graph neural networks

Data and models for leakage-controlled PFAS bioactivity prediction with chemical-space-aware routing

Code, decontaminated data, and model weights for the manuscript "Chemical-space-aware routing enhances PFAS toxicity prediction: large-scale pretraining, conditional fine-tuning, and leakage control". The archive contains the complete pipeline for training and evaluating multi-task graph neural networks (Chemprop D-MPN...

SR-CGCNN: Shared recurrent convolution in crystal graph neural networks for materials property prediction

Crystal graph neural networks predict materials properties by propagating information through local atomic environments. In conventional crystal graph convolutional neural networks (CGCNNs), this propagation depth is increased by stacking independently parameterized convolutional layers. This coupling between message-p...

From Bellman to Real-Time: Extensions to Complex Weather Regimes, Physics-Informed Optimization, and Full-Scale Validation

In our earlier methodology paper, we introduced a hierarchical framework combining graph compression, Diffusion Convolutional Recurrent Neural Networks (DCRNNs), and Multi-Agent Reinforcement Learning (MARL) to approximate Bellman’s optimality principle for real-time energy system control, validated using Palm Springs,...

Artificial Intelligence-Assisted Herbal Formulation Development: From Phytochemical Intelligence to Predictive Nanodelivery and Precision Phytotherapy

Herbal medicines constitute a chemically diverse source of bioactive molecules and remain important components of traditional and complementary healthcare systems. However, the development of reproducible pharmaceutical formulations from herbal materials is complicated by variability in botanical identity, geographical...

Artificial Intelligence-Assisted Herbal Formulation Development: From Phytochemical Intelligence to Predictive Nanodelivery and Precision Phytotherapy

Herbal medicines constitute a chemically diverse source of bioactive molecules and remain important components of traditional and complementary healthcare systems. However, the development of reproducible pharmaceutical formulations from herbal materials is complicated by variability in botanical identity, geographical...

PathSepsisNet: a pathway-aware temporal graph attention network integrating inflammatory crosstalk dynamics for early prediction of multi-organ dysfunction in sepsis

Leveraging large models for domain knowledge-informed architecture search of fault diagnosis

To leverage complex domain knowledge in mechanical fault diagnosis for neural architecture search (NAS) effectively, a domain knowledge-informed architecture search approach utilizing large models is proposed. First, a multi-dimensional, standardized architecture data model is constructed. This model is populated with...

Research on Intelligent Identification of Sea Surface Targets and Sea Clutter Based on Lightweight Network

Aiming at the problem of sea clutter suppression and dim target detection in sea clutter, a sea clutter identification method based on detection sliding window convolutional neural network ( DSW-CNN ) model is proposed. Firstly, the characteristics of sea clutter are analyzed to obtain the characteristics that can dist...

OISES-Graph-Surrogate: geometry-aware surrogate modelling and inverse design of origami-inspired super-expandable scaffolds

Virtual laboratory and graph neural surrogate for origami-inspired super-expandable scaffolds in distraction osteogenesis: co-rotational beam and pore-scale Stokes solvers, an STL-to-graph front end, a multi-task heteroscedastic Scaffold Graph Network, parametric baselines, and the optimisation, ablation and repetition...

From Lab to Clinic: Toward Deployment-Ready Graph Neural Networks for EEG-Based Neurological Diagnosis

Hzw-ZuttoZutto/Revisiting-Locally-Differentially-Private-Graph-Neural-Networks: v1.1.2

No description provided.

Probabilistic protection of smart power systems against load redistribution attacks using ai-based critical measurement selection

Simulation results indicate that the proposed framework improves attack detection accuracy, reduces economic losses, and enhances system resilience relative to conventional deterministic protection approaches.