Research
On-device research index

arXiv research

A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.

169,291 papers · 148 categories

Trend · papers per month

126252378504 · Jun 202019922001200920182026
48 results for Chemical Graph Theory

EAGCN learns attention weights and node features for multi-relational graphs.

problem Learning molecular properties from complex graph structures.
method Edge attention-based multi-relational GCN (EAGCN) that learns attention weights and node features.
result EAGCN predicts compound properties from molecular graphs efficiently and interprets attention weights.

Graph neural network predicts protonation energies of oxygen atoms in bio-oil molecules.

problem Predicting protonation energies of oxygen atoms in bio-oil molecules for chemical upgrading.
method Site-specific graph neural network approach using iterative local nonlinear embedding.
result Effective prediction of protonation energies of individual oxygen atoms in bio-oil molecules.

MoFlow generates chemically valid molecular graphs from latent representations.

problem Generating chemically valid molecular graphs from latent representations is challenging.
method MoFlow uses a flow-based approach with Glow for bond generation and a novel graph conditional flow for atom generation, ensuring chemical validity and efficiency.
result MoFlow achieves state-of-the-art performance in molecular graph generation and optimization.

MEGAN models chemical reactions as graph edits, improving synthesis planning.

problem Generating and predicting chemical reactions under constraints.
method End-to-end encoder-decoder neural model inspired by arrow pushing formalism.
result State-of-the-art accuracy in standard benchmarks for retrosynthesis prediction.

GraphAF generates chemically valid molecules efficiently and accurately.

problem Generating chemically valid molecular structures while optimizing chemical properties.
method Flow-based autoregressive model combining autoregressive and flow-based approaches.
result GraphAF generates 68% chemically valid molecules without chemical knowledge rules and 100% with rules, achieving state-of-the-art performance.

ChemGrapher uses deep learning to automatically convert chemical compound images into accurate graphs.

problem Automatically converting chemical compound images into accurate graphs with correct bond multiplicity and stereochemical information.
method Developed a deep neural network model for optical compound recognition, including segmentation and classification models.
result Significant error reductions in bond multiplicity and stereochemical information compared to existing tools.

Automates molecule design with a novel variational autoencoder.

problem Designing molecules based on specific chemical properties.
method Junction tree variational autoencoder generating tree-structured scaffolds and combining them into molecules.
result Significantly outperforms previous models on molecular generation and optimization tasks.

DeepSIBA predicts biological effects of chemical structures using graph neural networks.

problem Predicting biological effects of chemical structures for drug discovery.
method Siamese Graph Convolutional Neural Networks for structure-biological effect mapping.
result Highly accurate predictions of biological effects for structurally dissimilar compounds.

Graph neural networks improve molecular property prediction.

problem Efficiently predicting molecular properties with high accuracy and scalability.
method Gated Graph Recursive Neural Networks (GGNN) with skip connections.
result GGNN achieves state-of-the-art performance on molecular property prediction benchmarks.

A framework separates chemical and structural contributions to aqueous solubility.

problem Merging chemical and structural information in solubility models obscures their relative contributions.
method Additive MLP-GNN framework with separate chemical and structural branches.
result Framework reveals distinct roles of chemical and structural information in solubility.

Capsule Neural Networks classify graphs from categorical features and relationships.

problem Graph classification in scientific domains, especially with varying graph sizes and features.
method Explicit tensor representations, Capsule Network for classification.
result Capsule Network model performs competitively with state-of-the-art models.

Framework separates chemical and structural contributions to aqueous solubility.

problem Merging chemical and structural information in solubility models obscures their relative importance.
method Additive MLP-GNN framework with separate chemical and structural branches.
result Framework reveals distinct roles of chemical and structural information in solubility.

Novel multigraph network improves chemical classification tasks.

problem Learning from variable graphs with multiple relationships.
method Proposed a multigraph network using Chebyshev GCNs to handle variable graphs and learned edges.
result Achieved competitive results on chemical classification benchmarks.

Hyperbolic volume correlates with chemical properties of fullerenes.

problem Understanding the relationship between fullerene structure and chemical properties.
method Calculated hyperbolic volumes of fullerenes and correlated them with topological indices.
result Hyperbolic volume correlates with Wiener index and other topological indices of fullerenes.

Graph Convolutional Neural Networks identify molecular functional groups.

problem Automatic discovery of molecular functional groups to reduce lab experiments.
method Graph Convolutional Neural Networks (GCNNs) trained on relational graphs of molecules.
result Grad-CAM method identified the most specific and relevant molecular substructures.

GraphNVP generates molecular graphs efficiently and reversibly.

problem Generating valid molecular graphs with desired properties.
method Decomposes graph generation into adjacency tensor and node attributes, using reversible flows.
result Efficiently generates valid molecular graphs with minimal duplicates and latent space for property generation.

Improved molecular property prediction using WL embedding in GNNs.

problem Limited performance of GNNs in predicting molecular properties.
method Explored Weisfeiler-Lehman (WL) embedding to replace GNN layers, enhancing representability and performance.
result WL embedding consistently improves GNN performance across multiple datasets.

Efficient memory layer improves graph neural networks for graph classification and regression.

problem Efficiently learning node representations and graph coarsening for arbitrary graph topology.
method Introduces a memory layer for GNNs that learns node representations and graph coarsening, and two new networks: MemGNN and GMN.
result Proposed models achieve state-of-the-art results in graph classification and regression benchmarks.

HiGraphDTI learns drug and target representations from molecular graphs to predict DTIs.

problem Inaccurate drug-target interaction prediction due to insufficient chemical information extraction.
method Hierarchical graph representation learning to extract chemical information from atoms, motifs, and molecules.
result HiGraphDTI outperforms state-of-the-art methods in DTI prediction and interaction interpretation.

BayesGrad explains graph convolutional network predictions.

problem Uncertainty in chemical property predictions due to small sample size and label imbalance.
method Bayesian predictive distribution with dropout technique to define node importance.
result BayesGrad successfully visualizes substructures responsible for predictions in small sample size scenarios.

Generative model designs drug combinations for improved efficacy and reduced side effects.

problem Designing effective drug combinations to overcome resistance and reduce side effects.
method Developed a deep generative model using HVGAE and a novel reward system.
result Network-principled drug combinations show reduced toxicity and potential for new strategies.

TeaNet uses GCNs to model complex atomic interactions inspired by electronic relaxation.

problem Creating a universal interatomic potential for all elements.
method Tensor-embedded atom network (TeaNet) using graph convolutional neural networks (GCNs).
result TeaNet achieves good performance (19 meV/atom) for structures and reactions involving elements from H to Ar.

HLTF generates chemically valid 3D molecules with improved topology control.

problem Generating chemically valid 3D molecules is challenging due to bond topology errors.
method HLTF uses a latent multi-scale plan for global context and a constraint-aware sampler to suppress topology-driven failures.
result HLTF achieves high validity and uniqueness on QM9 and GEOM-DRUGS datasets.

Automates molecule design with simpler SMILES generation and reinforcement learning.

problem Designing molecules with specific chemical properties.
method Combines context-free grammar for SMILES strings and reinforcement learning with a Transformer model.
result Significantly reduces model steps per atom and beats previous baselines.

Proposes a new model to predict polymer properties by integrating various data types.

problem Inaccurate polymer property prediction due to separate modeling of different data types.
method Multi-modal cascade feature transfer using GCN for chemical structure and molecular descriptors.
result Empirically evaluated model shows higher predictive performance than single-feature approaches.

GCPN uses reinforcement learning to generate molecules optimizing desired properties.

problem Generating novel molecules with desired properties while obeying physical laws.
method Graph Convolutional Policy Network (GCPN) trained with reinforcement learning.
result GCPN achieves significant improvements in molecule optimization tasks.

InteractionNet models noncovalent protein-ligand interactions with GNNs and explains predictions.

problem Modeling noncovalent protein-ligand interactions with graph neural networks.
method InteractionNet uses a GNN architecture with separated covalent and noncovalent convolution layers and layer-wise relevance propagation for explainability.
result InteractionNet successfully predicts noncovalent protein-ligand interactions with chemical relevance.

Geometric approach to thermodynamics of chemical reaction networks.

problem Thermodynamics of chemical reaction networks with non-ideal behavior.
method Information geometry, Riemannian geometry, Cramer-Rao bound, absolute sensitivity.
result Absolute sensitivity is a projection operator onto the tangent bundle of the equilibrium manifold.

Graph neural networks outperform fixed molecular descriptors in property prediction.

problem Comparing graph neural networks to fixed molecular descriptors for property prediction.
method Benchmarked graph convolutional neural networks on public and proprietary datasets.
result Graph convolutional model consistently matches or outperforms existing models on both public and proprietary datasets.

A new graph model HMG and neural network HMGNN improve molecule property predictions.

problem Predicting quantum mechanical properties of molecules with limited consideration of many-body interactions.
method Introducing heterogeneous molecular graphs (HMG) and building HMGNN on neural message passing scheme.
result HMGNN achieves state-of-the-art performance in 9 out of 12 tasks on the QM9 dataset.

New method finds graphene nanocrystals with reduced DFT calculations.

problem Efficiently discovering materials with desired properties in high-dimensional chemical space.
method Bayesian optimization with neural network kernel to minimize DFT calculations.
result Reduced computational cost by 20% for discovering materials with target properties.

GemNet improves molecular predictions by overcoming graph neural network limitations.

problem Graph neural networks struggle with distinguishing certain types of molecular graphs.
method Discretized geometric message passing neural network (GemNet) with spherical representations.
result GemNet outperforms previous models on molecular datasets by 34-20%.

Formulates approach for guiding explanation types based on user specifications.

problem Creating explainable AI components from user-defined specifications.
method Develops a method for generating explanations based on user-defined specifications.
result Demonstrates feasibility of user-defined explanations for complex models like Bayesian networks and graph neural networks.