graph neural networks

Federated Learning and Generative AI for Resilient Supply Chain Network Optimization: A Data-Driven Approach

Monitoring Change in 3D (MonChain3D)

MonChain3D, short for Monitoring Change in 3D, is a Python-based software suite for the processing, analysis, and comparison of 3D mesh data and mesh-derived graphs. It provides an integrated workflow encompassing mesh preprocessing, annotation and labeling, orientation and registration, graph construction and analysis...

Benchmarking Spatio-Temporal Graph Neural Networks for Time Series Forecasting Across Heterogeneous Graph Domains

An energy-based differentiable finite element framework for elastic and path-dependent elastoplastic solids

This paper proposes a finite-element-integrated deep energy method (DEM), hereafter referred to as FE-integrated DEM, for linear elasticity and path-dependent J 2 /von Mises plasticity. The method targets a central difficulty in neural elastoplastic solvers: path-dependent internal variables must be evolved consistentl...

OpenFOAM reference solutions of the 3D lid-driven cavity and 3D natural-convection cavity benchmarks

Converged OpenFOAM reference flow fields of the two steady benchmarks of the manuscript "Label-Free Finite-Volume-Residual Training of Attention Graph Neural Networks for Coupled Thermo-Fluid Fields". LDC_3D_lid_driven_cavity_OpenFOAM_reference.h5 holds the 3D lid-driven cavity (48^3 uniform mesh) at Re = 100, 400, 100...

Simulation Study on Digital Divide Propagation Path of Elderly Medical Treatment Based on Graph Neural Network and Public Social Network Data

To address the self-reinforcing diffusion of the digital divide in elderly medical treatment and the difficulty of precise intervention, this study proposes a Propagation–Adoption Coupled Graph Neural Network (PAC-GNN) and a path-level interpretable simulation framework. Using three types of public social network data,...

A graph neural network-based decision support model for educational management

When does network topology help? Cross-domain evaluation of similarity networks for binary classication

Strain-Engineered Magnetism, Super-Exchange Physics, and Thermal Phase Transitions in Monolayer Chromium Trihalides (CrX3, X = Cl, Br, I)

This repository contains the simulation dataset, processing scripts, and workflow execution files for the study: "Strain-Engineered Magnetism, Super-Exchange Physics, and Thermal Phase Transitions in Monolayer Chromium Trihalides (CrX3, X = Cl, Br, I)". Abstract:Using a multiscale framework combining Graph Neural Netwo...

Monotone Physics-Constrained Graph Neural Networks for Image-Based Structural Damage Assessment: Theory and Leakage-Free Evaluation

Image-based structural damage assessment requires automated methods that respect physical constraints. We formulate graph-neural-network message passing as a pseudo-time iteration of a monotone operator on a spatial-region graph. Under non-negative projected weights, order-preserving activations, and a self-loop maximu...

Bonsai: Efficient and Optimal Automatic Tensor Rematerialization for Memory-Constrained DNN Training

GPU memory is increasingly the primary bottleneck in scaling deep neural network (DNN) training, where the activation tensors footprint of a model may exceed the memory capacity. Tensor recomputation is a powerful technique that trades additional computation for reduced peak memory usage. However, existing approaches f...

Relaxation via separable estimators: arithmetic and implementation

Abstract This article presents an arithmetic, called superposition relaxation, for bracketing the graph of a multivariate factorable function on a compact domain between a pair of underestimating and overestimating functions that are both separable. Propagation rules are established for affine and nonlinear composition...