Gauge-equivariant graph neural networks embed non-Abelian local symmetries directly into message passing for lattice gauge theories, enabling learning of nonlocal observables from local operations.
hub
Neural Message Passing for Quantum Chemistry
20 Pith papers cite this work. Polarity classification is still indexing.
20
Pith papers citing it
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.
hub tools
citation-role summary
background 2
method 1
citation-polarity summary
representative citing papers
GraphNPE recovers a significantly lower central density for Boötes I consistent with a core while Draco remains marginally cuspy, and demonstrates that higher-order velocity moments reduce bias in dynamical modeling.
mHIP-NN extends hierarchical message-passing networks to model electron-mediated spin dynamics in disordered itinerant magnets while preserving rotational symmetry.
Neural-network quantum states applied to HAL QCD meson-nucleon potentials predict bound states for phi at A>=2, J/psi at A>=4, and eta_c at A>=6, with binding energies from tens of MeV to sub-MeV scales.
HetSheaf applies cellular sheaves and type-conditioned restriction maps to heterogeneous graphs, plus SheafPool for basis-invariant graph-level representations, delivering competitive accuracy with substantially reduced parameter counts.
A gauge-invariant GNN using Wilson loops as inputs accurately predicts observables and simulates dynamics in Z2 and U(1) lattice gauge models.
PROVFUSION fuses three complementary views of provenance data with lightweight schemes and voting to achieve higher detection accuracy and lower false positives than node- or edge-only baselines on nine benchmarks.
Boundary degree as a per-node feature improves epidemic scenario identification accuracy by 19% on realistic contact networks from Tennessee and Virginia.
MMGNN decomposes molecular graphs into multi-color subgraphs by atom-type pairs and applies shared message-passing per subgraph, achieving top macro AUC-ROC of 0.838 on classification and best RMSE on ESOL and FreeSolv among tested models.
Trained MPNNs factor through bounded step-graphon-signals that embed via an explicit map into disjoint caps on the n-sphere, producing a topological fingerprint for model comparison and retrieval.
QARMA applies transformer-augmented reinforcement learning to qubit allocation and reuse in modular quantum systems, reporting up to 86% average reduction in inter-core communications versus optimized Qiskit baselines.
A graph neural network framework learns affinities from appearance and motion then solves bipartite matching for online multiple-object tracking.
Machine learning models, especially certain deep neural networks, can predict lattice thermal conductivity with useful accuracy across different generalization tests while being orders of magnitude faster than first-principles calculations.
GRASP detects anomalies in system provenance graphs via self-supervised executable prediction from two-hop neighborhoods, outperforming prior PIDS on DARPA datasets by identifying all documented attacks where behaviors are learnable plus additional unlabeled suspicious activity.
Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities.
IO-aware GPU kernels for SpMM convolutions, degree-aware reductions, and fused attention layers deliver median speedups of 1.6-2.6x (up to 10x) and memory reductions up to 76x over DGL/PyG baselines on realistic graphs.
UTOPYA fuses eight modalities via FiLM-conditioned attention and physics-informed regularization to reach AUROC 0.874 for anomaly detection in batch distillation, outperforming baselines by 0.147.
FIT-GNN applies graph coarsening during inference to deliver orders-of-magnitude faster single-node inference and lower memory use on node and graph classification/regression tasks while keeping competitive accuracy.
MACE-MPA-0 predicts Li diffusion Ea of 0.22 eV in LiF, fine-tuned version with 300 points gives 0.20 eV, close to DeePMD reference of 0.24 eV, using far less training data.
This perspective article develops a definition of foundational MLIPs and poses six open questions that the authors believe will define future research in machine-learned interatomic potentials.
citing papers explorer
-
Gauge-Equivariant Graph Neural Networks for Lattice Gauge Theories
Gauge-equivariant graph neural networks embed non-Abelian local symmetries directly into message passing for lattice gauge theories, enabling learning of nonlocal observables from local operations.
-
Dark Matter in Draco and Bo\"otes I: Hints of a Core in an Ultra-Faint Dwarf from Simulation-Based Inference
GraphNPE recovers a significantly lower central density for Boötes I consistent with a core while Draco remains marginally cuspy, and demonstrates that higher-order velocity moments reduce bias in dynamical modeling.
-
Magnetic HIP-NN for spin dynamics in disordered itinerant magnets
mHIP-NN extends hierarchical message-passing networks to model electron-mediated spin dynamics in disordered itinerant magnets while preserving rotational symmetry.
-
Meson-Nucleus Bound States with Neural-Network Quantum States
Neural-network quantum states applied to HAL QCD meson-nucleon potentials predict bound states for phi at A>=2, J/psi at A>=4, and eta_c at A>=6, with binding energies from tens of MeV to sub-MeV scales.
-
Heterogeneous Sheaf Neural Networks
HetSheaf applies cellular sheaves and type-conditioned restriction maps to heterogeneous graphs, plus SheafPool for basis-invariant graph-level representations, delivering competitive accuracy with substantially reduced parameter counts.
-
Graph Neural Networks in the Wilson Loop Representation of Abelian Lattice Gauge Theories
A gauge-invariant GNN using Wilson loops as inputs accurately predicts observables and simulates dynamics in Z2 and U(1) lattice gauge models.
-
Beyond Nodes vs. Edges: A Multi-View Fusion Framework for Provenance-Based Intrusion Detection
PROVFUSION fuses three complementary views of provenance data with lightweight schemes and voting to achieve higher detection accuracy and lower false positives than node- or edge-only baselines on nine benchmarks.
-
Boundary Degree as a Node-level Feature for Epidemic Scenario Identification in Agent-based Cascade Simulations
Boundary degree as a per-node feature improves epidemic scenario identification accuracy by 19% on realistic contact networks from Tennessee and Virginia.
-
MMGNN: Multi-level, multi-color graph neural networks for molecular property prediction
MMGNN decomposes molecular graphs into multi-color subgraphs by atom-type pairs and applies shared message-passing per subgraph, achieving top macro AUC-ROC of 0.838 on classification and best RMSE on ESOL and FreeSolv among tested models.
-
A Topological Characterization of Graph Neural Networks via Stochastic Block Model Embeddings on the n-Sphere
Trained MPNNs factor through bounded step-graphon-signals that embed via an explicit map into disjoint caps on the n-sphere, producing a topological fingerprint for model comparison and retrieval.
-
Learning-Optimized Qubit Mapping and Reuse to Minimize Inter-Core Communication in Modular Quantum Architectures
QARMA applies transformer-augmented reinforcement learning to qubit allocation and reuse in modular quantum systems, reporting up to 86% average reduction in inter-core communications versus optimized Qiskit baselines.
-
Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Tracking
A graph neural network framework learns affinities from appearance and motion then solves bipartite matching for online multiple-object tracking.
-
Fast and Accurate Prediction of Lattice Thermal Conductivity via Machine Learning Surrogates
Machine learning models, especially certain deep neural networks, can predict lattice thermal conductivity with useful accuracy across different generalization tests while being orders of magnitude faster than first-principles calculations.
-
GRASP -- Graph-Based Anomaly Detection Through Self-Supervised Classification
GRASP detects anomalies in system provenance graphs via self-supervised executable prediction from two-hop neighborhoods, outperforming prior PIDS on DARPA datasets by identifying all documented attacks where behaviors are learnable plus additional unlabeled suspicious activity.
-
Geometric Deep Learning: Grids, Groups, Graphs, Geodesics, and Gauges
Geometric deep learning provides a unified mathematical framework based on grids, groups, graphs, geodesics, and gauges to explain and extend neural network architectures by incorporating physical regularities.
-
On Efficient Scaling of GNNs via IO-Aware Layers Implementations
IO-aware GPU kernels for SpMM convolutions, degree-aware reductions, and fused attention layers deliver median speedups of 1.6-2.6x (up to 10x) and memory reductions up to 76x over DGL/PyG baselines on realistic graphs.
-
UTOPYA: A Multimodal Deep Learning Framework for Physics-Informed Anomaly Detection and Time-Series Prediction
UTOPYA fuses eight modalities via FiLM-conditioned attention and physics-informed regularization to reach AUROC 0.874 for anomaly detection in batch distillation, outperforming baselines by 0.147.
-
FIT-GNN: Faster Inference Time for GNNs that 'FIT' in Memory Using Coarsening
FIT-GNN applies graph coarsening during inference to deliver orders-of-magnitude faster single-node inference and lower memory use on node and graph classification/regression tasks while keeping competitive accuracy.
-
Comparing fine-tuning strategies of MACE machine learning force field for modeling Li-ion diffusion in LiF for batteries
MACE-MPA-0 predicts Li diffusion Ea of 0.22 eV in LiF, fine-tuned version with 300 points gives 0.20 eV, close to DeePMD reference of 0.24 eV, using far less training data.
-
Six Open Questions in Machine-Learned Interatomic Potential Foundation Models
This perspective article develops a definition of foundational MLIPs and poses six open questions that the authors believe will define future research in machine-learned interatomic potentials.