graph neural networks

Gas-Conditioned Message Passing Graph Neural Network for Permeability Prediction in Polymeric Membranes

Designing polymeric membranes for diverse gas-separation applications remains a critical challenge. Machine learning (ML) models can significantly accelerate this effort by capturing complex relationships between polymer-gas pairs and enabling permeability prediction over an extended chemical space of gases and polymer...

Non-Commutative Rough Network Economics and Computational Dynamics (NC-RNET): Superseding Finite Graphs via Graphon Operator Theory, Variational Inequalities, and Neural Operator Approximations

Traditional network economics relying on finite graphs and spectral linearizations fails to scale in large-scale heterogeneous limits, while computational economics faces severe curses of dimensionality and approximation disconnects. This paper establishes Non-Commutative Rough Network Economics and Computational Dynam...

Response to comments on "SpatialDG: a novel spatial domain identification method for spatially resolved transcriptomics data based on dual-graph neural network"

Datasets reporting the comparisons shown in Response to comments on "SpatialDG: a novel spatial domain identification method for spatially resolved transcriptomics data based on dual-graph neural network"

Predicting Scientific Collaboration in the Ecuadorian Academic Ecosystem Using Graph Neural Networks

NicheTarget-GNN: niche-aware graph neural networks with counterfactual perturbation for cell-state-specific target discovery in the tumor microenvironment

Code, simulator, analysis scripts and raw outputs for the manuscript 'Niche-Aware Heterogeneous Graph Neural Networks with Counterfactual Perturbation for Discovering Cell-State-Specific Druggable Targets in the Tumor Microenvironment' (Computers in Biology and Medicine, submitted). Includes the simulation benchmark, t...

Learnable coarsening for two-phase flow in porous media

Abstract Hydrodynamic simulations of multi-phase flow in porous media are essential for oil production forecasting but require significant computational resources. Traditional approaches lead to high memory and time demands, restricting multi- scenario analysis. We propose a learnable coarsening algorithm based on grap...

What's the best predictive model for ionic liquid screening? COSMO-SAC, COSMO-RS and GNN

Screening ionic liquids (ILs) is a ranking problem before it is a prediction problem: among millions of cation–anion combinations, what matters is which candidates reach the laboratory, not the value assigned to each. Models are nevertheless compared almost exclusively on absolute error. We benchmark six physics-based...

BioAgent-RAG: A Knowledge-Graph-Augmented Multi-Agent LLM Framework with Self-Reflective Verification for Explainable Drug Repurposing

Biomedical Knowledge Graphs (KGs) such as PrimeKG and Hetionet offer vast structured repositories for clinical discovery; however, conventional Graph Neural Networks (GNNs) suffer from black-box opacity, while standard Retrieval-Augmented Generation (RAG) paradigms face catastrophic hallucinations and biological implau...

Fractal Information Dynamics – Part 2

We propose Fractal Information AI (FIAI), a graph-based architecture for adaptive learning in which knowledge is represented as recursively organized information structures and learning actions are prioritized by validated information gain, uncertainty reduction, network propagation, and decision relevance. The framewo...

Fractal Knowledge Trees for Provability-Guided Multi-Agent Learning

We introduce Fractal Information AI, a proof-of-concept framework for structured knowledge representation and selective multi-agent learning. Knowledge is represented by recursively nested tree structures whose nodes carry uncertainty, entropy-like information measures, and a model-defined provability score. A Learning...

FAST AND ROBUST ELECTROMAGNETIC MODELING AND OPTIMIZATION FROM DC TO LIGHT: BRIDGING FIRST-PRINCIPLES PHYSICS AND MACHINE LEARNING

The rapid advancement of semiconductor technology demands electromagnetic (EM) solvers that are both accurate and computationally efficient, while artificial intelligence (AI) offers new opportunities for accelerating physics-based modeling and optimization. This work develops robust numerical solvers, physics-informed...

Optical and Photonic Computing for Deep Learning Acceleration: Silicon Photonics, Mach-Zehnder Meshes, and Wavelength-Division Multiplexing

Abstract—The relentless exponential scaling of foundation models and transformer architectures has pushed conventional silicon complementary metal-oxide-semiconductor (CMOS) digital accelerators (GPUs, TPUs) toward fundamental thermodynamic and interconnect boundaries. Joule heating, resistance-capacitance (RC) interco...