
• Dual-Primal Graph Convolutional Networks
• Predicting solvation free energies for neutral molecules in any solvent with openCOSMO-RS
• Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
• Graphite: Iterative Generative Modeling of Graphs
• Chemical-Reaction-Aware Molecule Representation Learning
• Learning Variable Ordering Heuristics for Solving Constraint Satisfaction Problems
• Multi-View Graph Neural Networks for Molecular Property Prediction
• Finite Volume Graph Network(FVGN): Predicting unsteady incompressible fluid dynamics with finite volume informed neural network
• LieTransformer: Equivariant self-attention for Lie Groups
• Natural Graph Networks
• Bridging the Gap between Spatial and Spectral Domains: A Survey on Graph Neural Networks
• Understanding over-squashing and bottlenecks on graphs via curvature
• Dynamic Graph Convolutional Networks Using the Tensor M-Product
• Space4HGNN: A Novel, Modularized and Reproducible Platform to Evaluate Heterogeneous Graph Neural Network
• Differentiable Molecular Simulations for Control and Learning
• KGNN: Harnessing Kernel-based Networks for Semi-supervised Graph Classification
• Nested Graph Neural Networks
• Graph Collaborative Reasoning
• Benchmarking Accuracy and Generalizability of Four Graph Neural Networks Using Large In Vitro ADME Datasets from Different Chemical Spaces
• Designing the Topology of Graph Neural Networks: A Novel Feature Fusion Perspective
• Directed Acyclic Graph Neural Networks
• On the design space between molecular mechanics and machine learning force fields
• Detecting Code Clones with Graph Neural Networkand Flow-Augmented Abstract Syntax Tree
• Path Integral Based Convolution and Pooling for Graph Neural Networks
• The Unbalanced Gromov Wasserstein Distance: Conic Formulation and Relaxation
• Learning to Extrapolate Knowledge: Transductive Few-shot Out-of-Graph Link Prediction
• Piezoelectric modulus prediction using machine learning and graph neural networks
• Path-Aware Graph Attention for HD Maps in Motion Prediction
• An attentive neural architecture for joint segmentation and parsing and its application to real estate ads
• Investigating Object Compositionality in Generative Adversarial Networks
• M-Evolve: Structural-Mapping-Based Data Augmentation for Graph Classification
• Graph Star Net for Generalized Multi-Task Learning
• Learning Symbolic Physics with Graph Networks
• Spherical Message Passing for 3D Graph Networks
• Interpretable Graph Convolutional Network of Multi-Modality Brain Imaging for Alzheimer's Disease Diagnosis
• Towards Explainable Graph Representations in Digital Pathology
• Symmetrical Graph Neural Network for Quantum Chemistry, with Dual R/K Space
• Graph Convolutional Neural Networks for Polymers Property Prediction
• Graph Neural Networks: Methods, Applications, and Opportunities
• ænet-PyTorch: a GPU-supported implementation for machine learning atomic potentials training
• Large-Scale Representation Learning on Graphs via Bootstrapping
• NMR shift prediction from small data quantities
• PhysNet Meets CHARMM: A Framework for Routine Machine Learning / Molecular Mechanics Simulations
• GDDR: GNN-based Data-Driven Routing
• Exploring Edge Disentanglement for Node Classification
• Isomerization and Decomposition Reactions of Acetaldehyde Relevant to Atmospheric Processes from Dynamics Simulations on Neural Network-Based Potential Energy Surfaces
• Stochastic Graph Neural Networks
• OSLO: On-the-Sphere Learning for Omnidirectional images and its application to 360-degree image compression
• SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks
• MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
• Feature Overcorrelation in Deep Graph Neural Networks: A New Perspective
• Networked Time Series Imputation via Position-aware Graph Enhanced Variational Autoencoders
• Heterogeneous Network Representation Learning: A Unified Framework with Survey and Benchmark
• Bag of Tricks for Node Classification with Graph Neural Networks
• Finding Patient Zero: Learning Contagion Source with Graph Neural Networks
• Mean-field theory of graph neural networks in graph partitioning
• Molecular Property Prediction: A Multilevel Quantum Interactions Modeling Perspective
• Hierarchical Graph-to-Graph Translation for Molecules
• The Graph Neural Networking Challenge: A Worldwide Competition for Education in AI/ML for Networks
• Active Learning for Graph Neural Networks via Node Feature Propagation
• Can Graph Neural Networks Count Substructures?
• Deep Generative Models for Detector Signature Simulation: A Taxonomic Review
• Multi-hop Reading Comprehension across Multiple Documents by Reasoning over Heterogeneous Graphs
• Flow Network based Generative Models for Non-Iterative Diverse Candidate Generation
• A Meta-Learning Approach for Training Explainable Graph Neural Networks
• Language-Conditioned Graph Networks for Relational Reasoning
• Representation, learning, and planning algorithms for geometric task and motion planning
• Implementing graph neural networks with TensorFlow-Keras
• From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness
• A Unified Lottery Ticket Hypothesis for Graph Neural Networks
• Graph Neural Networks with Generated Parameters for Relation Extraction
• Image Classification with Hierarchical Multigraph Networks
• Stochastic Gradient Descent with Biased but Consistent Gradient Estimators
• Modeling electronic response properties with an explicit-electron machine learning potential
• Scene Graph Reasoning with Prior Visual Relationship for Visual Question Answering
• Generating equilibrium molecules with deep neural networks
• Graph Neural Networks for Surfactant Multi-Property Prediction
• Probing triple Higgs coupling with machine learning at the LHC
• Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling
• Search to aggregate neighborhood for graph neural network
• A Review of Graph Neural Networks and Their Applications in Power Systems
• Relational recurrent neural networks
• Gaussian Process Molecule Property Prediction with FlowMO
• Detecting Arbitrary Order Beneficial Feature Interactions for Recommender Systems
• SE(3)-equivariant prediction of molecular wavefunctions and electronic densities
• Reasoning Visual Dialogs with Structural and Partial Observations
• Understanding Image Retrieval Re-Ranking: A Graph Neural Network Perspective
• Graph Neural Networks with Learnable Structural and Positional Representations
• ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations
• TrackMPNN: A Message Passing Graph Neural Architecture for Multi-Object Tracking
• MugRep: A Multi-Task Hierarchical Graph Representation Learning Framework for Real Estate Appraisal
• A community-powered search of machine learning strategy space to find NMR property prediction models
• Spectral Multigraph Networks for Discovering and Fusing Relationships in Molecules
• ProGraML: Graph-based Deep Learning for Program Optimization and Analysis
• Understanding and Resolving Performance Degradation in Graph Convolutional Networks
• Graph-Guided Network for Irregularly Sampled Multivariate Time Series
• SLAPS: Self-Supervision Improves Structure Learning for Graph Neural Networks
• Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
• Graph Policy Network for Transferable Active Learning on Graphs
• Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
• Bayesian graph convolutional neural networks via tempered MCMC
• What graph neural networks cannot learn: depth vs width
• Fast Dynamic 1D Simulation of Divertor Plasmas with Neural PDE Surrogates
• Graph Random Neural Network for Semi-Supervised Learning on Graphs
• State Estimation in Electric Power Systems Leveraging Graph Neural Networks
• GNN-Geo: A Graph Neural Network-based Fine-grained IP geolocation Framework
• Transfer-Learned Potential Energy Surfaces: Towards Microsecond-Scale Molecular Dynamics Simulations in the Gas Phase at CCSD(T) Quality
• KG^2: Learning to Reason Science Exam Questions with Contextual Knowledge Graph Embeddings
• Graph Neural Networks in Computer Vision -- Architectures, Datasets and Common Approaches
• Improving Graph Neural Network Representations of Logical Formulae with Subgraph Pooling
• Streaming Graph Neural Networks
• Understanding Human Gaze Communication by Spatio-Temporal Graph Reasoning
• A Technique for Determining Relevance Scores of Process Activities using Graph-based Neural Networks
• DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs
• GraphFlow: Exploiting Conversation Flow with Graph Neural Networks for Conversational Machine Comprehension
• Hierarchical stochastic graphlet embedding for graph-based pattern recognition
• Optimal Transport Graph Neural Networks
• Tripartite Heterogeneous Graph Propagation for Large-scale Social Recommendation
• Automated Relational Meta-learning
• Cell Attention Networks
• Temporal Knowledge Graph Forecasting with Neural ODE
• Adversarial Attack on Hierarchical Graph Pooling Neural Networks
• Shift-Robust GNNs: Overcoming the Limitations of Localized Graph Training Data
• Accelerating Training and Inference of Graph Neural Networks with Fast Sampling and Pipelining
• Probabilistic Dual Network Architecture Search on Graphs
• Automated Self-Supervised Learning for Graphs
• The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning
• Exploratory Combinatorial Optimization with Reinforcement Learning
• Graph Neural Networks with Diverse Spectral Filtering
• Building powerful and equivariant graph neural networks with structural message-passing
• Graph Element Networks: adaptive, structured computation and memory
• Data efficiency and extrapolation trends in neural network interatomic potentials
• Graph Geometry Interaction Learning
• Towards a Unified Framework for Fair and Stable Graph Representation Learning
• Distilling Knowledge from Graph Convolutional Networks
• Decimated Framelet System on Graphs and Fast G-Framelet Transforms
• Combining Machine Learning and Physics to Understand Glassy Systems
• Meta-Learning GNN Initializations for Low-Resource Molecular Property Prediction
• Degree-Quant: Quantization-Aware Training for Graph Neural Networks
• Inclusion of Domain-Knowledge into GNNs using Mode-Directed Inverse Entailment
• An Introduction to Electrocatalyst Design using Machine Learning for Renewable Energy Storage
• Automatic Symmetry Discovery with Lie Algebra Convolutional Network
• Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks
• Scalable and Adaptive Graph Neural Networks with Self-Label-Enhanced training
• Hyperbolic Geometric Graph Representation Learning for Hierarchy-imbalance Node Classification
• Tackling the Challenges in Scene Graph Generation with Local-to-Global Interactions
• Mucko: Multi-Layer Cross-Modal Knowledge Reasoning for Fact-based Visual Question Answering
• Solving NP-Hard Problems on Graphs with Extended AlphaGo Zero
• Learning Domain-Independent Planning Heuristics with Hypergraph Networks
• Temporal Aggregation and Propagation Graph Neural Networks for Dynamic Representation
• An End-to-End Framework for Molecular Conformation Generation via Bilevel Programming
• Strong Generalization and Efficiency in Neural Programs
• Projective Ranking-based GNN Evasion Attacks
• Search to Capture Long-range Dependency with Stacking GNNs for Graph Classification
• Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks
• GripNet: Graph Information Propagation on Supergraph for Heterogeneous Graphs
• Unsupervised Inductive Graph-Level Representation Learning via Graph-Graph Proximity
• Stress and heat flux via automatic differentiation
• NRGNN: Learning a Label Noise-Resistant Graph Neural Network on Sparsely and Noisily Labeled Graphs
• Pointer Graph Networks
• Improved Constraints on Effective Top Quark Interactions using Edge Convolution Networks
• Beyond Graph Neural Networks with Lifted Relational Neural Networks
• Edge Representation Learning with Hypergraphs
• PeerNets: Exploiting Peer Wisdom Against Adversarial Attacks
• Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation
• A Survey on Graph Neural Networks for Knowledge Graph Completion
• Pre-training of Graph Augmented Transformers for Medication Recommendation
• PDE-GCN: Novel Architectures for Graph Neural Networks Motivated by Partial Differential Equations
• Explaining Deep Graph Networks with Molecular Counterfactuals
• Provably Powerful Graph Networks
• Utilizing Edge Features in Graph Neural Networks via Variational Information Maximization
• Improving Graph Neural Networks with Simple Architecture Design
• Graph Generative Adversarial Networks for Sparse Data Generation in High Energy Physics
• PAN: Path Integral Based Convolution for Deep Graph Neural Networks
• Neural message passing for joint paratope-epitope prediction
• How hard is to distinguish graphs with graph neural networks?
• Pre-training Graph Neural Networks with Kernels
• End-to-End Entity Classification on Multimodal Knowledge Graphs
• Learned Low Precision Graph Neural Networks
• Differentiable graph-structured models for inverse design of lattice materials
• Structure fusion based on graph convolutional networks for semi-supervised classification
• Prediction of Large Magnetic Moment Materials With Graph Neural Networks and Random Forests
• Set2Graph: Learning Graphs From Sets
• Approximation Ratios of Graph Neural Networks for Combinatorial Problems
• What the foundations of quantum computer science teach us about chemistry
• Graph Nets for Partial Charge Prediction
• Be More with Less: Hypergraph Attention Networks for Inductive Text Classification
• RetroGNN: Approximating Retrosynthesis by Graph Neural Networks for De Novo Drug Design
• Spatial Aggregation and Temporal Convolution Networks for Real-time Kriging
• Energy-based View of Retrosynthesis
• Goal-directed graph construction using reinforcement learning
• Named Entity Disambiguation using Deep Learning on Graphs
• Graph Neural Networks with Local Graph Parameters
• Graph Neural Networks for IceCube Signal Classification
• Wavelet Scattering Networks for Atomistic Systems with Extrapolation of Material Properties
• BatmanNet: Bi-branch Masked Graph Transformer Autoencoder for Molecular Representation
• Incomplete Graph Representation and Learning via Partial Graph Neural Networks
• Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting
• Reliable Graph Neural Networks for Drug Discovery Under Distributional Shift
• Evaluating Logical Generalization in Graph Neural Networks
• Recurrent Relational Networks
• Graph Warp Module: an Auxiliary Module for Boosting the Power of Graph Neural Networks in Molecular Graph Analysis
• Step Change Improvement in ADMET Prediction with PotentialNet Deep Featurization
• RAGO: Recurrent Graph Optimizer For Multiple Rotation Averaging
• Unsupervised Graph Outlier Detection: Problem Revisit, New Insight, and Superior Method
• HGKT: Introducing Hierarchical Exercise Graph for Knowledge Tracing
• Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Properties
• On the Universality of Invariant Networks
• Graph Neural Network for Interpreting Task-fMRI Biomarkers
• Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem
• Large-scale graph representation learning with very deep GNNs and self-supervision
• Balancing Multi-level Interactions for Session-based Recommendation
• Model Extraction Attacks on Graph Neural Networks: Taxonomy and Realization
• Variational Autoencoder for Anti-Cancer Drug Response Prediction
• A Graph Isomorphism Network with Weighted Multiple Aggregators for Speech Emotion Recognition
• Making Graph Neural Networks Worth It for Low-Data Molecular Machine Learning
• Say No to the Discrimination: Learning Fair Graph Neural Networks with Limited Sensitive Attribute Information
• Learning Intra-Batch Connections for Deep Metric Learning
• Equivariant Subgraph Aggregation Networks
• Parameterized Hypercomplex Graph Neural Networks for Graph Classification
• Node Similarity Preserving Graph Convolutional Networks
• Sampling methods for efficient training of graph convolutional networks: A survey
• Energy-based models for atomic-resolution protein conformations
• Multiresolution Graph Transformers and Wavelet Positional Encoding for Learning Hierarchical Structures
• Discrete-Valued Neural Communication
• Geometric and Physical Quantities Improve E(3) Equivariant Message Passing
• Let's Agree to Degree: Comparing Graph Convolutional Networks in the Message-Passing Framework
• Factor Graph Neural Network
• Multitask Learning on Graph Neural Networks: Learning Multiple Graph Centrality Measures with a Unified Network
• Hierarchical Fashion Graph Network for Personalized Outfit Recommendation
• Training Robust Graph Neural Networks with Topology Adaptive Edge Dropping
• Speaker attribution with voice profiles by graph-based semi-supervised learning
• Supervised Learning on Relational Databases with Graph Neural Networks
• A Deep Reinforcement Learning Algorithm Using Dynamic Attention Model for Vehicle Routing Problems
• Machine learning and invariant theory
• PIC: Permutation Invariant Critic for Multi-Agent Deep Reinforcement Learning
• Text Level Graph Neural Network for Text Classification
• Optimizing Task Placement and Online Scheduling for Distributed GNN Training Acceleration
• Relation-based Motion Prediction using Traffic Scene Graphs
• Distinguish Confusing Law Articles for Legal Judgment Prediction
• Discriminative structural graph classification
• On Graph Classification Networks, Datasets and Baselines
• Tri-graph Information Propagation for Polypharmacy Side Effect Prediction
• Jointly Cross- and Self-Modal Graph Attention Network for Query-Based Moment Localization
• Dirichlet Graph Variational Autoencoder
• Ego-GNNs: Exploiting Ego Structures in Graph Neural Networks
• AGMI: Attention-Guided Multi-omics Integration for Drug Response Prediction with Graph Neural Networks
• LineMVGNN: Anti-Money Laundering with Line-Graph-Assisted Multi-View Graph Neural Networks
• On the data-driven description of lattice materials mechanics
• Structural Inference of Networked Dynamical Systems with Universal Differential Equations
• Adversarially Regularized Graph Attention Networks for Inductive Learning on Partially Labeled Graphs
• Graph Generative Models for Fast Detector Simulations in High Energy Physics
• Contrastive Graph Neural Network Explanation
• Using Graph Neural Networks for Mass Spectrometry Prediction
• A Tailored Convolutional Neural Network for Nonlinear Manifold Learning of Computational Physics Data using Unstructured Spatial Discretizations
• Graph Meta Learning via Local Subgraphs
• Global Attention Improves Graph Networks Generalization
• Memory-Based Graph Networks
• Neural Graph Embedding Methods for Natural Language Processing
• Dynamically Pruned Message Passing Networks for Large-Scale Knowledge Graph Reasoning
• STMARL: A Spatio-Temporal Multi-Agent Reinforcement Learning Approach for Cooperative Traffic Light Control
• Towards Interpretable Sparse Graph Representation Learning with Laplacian Pooling
• edGNN: a Simple and Powerful GNN for Directed Labeled Graphs
• Online Planner Selection with Graph Neural Networks and Adaptive Scheduling
• Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
• Propagation Networks for Model-Based Control Under Partial Observation
• Enhancing Drug-Drug Interaction Extraction from Texts by Molecular Structure Information
• A Variational-Sequential Graph Autoencoder for Neural Architecture Performance Prediction
• IsoNN: Isomorphic Neural Network for Graph Representation Learning and Classification
• Superpixels and Graph Convolutional Neural Networks for Efficient Detection of Nutrient Deficiency Stress from Aerial Imagery
• Discovering Molecular Functional Groups Using Graph Convolutional Neural Networks
• DiffGCN: Graph Convolutional Networks via Differential Operators and Algebraic Multigrid Pooling
• Finite-difference-informed graph network for solving steady-state incompressible flows on block-structured grids
• On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
• Frame Averaging for Invariant and Equivariant Network Design
• Using Graph Neural Networks and Frequency Domain Data for Automated Operational Modal Analysis of Populations of Structures
• Learning Universal Graph Neural Network Embeddings With Aid Of Transfer Learning
• Graph Neural Network Based Surrogate Model of Physics Simulations for Geometry Design
• Efficient force field and energy emulation through partition of permutationally equivalent atoms
• On the Equivalence Between Temporal and Static Graph Representations for Observational Predictions
• Combining Graph Neural Networks and Spatio-temporal Disease Models to Predict COVID-19 Cases in Germany
• Directional Graph Networks
• Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequences
• Iterative Graph Self-Distillation
• Principled Hyperedge Prediction with Structural Spectral Features and Neural Networks
• Towards Heterogeneous Multi-Agent Reinforcement Learning with Graph Neural Networks
• Optimizing ZX-Diagrams with Deep Reinforcement Learning
• Improving Compound Activity Classification via Deep Transfer and Representation Learning
• VersaGNN: a Versatile accelerator for Graph neural networks
• Generalizing Graph Neural Networks on Out-Of-Distribution Graphs
• Size-Invariant Graph Representations for Graph Classification Extrapolations
• How Framelets Enhance Graph Neural Networks
• Popularity Prediction on Social Platforms with Coupled Graph Neural Networks
• Grounded Relational Inference: Domain Knowledge Driven Explainable Autonomous Driving
• Graph Convolution for Semi-Supervised Classification: Improved Linear Separability and Out-of-Distribution Generalization
• Gated Graph Recursive Neural Networks for Molecular Property Prediction
• MGN-Net: a multi-view graph normalizer for integrating heterogeneous biological network populations
• Learning to Represent Programs with Heterogeneous Graphs
• A Generative Model for Molecular Distance Geometry
• You are AllSet: A Multiset Function Framework for Hypergraph Neural Networks
• Robust Line Segments Matching via Graph Convolution Networks
• From Local Structures to Size Generalization in Graph Neural Networks
• A Neural Network-based SAT-Resilient Obfuscation Towards Enhanced Logic Locking
• High-quality Task Division for Large-scale Entity Alignment
• Hierarchical Human Parsing with Typed Part-Relation Reasoning
• Finding Heterophilic Neighbors via Confidence-based Subgraph Matching for Semi-supervised Node Classification
• Stochastic Optimization of Areas Under Precision-Recall Curves with Provable Convergence
• Pileup mitigation at the Large Hadron Collider with Graph Neural Networks
• Iterative charge equilibration for fourth-generation high-dimensional neural network potentials
• OptTyper: Probabilistic Type Inference by Optimising Logical and Natural Constraints
• Detecting Beneficial Feature Interactions for Recommender Systems
• Search for light long-lived particles decaying to displaced jets in proton-proton collisions at $\sqrt{s}$ = 13.6 TeV
• EnGN: A High-Throughput and Energy-Efficient Accelerator for Large Graph Neural Networks
• Graph Neural Network Guided Local Search for the Traveling Salesperson Problem
• Learning Graph-Level Representations with Recurrent Neural Networks
• Improving Generative Imagination in Object-Centric World Models
• Barking up the right tree: an approach to search over molecule synthesis DAGs
• Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
• Contextual Heterogeneous Graph Network for Human-Object Interaction Detection
• Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection
• The Impact of Global Structural Information in Graph Neural Networks Applications
• GENN: Predicting Correlated Drug-drug Interactions with Graph Energy Neural Networks
• Learning the Geodesic Embedding with Graph Neural Networks
• Grouping-matrix based Graph Pooling with Adaptive Number of Clusters
• Information Obfuscation of Graph Neural Networks
• Artificial Intelligence in Drug Discovery: Applications and Techniques
• Constant Time Graph Neural Networks
• Unveiling the hidden reaction kinetic network of carbon dioxide in supercritical aqueous solutions
• Orders-of-magnitude speedup in atmospheric chemistry modeling through neural network-based emulation
• Molecule Property Prediction and Classification with Graph Hypernetworks
• MathNet: Haar-Like Wavelet Multiresolution-Analysis for Graph Representation and Learning
• Efficient Robustness Certificates for Discrete Data: Sparsity-Aware Randomized Smoothing for Graphs, Images and More
• Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT
• Enforcing Predictive Invariance across Structured Biomedical Domains
• Peptide-Spectra Matching from Weak Supervision
• Field-level simulation-based inference with galaxy catalogs: the impact of systematic effects
• Learning and Interpreting Multi-Multi-Instance Learning Networks
• PREDATOR: Registration of 3D Point Clouds with Low Overlap
• Backpropagation through nonlinear units for all-optical training of neural networks
• SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
• Learning continuous-time PDEs from sparse data with graph neural networks
• Relational Graph Learning on Visual and Kinematics Embeddings for Accurate Gesture Recognition in Robotic Surgery
• Network In Graph Neural Network
• Neural Bipartite Matching
• Graph2Seq: Scalable Learning Dynamics for Graphs
• Self-supervised edge features for improved Graph Neural Network training
• Simplifying Clustering with Graph Neural Networks
• Learning Diverse Fashion Collocation by Neural Graph Filtering
• Small-footprint Keyword Spotting with Graph Convolutional Network
• A Hierarchy of Graph Neural Networks Based on Learnable Local Features
• Learning Representations of Missing Data for Predicting Patient Outcomes
• Network Calculus with Flow Prolongation -- A Feedforward FIFO Analysis enabled by ML
• FLEE-GNN: A Federated Learning System for Edge-Enhanced Graph Neural Network in Analyzing Geospatial Resilience of Multicommodity Food Flows
• SDGNN: Learning Node Representation for Signed Directed Networks
• On the Representation of Solutions to Elliptic PDEs in Barron Spaces
• Training Matters: Unlocking Potentials of Deeper Graph Convolutional Neural Networks
• HyperSAGE: Generalizing Inductive Representation Learning on Hypergraphs
• MEMO: A Deep Network for Flexible Combination of Episodic Memories
• MolDesigner: Interactive Design of Efficacious Drugs with Deep Learning
• Towards Deepening Graph Neural Networks: A GNTK-based Optimization Perspective
• Are Graph Neural Networks Miscalibrated?
• Simplifying Architecture Search for Graph Neural Network
• PEMP: Leveraging Physics Properties to Enhance Molecular Property Prediction
• Graph neural induction of value iteration
• Bipartite Graph Embedding via Mutual Information Maximization
• LT-OCF: Learnable-Time ODE-based Collaborative Filtering
• Utilising Graph Machine Learning within Drug Discovery and Development
• SceneGraphNet: Neural Message Passing for 3D Indoor Scene Augmentation
• Generating Logical Forms from Graph Representations of Text and Entities
• HamNet: Conformation-Guided Molecular Representation with Hamiltonian Neural Networks
• Molecule3D: A Benchmark for Predicting 3D Geometries from Molecular Graphs
• Counting Substructures with Higher-Order Graph Neural Networks: Possibility and Impossibility Results
• Particle Cloud Generation with Message Passing Generative Adversarial Networks
• XLVIN: eXecuted Latent Value Iteration Nets
• Graph Signal Processing -- Part III: Machine Learning on Graphs, from Graph Topology to Applications
• Entropy-Transport distances between unbalanced metric measure spaces
• Convolutional Geometric Matrix Completion
• Learning Robot Structure and Motion Embeddings using Graph Neural Networks
• Parallel Extraction of Long-term Trends and Short-term Fluctuation Framework for Multivariate Time Series Forecasting
• Graph Neural Networks for Learning Robot Team Coordination
• LGD-GCN: Local and Global Disentangled Graph Convolutional Networks
• GN-Transformer: Fusing Sequence and Graph Representation for Improved Code Summarization
• Weisfeiler and Lehman Go Paths: Learning Topological Features via Path Complexes
• Learning Domain-Independent Heuristics for Grounded and Lifted Planning
• Trial by FIRE: Probing the dark matter density profile of dwarf galaxies with GraphNPE
• Revisiting Random Forests in a Comparative Evaluation of Graph Convolutional Neural Network Variants for Traffic Prediction
• Modeling Attention Flow on Graphs
• Relational Message Passing for Knowledge Graph Completion
• Understanding Graph Isomorphism Network for rs-fMRI Functional Connectivity Analysis
• Topology Aware Deep Learning for Wireless Network Optimization
• Unified Robust Training for Graph NeuralNetworks against Label Noise
• Multi-task Learning over Graph Structures
• Conditional Directed Graph Convolution for 3D Human Pose Estimation
• EvoNet: A Neural Network for Predicting the Evolution of Dynamic Graphs
• Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks
• Graph Few-shot Learning via Knowledge Transfer
• Message-Passing Monte Carlo: Generating low-discrepancy point sets via Graph Neural Networks
• Attentional Multilabel Learning over Graphs: A Message Passing Approach
• SENSORIMOTOR GRAPH: Action-Conditioned Graph Neural Network for Learning Robotic Soft Hand Dynamics
• GraphTheta: A Distributed Graph Neural Network Learning System With Flexible Training Strategy
• Graph Convolution with Low-rank Learnable Local Filters
• From Shallow to Deep Interactions Between Knowledge Representation, Reasoning and Machine Learning (Kay R. Amel group)
• Probabilistic Generative Deep Learning for Molecular Design
• Why Propagate Alone? Parallel Use of Labels and Features on Graphs
• Natural Language QA Approaches using Reasoning with External Knowledge
• Graph Homomorphism Convolution
• Metapath- and Entity-aware Graph Neural Network for Recommendation
• Grammars and reinforcement learning for molecule optimization
• DeepGG: a Deep Graph Generator
• Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
• Graph-Based Multi-Camera Soccer Player Tracker
• Communication-Efficient Sampling for Distributed Training of Graph Convolutional Networks
• An Overview on the Application of Graph Neural Networks in Wireless Networks
• Adversarial Graph Disentanglement
• Graph convolutions that can finally model local structure
• Semi-Supervised Learning on Graphs Based on Local Label Distributions
• Black-box Attacks Against Neural Binary Function Detection
• Fast Quantum Property Prediction via Deeper 2D and 3D Graph Networks
• The expressive power of kth-order invariant graph networks
• Node2Seq: Towards Trainable Convolutions in Graph Neural Networks
• A Hyperbolic-to-Hyperbolic Graph Convolutional Network
• A game-theoretic analysis of networked system control for common-pool resource management using multi-agent reinforcement learning
• Optimization and Generalization Analysis of Transduction through Gradient Boosting and Application to Multi-scale Graph Neural Networks
• Weisfeiler and Lehman Go Cellular: CW Networks
• Quaternion Graph Neural Networks
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• Edge Proposal Sets for Link Prediction
• Attention-Based Learning on Molecular Ensembles
• MxPool: Multiplex Pooling for Hierarchical Graph Representation Learning
• Demand Forecasting from Spatiotemporal Data with Graph Networks and Temporal-Guided Embedding
• PhysGNN: A Physics-Driven Graph Neural Network Based Model for Predicting Soft Tissue Deformation in Image-Guided Neurosurgery
• On the equivalence of molecular graph convolution and molecular wave function with poor basis set
• Conv-MPN: Convolutional Message Passing Neural Network for Structured Outdoor Architecture Reconstruction
• Accurately Solving Physical Systems with Graph Learning
• Graph Polish: A Novel Graph Generation Paradigm for Molecular Optimization
• Complete Neural Networks for Complete Euclidean Graphs
• Physics-inspired spatiotemporal-graph AI ensemble for the detection of higher order wave mode signals of spinning binary black hole mergers
• Lane Attention: Predicting Vehicles' Moving Trajectories by Learning Their Attention over Lanes
• Lymph Node Gross Tumor Volume Detection in Oncology Imaging via Relationship Learning Using Graph Neural Network
• Learning Graph Structure With A Finite-State Automaton Layer
• Tree Structure-Aware Graph Representation Learning via Integrated Hierarchical Aggregation and Relational Metric Learning
• Next Waves in Veridical Network Embedding
• SB-MTL: Score-based Meta Transfer-Learning for Cross-Domain Few-Shot Learning
• CoSimGNN: Towards Large-scale Graph Similarity Computation
• Generalization of Neural Combinatorial Solvers Through the Lens of Adversarial Robustness
• Reconstruction for Powerful Graph Representations
• Certified Robustness of Graph Neural Networks against Adversarial Structural Perturbation
• Free energy profiles for chemical reactions in solution from high-dimensional neural network potentials: The case of the Strecker synthesis
• Neural Status Registers
• Molecular Dynamics and Machine Learning Unlock Possibilities in Beauty Design -- A Perspective
• Highly Accurate Disease Diagnosis and Highly Reproducible Biomarker Identification with PathFormer
• A Dynamic Reduction Network for Point Clouds
• A comprehensive study on the prediction reliability of graph neural networks for virtual screening
• An Experimental Study of Formula Embeddings for Automated Theorem Proving in First-Order Logic
• Collaborative Motion Prediction via Neural Motion Message Passing
• Learning Graph Neural Networks using Exact Compression
• DPPIN: A Biological Repository of Dynamic Protein-Protein Interaction Network Data
• Molecular distance matrix prediction based on graph convolutional networks
• Teaching Temporal Logics to Neural Networks
• Exploiting Heterogeneous Graph Neural Networks with Latent Worker/Task Correlation Information for Label Aggregation in Crowdsourcing
• PushNet: Efficient and Adaptive Neural Message Passing
• The general theory of permutation equivarant neural networks and higher order graph variational encoders
• Graph Sequential Network for Reasoning over Sequences
• Improving Molecular Design by Stochastic Iterative Target Augmentation
• Node Classification Meets Link Prediction on Knowledge Graphs
• Feature Interaction-aware Graph Neural Networks
• Investigating 3D Atomic Environments for Enhanced QSAR
• Graph Cross Networks with Vertex Infomax Pooling
• Atomistic Graph Neural Networks for metals: Application to bcc iron
• Sampling and Recovery of Graph Signals based on Graph Neural Networks
• A Geometric Perspective on Visual Imitation Learning
• Equivariant Entity-Relationship Networks
• Maximum Entropy Weighted Independent Set Pooling for Graph Neural Networks
• Improving Federated Relational Data Modeling via Basis Alignment and Weight Penalty
• Data-Driven Short-Term Voltage Stability Assessment Based on Spatial-Temporal Graph Convolutional Network
• Lipophilicity Prediction with Multitask Learning and Molecular Substructures Representation
• Train on Small, Play the Large: Scaling Up Board Games with AlphaZero and GNN
• A Study of Joint Graph Inference and Forecasting
• Improving COVID-19 Forecasting using eXogenous Variables
• Ab initio machine learning in chemical compound space
• Ego-based Entropy Measures for Structural Representations
• From Gameplay to Symbolic Reasoning: Learning SAT Solver Heuristics in the Style of Alpha(Go) Zero
• Finding spin glass ground states through deep reinforcement learning
• Enhance Information Propagation for Graph Neural Network by Heterogeneous Aggregations
• MLSolv-A: A Novel Machine Learning-Based Prediction of Solvation Free Energies from Pairwise Atomistic Interactions
• Continuous Graph Flow
• Discrete Object Generation with Reversible Inductive Construction
• Deep Policies for Online Bipartite Matching: A Reinforcement Learning Approach
• Modern Hopfield Networks for Few- and Zero-Shot Reaction Template Prediction
• Visual Semantic Information Pursuit: A Survey
• Node-Level Differentially Private Graph Neural Networks
• Walk Message Passing Neural Networks and Second-Order Graph Neural Networks
• Hallucinating Optical Flow Features for Video Classification
• Transfer Learned Potential Energy Surfaces: Accurate Anharmonic Vibrational Dynamics and Dissociation Energies for the Formic Acid Monomer and Dimer
• Accurate Prediction of Free Solvation Energy of Organic Molecules via Graph Attention Network and Message Passing Neural Network from Pairwise Atomistic Interactions
• Isometric Transformation Invariant and Equivariant Graph Convolutional Networks
• Exploiting Contextual Information with Deep Neural Networks
• Lossless Compression of Structured Convolutional Models via Lifting
• MPLP: Learning a Message Passing Learning Protocol
• Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction
• Calendar Graph Neural Networks for Modeling Time Structures in Spatiotemporal User Behaviors
• Cluster Counting Algorithm for the CEPC Drift Chamber using LSTM and DGCNN
• Graph Neural Networks for Image Understanding Based on Multiple Cues: Group Emotion Recognition and Event Recognition as Use Cases
• ZIPPER: Exploiting Tile- and Operator-level Parallelism for General and Scalable Graph Neural Network Acceleration
• Optimization-Based Algebraic Multigrid Coarsening Using Reinforcement Learning
• Graph Information Bottleneck for Subgraph Recognition
• Graph Attentional Autoencoder for Anticancer Hyperfood Prediction
• Simulating Continuum Mechanics with Multi-Scale Graph Neural Networks
• Learning Depthwise Separable Graph Convolution from Data Manifold
• Graph Inference Representation: Learning Graph Positional Embeddings with Anchor Path Encoding
• An In-depth Summary of Recent Artificial Intelligence Applications in Drug Design
• TransCamP: Graph Transformer for 6-DoF Camera Pose Estimation
• Learning distributed representations of graphs with Geo2DR
• The Atlas for the Aspiring Network Scientist
• XInsight: Revealing Model Insights for GNNs with Flow-based Explanations
• Breaking the Expressive Bottlenecks of Graph Neural Networks
• Discovering Dynamic Salient Regions for Spatio-Temporal Graph Neural Networks
• Persistent Message Passing
• Physics-Constrained Predictive Molecular Latent Space Discovery with Graph Scattering Variational Autoencoder
• Scaffold Embeddings: Learning the Structure Spanned by Chemical Fragments, Scaffolds and Compounds
• Permutation-Invariant Variational Autoencoder for Graph-Level Representation Learning
• Edgeless-GNN: Unsupervised Representation Learning for Edgeless Nodes
• Neuralizing Efficient Higher-order Belief Propagation
• Deep Generative Modeling in Network Science with Applications to Public Policy Research
• Locality Preserving Dense Graph Convolutional Networks with Graph Context-Aware Node Representations
• Data-Driven Learning of Geometric Scattering Networks
• GeoT: A Geometry-aware Transformer for Reliable Molecular Property Prediction and Chemically Interpretable Representation Learning
• GraphITE: Estimating Individual Effects of Graph-structured Treatments
• Zero-shot Synthesis with Group-Supervised Learning
• Graph Neural Networks with Feature and Structure Aware Random Walk
• A Graph Deep Learning Framework for High-Level Synthesis Design Space Exploration
• Aiding Medical Diagnosis Through the Application of Graph Neural Networks to Functional MRI Scans
• gSuite: A Flexible and Framework Independent Benchmark Suite for Graph Neural Network Inference on GPUs
• PACIA: Parameter-Efficient Adapter for Few-Shot Molecular Property Prediction
• Local Off-Grid Weather Forecasting with Multi-Modal Earth Observation Data
• Learning physics confers pose-sensitivity in structure-based virtual screening
• Graph4Rec: A Universal Toolkit with Graph Neural Networks for Recommender Systems
• Flexible dual-branched message passing neural network for quantum mechanical property prediction with molecular conformation
• Unsupervised Resource Allocation with Graph Neural Networks
• Hybrid graph convolutional neural networks for landmark-based anatomical segmentation
• Message Passing in Graph Convolution Networks via Adaptive Filter Banks
• Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
• Reliable Graph Neural Network Explanations Through Adversarial Training
• Quantum evolution kernel : Machine learning on graphs with programmable arrays of qubits
• Deep Weisfeiler-Lehman Assignment Kernels via Multiple Kernel Learning
• Hybrid Low-order and Higher-order Graph Convolutional Networks
• A Framework for Joint Unsupervised Learning of Cluster-Aware Embedding for Heterogeneous Networks
• Progressive Relation Learning for Group Activity Recognition
• SMILES-X: autonomous molecular compounds characterization for small datasets without descriptors
• Adaptive Neural Message Passing for Inductive Learning on Hypergraphs
• Learning Predicates as Functions to Enable Few-shot Scene Graph Prediction
• Signed Graph Attention Networks
• Prediction of Carbon Nanostructure Mechanical Properties and Role of Defects Using Machine Learning
• Time-Series Event Prediction with Evolutionary State Graph
• Deep Data Flow Analysis
• Using ontology embeddings for structural inductive bias in gene expression data analysis
• Cyclic Label Propagation for Graph Semi-supervised Learning
• Process-Level Representation of Scientific Protocols with Interactive Annotation
• Drug Package Recommendation via Interaction-aware Graph Induction
• Graph Traversal with Tensor Functionals: A Meta-Algorithm for Scalable Learning
• Should Graph Neural Networks Use Features, Edges, Or Both?
• Image-Level Attentional Context Modeling Using Nested-Graph Neural Networks
• Deep learning of material transport in complex neurite networks
• Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning
• Quadratic GCN for Graph Classification
• Scan2Mesh: From Unstructured Range Scans to 3D Meshes
• Histopathology WSI Encoding based on GCNs for Scalable and Efficient Retrieval of Diagnostically Relevant Regions
• Geometrically Principled Connections in Graph Neural Networks
• Weisfeiler-Lehman Embedding for Molecular Graph Neural Networks
• Message Passing Graph Kernels
• Fast and Accurate: Structure Coherence Component for Face Alignment
• Graph2Kernel Grid-LSTM: A Multi-Cued Model for Pedestrian Trajectory Prediction by Learning Adaptive Neighborhoods
• Robust Hierarchical Graph Classification with Subgraph Attention
• Classifying the Cosmic-Ray Proton and Light Groups on the LHAASO-KM2A Experiment with the Graph Neural Network
• CoulGAT: An Experiment on Interpretability of Graph Attention Networks
• Relational State-Space Model for Stochastic Multi-Object Systems
• Reversible Action Design for Combinatorial Optimization with Reinforcement Learning
• Snowflake: Scaling GNNs to High-Dimensional Continuous Control via Parameter Freezing
• Symmetry-adapted graph neural networks for constructing molecular dynamics force fields
• Region-based Energy Neural Network for Approximate Inference
• Maximizing Mutual Information Across Feature and Topology Views for Learning Graph Representations
• Sparse hierarchical representation learning on molecular graphs
• Deep Dynamic Effective Connectivity Estimation from Multivariate Time Series
• Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels
• Spectral Network Embedding: A Fast and Scalable Method via Sparsity
• Minimally-Supervised Structure-Rich Text Categorization via Learning on Text-Rich Networks
• Personalized Hashtag Recommendation for Micro-videos
• On the Universality of Graph Neural Networks on Large Random Graphs
• Zero-Shot Scene Graph Relation Prediction through Commonsense Knowledge Integration
• Which Hyperparameters to Optimise? An Investigation of Evolutionary Hyperparameter Optimisation in Graph Neural Network For Molecular Property Prediction
• Neural Circuit Synthesis from Specification Patterns
• Multi-Level Attention Pooling for Graph Neural Networks: Unifying Graph Representations with Multiple Localities
• Improving the Long-Range Performance of Gated Graph Neural Networks
• TreeRNN: Topology-Preserving Deep GraphEmbedding and Learning
• Lorentzian Graph Convolutional Networks
• Semi-Supervised Graph Embedding for Multi-Label Graph Node Classification
• On Graph Neural Network Ensembles for Large-Scale Molecular Property Prediction
• struc2gauss: Structural Role Preserving Network Embedding via Gaussian Embedding
• Predicting Material Properties Using a 3D Graph Neural Network with Invariant Local Descriptors
• Adversarially-learned Inference via an Ensemble of Discrete Undirected Graphical Models
• PanRep: Graph neural networks for extracting universal node embeddings in heterogeneous graphs
• Neural Enhanced Belief Propagation for Cooperative Localization
• Framework for Designing Filters of Spectral Graph Convolutional Neural Networks in the Context of Regularization Theory
• NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
• Beyond permutation equivariance in graph networks
• HOPF: Higher Order Propagation Framework for Deep Collective Classification
• Unsupervised Hierarchical Graph Representation Learning by Mutual Information Maximization
• Graph Analysis and Graph Pooling in the Spatial Domain
• Automatic Text Extractive Summarization Based on Graph and Pre-trained Language Model Attention
• End-to-End Learning from Complex Multigraphs with Latent-Graph Convolutional Networks
• Data-Centric AI Requires Rethinking Data Notion
• Vitruvion: A Generative Model of Parametric CAD Sketches
• GeoGraph: Learning graph-based multi-view object detection with geometric cues end-to-end
• Graph Embedding VAE: A Permutation Invariant Model of Graph Structure
• Reasoning-Modulated Representations
• Node Feature Kernels Increase Graph Convolutional Network Robustness
• InteractionNet: Modeling and Explaining of Noncovalent Protein-Ligand Interactions with Noncovalent Graph Neural Network and Layer-Wise Relevance Propagation
• A Spectral Nonlocal Block for Neural Networks
• Graph-FCN for image semantic segmentation
• Stable Prediction on Graphs with Agnostic Distribution Shift
• Predicting outcomes of catalytic reactions using machine learning
• Partition and Code: learning how to compress graphs
• Graph Filtration Learning
• Optimal message passing for molecular prediction is simple, attentive and spatial
• Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
• A Peek Into the Reasoning of Neural Networks: Interpreting with Structural Visual Concepts
• Ego-CNN: Distributed, Egocentric Representations of Graphs for Detecting Critical Structures
• LiteGEM: Lite Geometry Enhanced Molecular Representation Learning for Quantum Property Prediction
• Graph Denoising with Framelet Regularizer
• Feature Correlation Aggregation: on the Path to Better Graph Neural Networks
• Deep Constraint-based Propagation in Graph Neural Networks
• AI ensemble for signal detection of higher order gravitational wave modes of quasi-circular, spinning, non-precessing binary black hole mergers
• Compositional Language Understanding with Text-based Relational Reasoning
• Relational dynamic memory networks
• Fast OBDD Reordering using Neural Message Passing on Hypergraph
• Neural Trees for Learning on Graphs
• Program-to-Circuit: Exploiting GNNs for Program Representation and Circuit Translation
• Structural Optimization Makes Graph Classification Simpler and Better
• Unsupervised Graph Representation by Periphery and Hierarchical Information Maximization
• Rotation Averaging with Attention Graph Neural Networks
• BayesGrad: Explaining Predictions of Graph Convolutional Networks
• Towards explainable message passing networks for predicting carbon dioxide adsorption in metal-organic frameworks
• Graph-Convolutional Deep Learning to Identify Optimized Molecular Configurations
• Computing Steiner Trees using Graph Neural Networks
• Benchmarking Deep Graph Generative Models for Optimizing New Drug Molecules for COVID-19
• CSAGN: Conversational Structure Aware Graph Network for Conversational Semantic Role Labeling
• An FEA surrogate model with Boundary Oriented Graph Embedding approach
• Graphs for deep learning representations
• Spatial Mixture Models with Learnable Deep Priors for Perceptual Grouping
• Improving Graph Property Prediction with Generalized Readout Functions
• Signed Bipartite Graph Neural Networks
• Neural representation and generation for RNA secondary structures
• Zero Training Overhead Portfolios for Learning to Solve Combinatorial Problems
• SEEN: Sharpening Explanations for Graph Neural Networks using Explanations from Neighborhoods
• Logic and the $2$-Simplicial Transformer
• Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast
• Approximate Knowledge Graph Query Answering: From Ranking to Binary Classification
• STR-GODEs: Spatial-Temporal-Ridership Graph ODEs for Metro Ridership Prediction
• Deep Message Passing on Sets
• A Forecasting System of Computational Time of DFT/TDDFT Calculations under the Multiverse ansatz via Machine Learning and Cheminformatics
• On the Robustness of Deep Learning-predicted Contention Models for Network Calculus
• Analysis of Atomistic Representations Using Weighted Skip-Connections
• Knowledge- and Data-driven Services for Energy Systems using Graph Neural Networks
• OpenGraphGym-MG: Using Reinforcement Learning to Solve Large Graph Optimization Problems on MultiGPU Systems
• Graph Context Encoder: Graph Feature Inpainting for Graph Generation and Self-supervised Pretraining
• Graph Convolutional Memory using Topological Priors
• Detect the Interactions that Matter in Matter: Geometric Attention for Many-Body Systems
• Graph Neural Networks for Inconsistent Cluster Detection in Incremental Entity Resolution
• Mapping the Internet: Modelling Entity Interactions in Complex Heterogeneous Networks
• Graph Feature Gating Networks
• Symmetry-driven graph neural networks
• Docking-based Virtual Screening with Multi-Task Learning
• Equivariant Graph Attention Networks with Structural Motifs for Predicting Cell Line-Specific Synergistic Drug Combinations
• Modeling Pharmacological Effects with Multi-Relation Unsupervised Graph Embedding
• Speaker diarization with session-level speaker embedding refinement using graph neural networks
• Graph Neural Network for Hamiltonian-Based Material Property Prediction
• On the Global Self-attention Mechanism for Graph Convolutional Networks
• SimPool: Towards Topology Based Graph Pooling with Structural Similarity Features
• Evening the Score: Targeting SARS-CoV-2 Protease Inhibition in Graph Generative Models for Therapeutic Candidates
• Improving accuracy of interatomic potentials: more physics or more data? A case study of silica
• Jointly learning relevant subgraph patterns and nonlinear models of their indicators
• Isometric Graph Neural Networks
• Weisfeiler and Leman go Hyperbolic: Learning Distance Preserving Node Representations
• Contributions to Representation Learning with Graph Autoencoders and Applications to Music Recommendation
• Multi-fidelity Stability for Graph Representation Learning
• Rotation Equivariant 3D Hand Mesh Generation from a Single RGB Image
• Convolutions for Spatial Interaction Modeling
• Node Copying for Protection Against Graph Neural Network Topology Attacks
• Inverse Graph Identification: Can We Identify Node Labels Given Graph Labels?
• Network representation learning: A macro and micro view
• Graph-Based Social Relation Reasoning
• Image-Like Graph Representations for Improved Molecular Property Prediction
• Subspace Graph Physics: Real-Time Rigid Body-Driven Granular Flow Simulation
• Spectral Transform Forms Scalable Transformer
• Sequential Aggregation and Rematerialization: Distributed Full-batch Training of Graph Neural Networks on Large Graphs
• Generating Symbolic Reasoning Problems with Transformer GANs
• Barlow Graph Auto-Encoder for Unsupervised Network Embedding
• Learning Atomic Multipoles: Prediction of the Electrostatic Potential with Equivariant Graph Neural Networks
• Irregular Convolutional Auto-Encoder on Point Clouds
• From abstract items to latent spaces to observed data and back: Compositional Variational Auto-Encoder
• ProDyn0: Inferring calponin homology domain stretching behavior using graph neural networks
• PotentialNet for Molecular Property Prediction
• Heterogeneous Graph Neural Network with Multi-view Representation Learning
• RaWaNet: Enriching Graph Neural Network Input via Random Walks on Graphs
• ClueReader: Heterogeneous Graph Attention Network for Multi-hop Machine Reading Comprehension
• A2I Transformer: Permutation-equivariant attention network for pairwise and many-body interactions with minimal featurization
• VACA: Design of Variational Graph Autoencoders for Interventional and Counterfactual Queries
• Equivariant Neural Network for Factor Graphs
• Learning on Random Balls is Sufficient for Estimating (Some) Graph Parameters
• Fast Haar Transforms for Graph Neural Networks
• Stateless actor-critic for instance segmentation with high-level priors
• Estimating Early Fundraising Performance of Innovations via Graph-based Market Environment Model
• Tesla-Rapture: A Lightweight Gesture Recognition System from mmWave Radar Point Clouds
• Sequential Graph Dependency Parser
• Neural PathSim for Inductive Similarity Search in Heterogeneous Information Networks