graph neural networks

CHISA-RSI: Proof-Carrying Continuous Capability Closure for Recursive Self-Improving Networks - Global Stability-Plasticity, No-Valley Rewiring, and Certified Structural Self-Improvement

CHISA-RSI develops a self-contained mathematical framework for capability-preserving structural self-modification in finite modular computational networks. It extends the Chernoff-Hybrid Information Severance Algebra (CHISA) into a continuous theory of recursive self-improvement in which architectural changes can be gl...

Spatiotemporal Graph Neural Network Modeling of Financial Systemic Risk Transmission and Multi-Market Linkages for Early Warning

This repository contains the data, source code, configuration files, trained-model implementation, and supporting materials required to reproduce the experiments presented in the associated manuscript on systemic-risk forecasting. The repository provides the processed dataset comprising 2,516 observations and 16 integr...

Machine Learning-Assisted Physical Design Optimization in Modern Electronic Design Automation (EDA)

Abstract The increasing size and complexity of modern integrated circuits have made physical design a computationally demanding stage of electronic design automation (EDA). Placement, routing, timing, and related optimization tasks require repeated evaluation of large design spaces, while decisions made at one stage ca...

GOLDWALK A Marked-Walk Engine for Cyclic Groups

GOLDWALK A Marked-Walk Engine for Cyclic Groups Author: C. J. Tully ORCID: 0009-0007-5661-7332 https://doi.org/10.5281/zenodo.23021217 Version: 0.1 Date: 29 September 2026 License: CC BY 4.0 Resource type: Technical note / Software documentation --- Abstract GOLDWALK is a software and theorem-card package for enumerati...

Machine Learning-Assisted Physical Design Optimization in Modern Electronic Design Automation (EDA)

Abstract The increasing size and complexity of modern integrated circuits have made physical design a computationally demanding stage of electronic design automation (EDA). Placement, routing, timing, and related optimization tasks require repeated evaluation of large design spaces, while decisions made at one stage ca...

AI Approaches for Industrial Control System Cybersecurity: A Comprehensive Review of Methodological Contexts

A re-view is systematic, analyzing the use of artificial intelligence (AI) methodologies in ICS cybersecurity from the year 2018 to 2024, suggesting that graph-based and hybrid methods yield the best detection accuracy, whereas classical methods still seem to be the most suitable for resource-constrained applications.

RyeongRing/GNN_Surrogate: v1.0.0 — Initial release

Initial public release of the code accompanying the manuscript: "A Graph Neural Network Surrogate for Urban Drainage Simulation: Uncertainty Quantification and Cross-Catchment Transfer" Hyeryeong Yun, Junsuk Kang (submitted to Water Research) This repository contains the model, training, and evaluation code for a conti...

An adaptive propagation layer‑residual deep graph neural network optimized with the gyro fireworks algorithm for stock volatility forecasting

RyeongRing/GNN_Surrogate: v1.0.0 — Initial release

Initial public release of the code accompanying the manuscript: "A Graph Neural Network Surrogate for Urban Drainage Simulation: Uncertainty Quantification and Cross-Catchment Transfer" Hyeryeong Yun, Junsuk Kang (submitted to Water Research) This repository contains the model, training, and evaluation code for a conti...

Lightweight Relation-Aware Graph Neural Networks for Network Threat Detection in the Social Internet of Things

Network threat detection in the Internet of Things must exploit typed relations between devices: a device with unremarkable flow statistics may still be compromised relative to its ownership, co-location, and social ties. Existing graph-based intrusion detectors discard relation type, while lightweight detectors compre...

CNN–GNN Dual-Path Network with Adaptive Feature Fusion and Wavelet-Enhanced Attention for Fine-Grained Pavement Crack Segmentation

A comparative analysis of graph neural networks and classical machine learning for carbapenem-resistance prediction and genomic interpretation in Acinetobacter baumannii

Carbapenem-resistant Acinetobacter baumannii is a hospital-associated pathogen linked to high mortality and limited treatment options. Although many resistance determinants have been identified, how they organize into coordinated systems remains unclear. Using a final binary modeling dataset of 2,448 g...