Neural Message Passing for Quantum Chemistry

2017/04/04 by Justin Gilmer, Gilmer, Justin, Samuel S. Schoenholz +7 · 452 citations
Computer Science · Materials Science · Chemistry · #Computational Drug Discovery Methods #Machine Learning in Materials Science #Various Chemistry Research Topics

paper · pdf · doi:10.48550/arxiv.1704.01212

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.

Cited by

• With Great Context Comes Great Prediction Power: Classifying Objects via Geo-Semantic Scene Graphs
• Debugging Tabular Log as Dynamic Graphs
• BLISS: Bandit Layer Importance Sampling Strategy for Efficient Training of Graph Neural Networks
• Iterative Deep Graph Learning for Graph Neural Networks: Better and Robust Node Embeddings
• Graph Policy Network for Transferable Active Learning on Graphs
• Investigating 3D Atomic Environments for Enhanced QSAR
• How hard is to distinguish graphs with graph neural networks?
• MxPool: Multiplex Pooling for Hierarchical Graph Representation Learning
• MEGA-CL: A Molecular Foundation Model for Generalizable ADMET Prediction through Graph External Attention and Contrastive Learning
• Graph Contrastive Learning with Augmentations
• From Cellular Responses to Pharmacological Domains: Multimodal Zero-Shot Drug Representation Learning
• Beyond Predictive Accuracy: A Reliability-Aware Audit of Molecular Representations for Human Olfaction
• The Atlas for the Aspiring Network Scientist
• SpreadGNN: Serverless Multi-task Federated Learning for Graph Neural Networks
• Graph Neural Networks for Predicting Solvability of Finite Groups
• Deep Generative Spatiotemporal Engression for Probabilistic Forecasting of Epidemics
• PEANUT: Perturbations by Eigenvector Alignment for Attacking Graph Neural Networks Under Topology-Driven Message Passing
• Toward Generalizable Surrogate Models for Molecular Dynamics via Graph Neural Networks
• Revisiting Graph Neural Networks: All We Have is Low-Pass Filters
• From GNNs to Symbolic Surrogates via Kolmogorov-Arnold Networks for Delay Prediction
• Algorithm for Interpretable Graph Features via Motivic Persistent Cohomology
• SHIRO: Near-Optimal Communication Strategies for Distributed Sparse Matrix Multiplication
• A hybrid global local computational framework for ship hull structural analysis using homogenized model and graph neural network
• Learning Continuous Solvent Effects from Transient Flow Data: A Graph Neural Network Benchmark on Catechol Rearrangement
• Specific Multi-emitter Identification: Theoretical Limits and Low-complexity Design
• A Logical View of GNN-Style Computation and the Role of Activation Functions
• Structure-Aware Antibody Design with Affinity-Optimized Inverse Folding
• Can You Hear Me Now? A Benchmark for Long-Range Graph Propagation
• Photonics-Enhanced Graph Convolutional Networks
• Accelerating High-Throughput Catalyst Screening by Direct Generation of Equilibrium Adsorption Structures
• A Roadmap for Applying Graph Neural Networks to Numerical Data: Insights from Cementitious Materials
• Dual-Axis RCCL: Representation-Complete Convergent Learning for Organic Chemical Space
• Parameter-Efficient Transfer Learning for Microseismic Phase Picking Using a Neural Operator
• Theoretically Improving Graph Neural Networks via Anonymous Walk Graph Kernels
• Understanding When Graph Convolutional Networks Help: A Diagnostic Study on Label Scarcity and Structural Properties
• GoMS: Graph of Molecule Substructure Network for Molecule Property Prediction
• Adaptive Neural Message Passing for Inductive Learning on Hypergraphs
• Fully Inductive Node Representation Learning via Graph View Transformation
• Rethinking Graph Transformers with Spectral Attention
• On the Representation of Solutions to Elliptic PDEs in Barron Spaces
• Supervised Learning of Random Neural Architectures Structured by Latent Random Fields on Compact Boundaryless Multiply-Connected Manifolds
• Representation of the structure of graphs by sequences of instructions
• On the Unreasonable Effectiveness of Feature propagation in Learning on Graphs with Missing Node Features
• Predicting Polymer Solubility in Solvents Using SMILES Strings
• Circuits, Features, and Heuristics in Molecular Transformers
• Transport Novelty Distance: A Distributional Metric for Evaluating Material Generative Models
• MolSculpt: Sculpting 3D Molecular Geometries from Chemical Syntax
• Understanding the Failure Modes of Transformers through the Lens of Graph Neural Networks
• TUDataset: A collection of benchmark datasets for learning with graphs
• Mapping Still Matters: Coarse-Graining with Machine Learning Potentials
• Multi-Scale Protein Structure Modelling with Geometric Graph U-Nets
• Self-Supervised Learning on Molecular Graphs: A Systematic Investigation of Masking Design
• Estimating Early Fundraising Performance of Innovations via Graph-based Market Environment Model
• The Graph-Embedded Hazard Model (GEHM): Stochastic Network Survival Dynamics on Economic Graphs
• Hierarchical geometric deep learning enables scalable analysis of molecular dynamics
• Self-supervised Graph-level Representation Learning with Local and Global Structure
• Probabilistic Dynamic Line Rating with Line Graph Convolutional LSTM
• Explainable Graph Representation Learning via Graph Pattern Analysis
• On the Binding Problem in Artificial Neural Networks
• VS-Graph: Scalable and Efficient Graph Classification Using Hyperdimensional Computing
• Representation of Inorganic Synthesis Reactions and Prediction: Graphical Framework and Datasets
• Language-Conditioned Graph Networks for Relational Reasoning
• Domain-Decomposed Graph Neural Network Surrogate Modeling for Ice Sheets
• QGShap: Quantum Acceleration for Faithful GNN Explanations
• Fast End-to-End Speech Recognition via Non-Autoregressive Models and Cross-Modal Knowledge Transferring from BERT
• A Generalization of Transformer Networks to Graphs
• SceneGraphFusion: Incremental 3D Scene Graph Prediction from RGB-D Sequences
• Polynomial Neural Sheaf Diffusion: A Spectral Filtering Approach on Cellular Sheaves
• Beyond Atoms: Evaluating Electron Density Representation for 3D Molecular Learning
• Image-Like Graph Representations for Improved Molecular Property\n Prediction
• Machine-Learned Interatomic Potentials for Structural and Defect Properties of YBa₂Cu₃O_7-δ
• Provably Powerful Graph Networks
• Hopfield Networks is All You Need
• A decoupled alignment kernel for peptide membrane permeability predictions
• Are Graph Transformers Necessary? Efficient Long-Range Message Passing with Fractal Nodes in MPNNs
• Accelerating Materials Discovery: Learning a Universal Representation of Chemical Processes for Cross-Domain Property Prediction
• Finding spin glass ground states through deep reinforcement learning
• On the Generalization of Equivariance and Convolution in Neural Networks to the Action of Compact Groups
• Rethinking Semi-Supervised Node Classification with Self-Supervised Graph Clustering
• Rethinking Message Passing Neural Networks with Diffusion Distance-guided Stress Majorization
• Solar-GECO: Perovskite Solar Cell Property Prediction with Geometric-Aware Co-Attention
• Resolving Node Identifiability in Graph Neural Processes via Laplacian Spectral Encodings
• Adaptive Mesh-Quantization for Neural PDE Solvers
• Developing an AI Course for Synthetic Chemistry Students
• Graph Neural Networks vs Convolutional Neural Networks for Graph Domination Number Prediction
• Lorentzian Graph Convolutional Networks
• N-Gram Graph: Simple Unsupervised Representation for Graphs, with Applications to Molecules
• Maximizing Mutual Information Across Feature and Topology Views for Learning Graph Representations
• Spatial-Temporal Transformer Networks for Traffic Flow Forecasting
• Gauge-Equivariant Graph Networks via Self-Interference Cancellation
• Exploiting Inter-Sample Information for Long-tailed Out-of-Distribution Detection
• WebRec: Enhancing LLM-based Recommendations with Attention-guided RAG from Web
• Complex-Weighted Convolutional Networks: Provable Expressiveness via Complex Diffusion
• Edge-aware baselines for ogbn-proteins in PyTorch Geometric: species-wise normalization, post-hoc calibration, and cost-accuracy trade-offs
• InteractiveGNNExplainer: A Visual Analytics Framework for Multi-Faceted Understanding and Probing of Graph Neural Network Predictions
• Real-time prediction of breast cancer sites using deformation-aware graph neural network
• Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures
• Equivariant Neural Network for Factor Graphs
• What graph neural networks cannot learn: depth vs width
• Rotation Invariant Graph Neural Networks using Spin Convolutions
• Search to aggregate neighborhood for graph neural network
• Scalable learning of macroscopic stochastic dynamics
• LT-OCF: Learnable-Time ODE-based Collaborative Filtering
• Geom-GCN: Geometric Graph Convolutional Networks
• Edge Representation Learning with Hypergraphs
• Barking up the right tree: an approach to search over molecule synthesis DAGs
• Using pretrained graph neural networks with token mixers as geometric featurizers for conformational dynamics
• Simplifying Architecture Search for Graph Neural Network
• Enhancing Graph Representations with Neighborhood-Contextualized Message-Passing
• Socrates-Mol: Self-Oriented Cognitive Reasoning through Autonomous Trial-and-Error with Empirical-Bayesian Screening for Molecules
• Lost in Serialization: Invariance and Generalization of LLM Graph Reasoners
• GraphSB: Boosting Imbalanced Node Classification on Graphs through Structural Balance
• TomoGraphView: 3D Medical Image Classification with Omnidirectional Slice Representations and Graph Neural Networks
• Weaver: Kronecker Product Approximations of Spatiotemporal Attention for Traffic Network Forecasting
• Rethinking Graph Super-resolution: Dual Frameworks for Topological Fidelity
• On topological descriptors for graph products
• Extract the Knowledge of Graph Neural Networks and Go Beyond it: An Effective Knowledge Distillation Framework
• Labeling Trick: A Theory of Using Graph Neural Networks for Multi-Node\n Representation Learning
• Improving Long-Range Interactions in Graph Neural Simulators via Hamiltonian Dynamics
• Stuart-Landau Oscillatory Graph Neural Network
• Generalizable Insights for Graph Transformers in Theory and Practice
• A Circular Argument : Does RoPE need to be Equivariant for Vision?
• Quantum-centric machine learning for molecular dynamics
• CGLE: Class-label Graph Link Estimator for Link Prediction
• Adaptive Initial Residual Connections for GNNs with Theoretical Guarantees
• Magnitude-Modulated Equivariant Adapter for Parameter-Efficient Fine-Tuning of Equivariant Graph Neural Networks
• Large-Scale Representation Learning on Graphs via Bootstrapping
• Reperio-rPPG: Relational Temporal Graph Neural Networks for Periodicity Learning in Remote Physiological Measurement
• Graph Information Bottleneck for Subgraph Recognition
• Quantitative Evaluation of Explainable Graph Neural Networks for Molecular Property Prediction
• GraphCliff: Short-Long Range Gating for Subtle Differences but Critical Changes
• Sketch-Augmented Features Improve Learning Long-Range Dependencies in Graph Neural Networks
• A Transferable Machine Learning Approach to Predict Quantum Circuit Parameters for Electronic Structure Problems
• QAGT-MLP: An Attention-Based Graph Transformer for Small and Large-Scale Quantum Error Mitigation
• Connecting the concepts of quantum state tomography and molecular representations for machine learning
• PrivGNN: High-Performance Secure Inference for Cryptographic Graph Neural Networks
• Design, Assessment, and Application of Machine Learning Potential Energy Surfaces
• G2rammar: Bilingual Grammar Modeling for Enhanced Text-attributed Graph Learning
• PolyRecommender: A Multimodal Recommendation System for Polymer Discovery
• Learning Sparse Approximate Inverse Preconditioners for Conjugate Gradient Solvers on GPUs
• Atomistic Simulations of Oxide-Water Interfaces using Machine Learning Potentials
• On the Dataless Training of Neural Networks
• Fourier Neural Operators for Two-Phase, 2D Mold-Filling Problems Related to Metal Casting
• Graph Network-based Structural Simulator: Graph Neural Networks for Structural Dynamics
• Hypergraph Convolution and Hypergraph Attention
• NeuroBack: Improving CDCL SAT Solving using Graph Neural Networks
• Rethinking pooling in graph neural networks
• Generalizing Graph Neural Networks on Out-Of-Distribution Graphs
• Automatic Symmetry Discovery with Lie Algebra Convolutional Network
• Neural Relational Inference for Interacting Systems
• ForceNet: A Graph Neural Network for Large-Scale Quantum Calculations
• A Primer on Deep Learning for Causal Inference
• Should Graph Neural Networks Use Features, Edges, Or Both?
• Strategies for Pre-training Graph Neural Networks
• Multipole Graph Neural Operator for Parametric Partial Differential Equations
• Ab initio machine learning in chemical compound space
• HyperSAGE: Generalizing Inductive Representation Learning on Hypergraphs
• Group-Wise Semantic Mining for Weakly Supervised Semantic Segmentation
• Open Graph Benchmark: Datasets for Machine Learning on Graphs
• CoulGAT: An Experiment on Interpretability of Graph Attention Networks
• Improving the generalization of protein expression models with mechanistic sequence information
• Pose-GNN : Camera Pose Estimation System Using Graph Neural Networks
• E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials
• Two Sides of the Same Coin: Heterophily and Oversmoothing in Graph Convolutional Neural Networks
• On Explainability of Graph Neural Networks via Subgraph Explorations
• Beyond molecular structure: critically assessing machine learning for designing organic photovoltaic materials and devices
• Relational Graph Learning on Visual and Kinematics Embeddings for Accurate Gesture Recognition in Robotic Surgery
• Spherical Message Passing for 3D Graph Networks
• Sparse Quantum Voxel Encoding for Readout-Efficient Molecular Geometry Reconstruction on NISQ Devices
• Fusion 360 Gallery: A Dataset and Environment for Programmatic CAD Construction from Human Design Sequences
• SketchGraphs: A Large-Scale Dataset for Modeling Relational Geometry in Computer-Aided Design
• Relational Message Passing for Knowledge Graph Completion
• Learning Symbolic Physics with Graph Networks
• Improving the Long-Range Performance of Gated Graph Neural Networks
• Graph neural networks: A review of methods and applications
• Neural Bellman-Ford Networks: A General Graph Neural Network Framework for Link Prediction
• Graph Geometry Interaction Learning
• LGD-GCN: Local and Global Disentangled Graph Convolutional Networks
• Edgeless-GNN: Unsupervised Representation Learning for Edgeless Nodes
• Symbol-Equivariant Recurrent Reasoning Models
• Pre-training Molecular Graph Representation with 3D Geometry
• Spatial Aggregation and Temporal Convolution Networks for Real-time Kriging
• Graph Normalizing Flows
• Next-Gen Therapeutics: Pioneering Drug Discovery with iPSCs, Genomics, AI, and Clinical Trials in a Dish
• Reinforced Neighborhood Selection Guided Multi-Relational Graph Neural Networks
• Are Graph Neural Networks Miscalibrated?
• GraphNorm: A Principled Approach to Accelerating Graph Neural Network Training
• GeoMol: Torsional Geometric Generation of Molecular 3D Conformer Ensembles
• Connecting the Dots: Multivariate Time Series Forecasting with Graph Neural Networks
• Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction
• Symmetry and Generalisation in Neural Approximations of Renormalisation Transformations
• Uniting Heterogeneity, Inductiveness, and Efficiency for Graph Representation Learning
• TransCamP: Graph Transformer for 6-DoF Camera Pose Estimation
• Unsupervised Graph Representation by Periphery and Hierarchical Information Maximization
• Graph Neural Networks: Methods, Applications, and Opportunities
• HyperGraphX: Graph Transductive Learning with Hyperdimensional Computing and Message Passing
• Machine learning approaches for interpretable antibody property prediction using structural data
• High-throughput quantum theory of atoms in molecules (QTAIM) for geometric deep learning of molecular and reaction properties
• How Does a Neural Network's Architecture Impact Its Robustness to Noisy Labels?
• Improving Predictions of Molecular Properties with Graph Featurisation and Heterogeneous Ensemble Models
• Sound Logical Explanations for Mean Aggregation Graph Neural Networks
• Logical GANs: Adversarial Learning through Ehrenfeucht Fraisse Games
• Random Search Neural Networks for Efficient and Expressive Graph Learning
• Enhancing Graph Classification Robustness with Singular Pooling
• A roadmap for curvature-based geometric data analysis and learning
• Iteratively Refined Early Interaction Alignment for Subgraph Matching based Graph Retrieval
• Self-Attention Graph Pooling
• Adaptive Universal Generalized PageRank Graph Neural Network
• A Hybrid GNN-LSE Method for Fast, Robust, and Physically-Consistent AC Power Flow
• HollowFlow: Efficient Sample Likelihood Evaluation using Hollow Message Passing
• M-GLC: Motif-Driven Global-Local Context Graphs for Few-shot Molecular Property Prediction
• Structural Invariance Matters: Rethinking Graph Rewiring through Graph Metrics
• Improving COVID-19 Forecasting using eXogenous Variables
• Data-Driven Short-Term Voltage Stability Assessment Based on Spatial-Temporal Graph Convolutional Network
• Revisiting Over-smoothing in Deep GCNs
• Robustness Verification of Graph Neural Networks Via Lightweight Satisfiability Testing
• Training Diverse Graph Experts for Ensembles: A Systematic Empirical Study
• NTKMTL: Mitigating Task Imbalance in Multi-Task Learning from Neural Tangent Kernel Perspective
• DeepChem Equivariant: SE(3)-Equivariant Support in an Open-Source Molecular Machine Learning Library
• Efficient High-Accuracy PDEs Solver with the Linear Attention Neural Operator
• On The Expressive Power of GNN Derivatives
• Coder as Editor: Code-driven Interpretable Molecular Optimization
• Composition-based Multi-Relational Graph Convolutional Networks
• Graph Neural Networks: A Review of Methods and Applications
• SimPoly: Simulation of Polymers with Machine Learning Force Fields Derived from First Principles
• Multi-Agent Design Assistant for the Simulation of Inertial Fusion Energy
• Reciprocal Space Attention for Learning Long-Range Interactions
• Dirichlet Energy Constrained Learning for Deep Graph Neural Networks
• Heterogeneous Graph Representation of Stiffened Panels with Non-Uniform Boundary Conditions and Loads
• Machine Learning on Graphs: A Model and Comprehensive Taxonomy
• Graph Few-Shot Learning via Adaptive Spectrum Experts and Cross-Set Distribution Calibration
• Graph-to-Tree Neural Networks for Learning Structured Input-Output Translation with Applications to Semantic Parsing and Math Word Problem
• Understanding over-squashing and bottlenecks on graphs via curvature
• A Graph-Attentive LSTM Model for Malicious URL Detection
• GraphTARIF: Linear Graph Transformer with Augmented Rank and Improved Focus
• Computing Steiner Trees using Graph Neural Networks
• struc2gauss: Structural Role Preserving Network Embedding via Gaussian Embedding
• Reasoning-Enhanced Large Language Models for Molecular Property Prediction
• Open Biomedical Network Benchmark A Python Toolkit for Benchmarking Datasets with Biomedical Networks
• Multi-View Graph Learning with Graph-Tuple
• Understanding and Resolving Performance Degradation in Graph Convolutional Networks
• MolGA: Molecular Graph Adaptation with Pre-trained 2D Graph Encoder
• Introspection in Learned Semantic Scene Graph Localisation
• Relational Database Distillation: From Structured Tables to Condensed Graph Data
• Revisiting Node Affinity Prediction in Temporal Graphs
• The Unreasonable Effectiveness of Randomized Representations in Online Continual Graph Learning
• When Does Global Attention Help? A Unified Empirical Study on Atomistic Graph Learning
• QGraphLIME - Explaining Quantum Graph Neural Networks
• Comparing fine-tuning strategies of MACE machine learning force field for modeling Li-ion diffusion in LiF for batteries
• Bond-Centered Molecular Fingerprint Derivatives: A BBBP Dataset Study
• Physics-Inspired All-Pair Interaction Learning for 3D Dynamics Modeling
• Toward Uncertainty-Aware and Generalizable Neural Decoding for Quantum LDPC Codes
• Bridging the Gap Between Simulated and Real Network Data Using Transfer Learning
• LEAP: Local ECT-Based Learnable Positional Encodings for Graphs
• Efficient E(3)-equivariant framework for universal charge density prediction
• Neural Operator: Graph Kernel Network for Partial Differential Equations
• DistDGL: Distributed Graph Neural Network Training for Billion-Scale Graphs
• Scalable Boltzmann Generators for equilibrium sampling of large-scale materials
• Accelerating Dynamic Image Graph Construction on FPGA for Vision GNNs
• AlphaSAGE: Structure-Aware Alpha Mining via GFlowNets for Robust Exploration
• Neural Message-Passing on Attention Graphs for Hallucination Detection
• VN-EGNN: E(3)- and SE(3)-Equivariant Graph Neural Networks with Virtual Nodes Enhance Protein Binding Site Identification
• Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks
• Monotonic Transformation Invariant Multi-task Learning
• Virtual Nodes based Heterogeneous Graph Convolutional Neural Network for Efficient Long-Range Information Aggregation
• On the design space between molecular mechanics and machine learning force fields
• Foundation models in bioinformatics
• Neighborhood Sampling Does Not Learn the Same Graph Neural Network
• Beyond Molecular Structure: Critically Assessing Machine Learning for Designing Organic Photovoltaic Materials and Devices
• Learning the Neighborhood: Contrast-Free Multimodal Self-Supervised Molecular Graph Pretraining
• Enhancing Molecular Dipole Moment Prediction with Multitask Machine Learning
• Reversible GNS for Dissipative Fluids with Consistent Bidirectional Dynamics
• SHAKE-GNN: Scalable Hierarchical Kirchhoff-Forest Graph Neural Network
• Stable and Interpretable Jet Physics with IRC-Safe Equivariant Feature Extraction
• GRAM-DTI: adaptive multimodal representation learning for drug target interaction prediction
• TRACE: Learning to Compute on Graphs
• Scaling Laws for Neural Material Models
• AI for Sustainable Future Foods
• GraphUniverse: Synthetic Graph Generation for Evaluating Inductive Generalization
• Equi-RO: A 4D mmWave Radar Odometry via Equivariant Networks
• Recurrent Independent Mechanisms
• GLM-RAG: Graph Language Models for Graph-Based Retrieval-Augmented Generation
• Stimulus-Evoked Network Dynamics in Human Cortical Organoids: From a Graph-Computational Framework to Repeated-Stimulation Depression
• Schreier-Coset Graph Rewiring
• Graph Neural Networks with Local Graph Parameters
• When Does Explicit View Routing Work? A Controlled Study of Multi-View Graph-Text Alignment
• Latent Bridges for Multi-Table Question Answering
• Graph Meta Learning via Local Subgraphs
• Symmetry-adapted graph neural networks for constructing molecular dynamics force fields
• GCVA: A Multiview Fusion Mechanism for Heterogeneous Data Representations
• OSCAgent: Accelerating the Discovery of Organic Solar Cells with LLM Agents
• Quantum Graph Neural Networks
• An Experimental Study of Formula Embeddings for Automated Theorem Proving in First-Order Logic
• Evaluating Logical Generalization in Graph Neural Networks
• Adaptive Graph Convolutional Network with Attention Graph Clustering for Co-saliency Detection
• Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks
• Unsupervised Learning of Graph Hierarchical Abstractions with Differentiable Coarsening and Optimal Transport
• Graphs for deep learning representations
• Transformer Modeling for Both Scalability and Performance in Multivariate Time Series
• Bridging Computational Social Science and Deep Learning: Cultural Dissemination-Inspired Graph Neural Networks
• Exploring Heterophily in Graph-level Tasks
• A Scalable Lift-and-Project Differentiable Approach For the Maximum Cut Problem
• Tackling GNARLy Problems: Graph Neural Algorithmic Reasoning Reimagined through Reinforcement Learning
• Learning from Protein Structure with Geometric Vector Perceptrons
• Is Homophily a Necessity for Graph Neural Networks?
• Neural message passing for joint paratope-epitope prediction
• DeepEOSNet: Capturing the dependency on thermodynamic state in property prediction tasks
• Small-footprint Keyword Spotting with Graph Convolutional Network
• Learning Graph Models for Retrosynthesis Prediction
• Bridging Graph and State-Space Modeling for Intensive Care Unit Length of Stay Prediction
• Robust deep learning–based protein sequence design using ProteinMPNN
• Physics-Informed GCN-LSTM Framework for Long-Term Forecasting of 2D and 3D Microstructure Evolution
• Exploring the Global-to-Local Attention Scheme in Graph Transformers: An Empirical Study
• A Multi-Scale Graph Neural Process with Cross-Drug Co-Attention for Drug-Drug Interactions Prediction
• Efficient Robustness Certificates for Discrete Data: Sparsity-Aware\n Randomized Smoothing for Graphs, Images and More
• Resolving the Body-Order Paradox of Machine Learning Interatomic Potentials
• Understanding and Tackling Over-Dilution in Graph Neural Networks
• Teachers that teach the irrelevant: Pre-training machine learned interaction potentials with classical force fields for robust molecular dynamics simulations
• Property-Isometric Variational Autoencoders for Sequence Modeling and Design
• A Survey of Deep Learning for Scientific Discovery
• Soft Graph Transformer for MIMO Detection
• Hierarchical Fashion Graph Network for Personalized Outfit Recommendation
• Barlow Graph Auto-Encoder for Unsupervised Network Embedding
• From Stars to Subgraphs: Uplifting Any GNN with Local Structure Awareness
• Explainability Techniques for Graph Convolutional Networks
• Scaling Graph Transformers: A Comparative Study of Sparse and Dense Attention
• Graph Homophily Booster: Rethinking the Role of Discrete Features on Heterophilic Graphs
• A Geometric Perspective on Visual Imitation Learning
• Communication-Efficient Sampling for Distributed Training of Graph Convolutional Networks
• Radio Propagation Modelling: To Differentiate or To Deep Learn, That Is The Question
• Dynamic Relational Priming Improves Transformer in Multivariate Time Series
• Asterisk Operator
• Automated Relational Meta-learning
• Descriptor and Graph-based Molecular Representations in Prediction of Copolymer Properties Using Machine Learning
• Weisfeiler and Lehman Go Topological: Message Passing Simplicial\n Networks
• Quantum Graph Attention Networks: Trainable Quantum Encoders for Inductive Graph Learning
• Node Similarity Preserving Graph Convolutional Networks
• Optimal message passing for molecular prediction is simple, attentive and spatial
• GraphPPD: Posterior Predictive Modelling for Graph-Level Inference
• Score Matching on Large Geometric Graphs for Cosmology Generation
• Drug Package Recommendation via Interaction-aware Graph Induction
• A Graph to Graphs Framework for Retrosynthesis Prediction
• Functional Groups are All you Need for Chemically Interpretable Molecular Property Prediction
• Attributed-graphs kernel implementation using local detuning of neutral-atoms Rydberg Hamiltonian
• ProgD: Progressive Multi-scale Decoding with Dynamic Graphs for Joint Multi-agent Motion Forecasting
• Graph Denoising with Framelet Regularizer
• Self-Supervised Graph Learning with Proximity-based Views and Channel Contrast
• How Attentive are Graph Attention Networks?
• Open Domain Question Answering Using Early Fusion of Knowledge Bases and Text
• Chemical-Reaction-Aware Molecule Representation Learning
• DR-CircuitGNN: Training Acceleration of Heterogeneous Circuit Graph Neural Network on GPUs
• Fake News Detection on Social Media using Geometric Deep Learning
• Finding Patient Zero: Learning Contagion Source with Graph Neural Networks
• Attention Maps in 3D Shape Classification for Dental Stage Estimation with Class Node Graph Attention Networks
• Long-Range Graph Wavelet Networks
• PAC-Bayesian Generalization Bounds for Graph Convolutional Networks on Inductive Node Classification
• GPUTB: Efficient Machine Learning Tight-Binding Method for Large-Scale Electronic Properties Calculations
• Data-Efficient Time-Dependent PDE Surrogates: Graph Neural Simulators vs. Neural Operators
• From Eigenmodes to Proofs: Integrating Graph Spectral Operators with Symbolic Interpretable Reasoning
• Discovering Symbolic Models from Deep Learning with Inductive Biases
• Learning to accelerate distributed ADMM using graph neural networks
• Hot-Ham: an accurate and efficient E(3)-equivariant machine-learning electronic structures calculation framework
• RapidGNN: Energy and Communication-Efficient Distributed Training on Large-Scale Graph Neural Networks
• Quantum-Enhanced Multi-Task Learning with Learnable Weighting for Pharmacokinetic and Toxicity Prediction
• Graph2Kernel Grid-LSTM: A Multi-Cued Model for Pedestrian Trajectory Prediction by Learning Adaptive Neighborhoods
• Learning to Simulate Complex Physics with Graph Networks
• WILDS: A Benchmark of in-the-Wild Distribution Shifts
• Learning Particle Dynamics Subject to Rigid Body Manipulations Using Graph Neural Networks
• Neural Circuit Synthesis from Specification Patterns
• Multi-Range Attentive Bicomponent Graph Convolutional Network for Traffic Forecasting
• EvoNet: A Neural Network for Predicting the Evolution of Dynamic Graphs
• Frame Averaging for Invariant and Equivariant Network Design
• STA-GANN: A Valid and Generalizable Spatio-Temporal Kriging Approach
• ADMP-GNN: Adaptive Depth Message Passing GNN
• Continuous Graph Neural Networks
• On the Universality of Graph Neural Networks on Large Random Graphs
• What Expressivity Theory Misses: Message Passing Complexity for GNNs
• Flow Matters: Directional and Expressive GNNs for Heterophilic Graphs
• MARS: Markov Molecular Sampling for Multi-objective Drug Discovery
• Curriculum Guided Personalized Subgraph Federated Learning
• Deep Learning on Attributed Graphs: A Journey from Graphs to Their Embeddings and Back
• Weisfeiler and Leman go Hyperbolic: Learning Distance Preserving Node Representations
• On the Hardness of Learning GNN-based SAT Solvers: The Role of Graph Ricci Curvature
• Artificial Intelligence in Drug Discovery: Applications and Techniques
• Directional Graph Networks
• GN-Transformer: Fusing Sequence and Graph Representation for Improved Code Summarization
• Improving Generative Imagination in Object-Centric World Models
• The expressive power of kth-order invariant graph networks
• Local Virtual Nodes for Alleviating Over-Squashing in Graph Neural Networks
• Molecular Machine Learning in Chemical Process Design
• A Deep Reinforcement Learning Algorithm Using Dynamic Attention Model for Vehicle Routing Problems
• Quantum-Classical Hybrid Molecular Autoencoder for Advancing Classical Decoding
• Memorization in Graph Neural Networks
• Dynamic Triangulation-Based Graph Rewiring for Graph Neural Networks
• Principled Hyperedge Prediction with Structural Spectral Features and Neural Networks
• How Powerful are Graph Neural Networks?
• EvoFormer: Learning Dynamic Graph-Level Representations with Structural and Temporal Bias Correction
• From Prediction to Simulation: AlphaFold 3 as a Differentiable Framework for Structural Biology
• PREDATOR: Registration of 3D Point Clouds with Low Overlap
• OGB-LSC: A Large-Scale Challenge for Machine Learning on Graphs
• SE(3)-equivariant prediction of molecular wavefunctions and electronic\n densities
• Fast Graph Neural Network for Image Classification
• Graph WaveNet for Deep Spatial-Temporal Graph Modeling
• Multimodal Quantum Vision Transformer for Enzyme Commission Classification from Biochemical Representations
• Nested Graph Neural Networks
• Symmetry-adapted generation of 3d point sets for the targeted discovery of molecules
• On the Interplay between Graph Structure and Learning Algorithms in Graph Neural Networks
• Enhancing Contrastive Link Prediction With Edge Balancing Augmentation
• Accelerating Image Classification with Graph Convolutional Neural Networks using Voronoi Diagrams
• CaPGNN: Optimizing Parallel Graph Neural Network Training with Joint Caching and Resource-Aware Graph Partitioning
• NovoMolGen: Rethinking Molecular Language Model Pretraining
• A Fully Spectral Neuro-Symbolic Reasoning Architecture with Graph Signal Processing as the Computational Backbone
• BLIPs: Bayesian Learned Interatomic Potentials
• Adversarial Graph Disentanglement
• Data-driven particle dynamics: Structure-preserving coarse-graining for emergent behavior in non-equilibrium systems
• Root Cause Analysis of Hydrogen Bond Separation in Spatio-Temporal Molecular Dynamics using Causal Models
• Recent advances and applications of deep learning methods in materials science
• Graph-Based Social Relation Reasoning
• Symmetry-Constrained Multi-Scale Physics-Informed Neural Networks for Graphene Electronic Band Structure Prediction
• Graph Embedding VAE: A Permutation Invariant Model of Graph Structure
• Dynamic Mixture-of-Experts for Incremental Graph Learning
• Fast Haar Transforms for Graph Neural Networks
• Over-Squashing in GNNs and Causal Inference of Rewiring Strategies
• Exact Verification of Graph Neural Networks with Incremental Constraint Solving
• Hybrid Node-Destroyer Model with Large Neighborhood Search for Solving the Capacitated Vehicle Routing Problem
• Agentic Graph Neural Networks for Wireless Communications and Networking Towards Edge General Intelligence: A Survey
• Chi-Geometry: A Library for Benchmarking Chirality Prediction of GNNs
• Multi-View Graph Neural Networks for Molecular Property Prediction
• MOTGNN: Interpretable Graph Neural Networks for Multi-Omics Disease Classification
• Synthesize, Retrieve, and Propagate: A Unified Predictive Modeling Framework for Relational Databases
• Propagation Tree Is Not Deep: Adaptive Graph Contrastive Learning Approach for Rumor Detection
• Graphite: Iterative Generative Modeling of Graphs
• Towards Real-World Rumor Detection: Anomaly Detection Framework with Graph Supervised Contrastive Learning
• Geometry-Aware Spiking Graph Neural Network
• Progressive Relation Learning for Group Activity Recognition
• Discriminative structural graph classification
• Benchmarking Pretrained Molecular Embedding Models For Molecular Representation Learning
• Hypergraph Neural Network with State Space Models for Node Classification
• Aggregate-Combine-Readout GNNs Are More Expressive Than Logic C2
• Multi-Stage Knowledge-Distilled VGAE and GAT for Robust Controller-Area-Network Intrusion Detection
• A Scalable Pretraining Framework for Link Prediction with Efficient Adaptation
• Complete the Missing Half: Augmenting Aggregation Filtering with Diversification for Graph Convolutional Networks
• Adversarial Graph Augmentation to Improve Graph Contrastive Learning
• Online Continual Graph Learning
• Learned Low Precision Graph Neural Networks
• Adaptive Riemannian Graph Neural Networks
• Nested Graph Pseudo-Label Refinement for Noisy Label Domain Adaptation Learning
• Neighbor-Sampling Based Momentum Stochastic Methods for Training Graph Neural Networks
• Invariant Graph Transformer for Out-of-Distribution Generalization
• Hierarchical Message-Passing Policies for Multi-Agent Reinforcement Learning
• MPFSR-Enhanced GNNs: Spectral Graph Neural Networks Enhancement Through Learnable Multiple-Parameter Graph Fractional Fourier Transforms
• Using ontology embeddings for structural inductive bias in gene\n expression data analysis

Related

• Flexible dual-branched message passing neural network for quantum mechanical property prediction with molecular conformation
• Automatic Identification of Chemical Moieties
• Simplicial Message Passing for Chemical Property Prediction
• Graph Neural Network Architecture Search for Molecular Property Prediction
• Optimal message passing for molecular prediction is simple, attentive and spatial