graph neural networks

1113wu/PE-Based-Defense: PE-Based deformable

Source code for paper: Degraded but Not Entirely Ineffective: PE-Based Deformable Graph Neural Networks

Prediction of vacancy formation energies in Ni-based superalloys by density functional theory calculations and machine learning

Thermal vacancies play a critical role in high-temperature Ni-based superalloys, influencing elastic constants, creep resistance, oxidation resistance, etc. Local chemical variations in multicomponent alloys generate a broad distribution of vacancy formation energies, producing low-energy states that increase vacancy c...

DM-GAE: A Dual-Masked Graph Autoencoder for Mineral Prospectivity Mapping Under Label-Limited Conditions

Physics-Informed Neural Networks and Graph Neural Networks for the Numerical Modeling of the Vector Helmholtz Equation

This workinvestigates neural network representations of vector fields governed by the vector Helmholtz equation, with particular attention on domains containing discontinuous material properties. The de Rham complex and its discrete Whitney–Nédélec counterpart are considered to clarify the relationship between the regu...

Spatio-Temporal Graph Neural Networks for UAV Swarm Intrusion Detection

Fault tolerant cluster-based routing in wireless sensor network using novel intelligent deep learning methodology

Wireless Sensor Networks (WSNs) are highly susceptible to cluster head (CH) failures due to limited node energy and unstable communication links, resulting in data loss and reduced network reliability. This work presents a fault-tolerant cluster-based routing model that integrates an Improved Graph Neural Network (IGNN...

Steady-State Visual-Evoked EEG Dataset for Visual Function Assessment via Biomarker Extraction

Amblyopia and intermittent exotropia (IXT) are prevalent pediatric visual impairments characterized by deficits in cortical visual processing. Understanding the underlying neurophysiological mechanisms and tracking neural recovery requires high–quality, objective data, yet open–access EEG datasets specifically designed...

HUNTINGTON'S DISEASE ENRICHED COHORT

This Zenodo record contains a free, evaluation-grade sample of 10,000 synthetic patient records — a genuine, unmodified subset of the full production dataset, not a separate re-generation. It is provided so that researchers, ML engineers, and clinical data scientists can inspect the schema, phenotypic depth, and biomar...

Information Cascade Popularity Prediction Using Structural and Temporal Features

The basic ideas of online diffusion are introduced by formalising cascade and global graphs, and the extraction of structural and temporal features is described, and the shift toward modelling stochastic cascade dynamics is highlighted.

GeoNicheTrans: Spatial Niche Inference and Immune Architecture Characterization in Oral and Oropharyngeal Squamous Cell Carcinoma Validated by CODEX Protein Profiling

Background: The tumor microenvironment is spatially organized into distinct ecological niches that shape immune responses and therapeutic outcomes, yet inferring spatial niches from transcriptomic data and validating them at the protein level remains challenging, particularly in oral and oropharyngeal squamous cell car...

Dynamic coarsened spatio-temporal graph convolutional networks for fMRI classification of addiction-induced sleep disorders

Abstract Substance Use Disorder (SUD) is frequently characterized by persistent sleep disturbances that hinder cognitive recovery. Accurately identifying these disruptions requires methods capable of tracking both spatial interactions and the temporal evolution of brain activity. While functional magnetic resonance ima...

Toward a Simulated Avian Visual System: Connectome Mapping of the Pigeon Tectofugal Pathway as a Biologically-Grounded CNN Alternative

Image recognition remains one of the central unsolved problems in machine learning. Despite superhuman benchmark accuracy, convolutional neural networks (CNNs) fail systematically at the tasks that define real-world deployment: they require orders of magnitude more labeled data than biological learners, collapse under...