graph neural networks

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...

Graph-structured hyperdimensional computing for data-efficient and explainable process–structure–property prediction

Deep learning of proteomics data

Next-generation sequencing technology has propelled the field of biology into the big data era, and continual advancements in computing have now made it easier to explore complex biological systems. However, analysing such highly complex data with conventional machine learning algorithms can be troublesome as these tec...

Deep learning for boundary representation CAD models

This thesis explores utilising deep learning methodologies for tasks relating to learning from boundary representation (B-Rep) CAD models. The ambition is to use deep learning for an automatic feature recognition algorithm to identify geometric features to help automate the CAD to analysis pre-processing task of defeat...

Is the graph doing anything? A sourced survey of recurrent self-routing neural graphs as an alternative to layered networks

Sourced survey with a public quote-per-claim evidence ledger on whether a persistent, self-routing recurrent graph of neural nodes gives more reasoning capacity per stored parameter than a weight-shared looped Transformer, plus a preregistered matched experimental protocol (not run). Built with AI agents; see README.

Is the graph doing anything? A sourced survey of recurrent self-routing neural graphs as an alternative to layered networks

Sourced survey with a public quote-per-claim evidence ledger on whether a persistent, self-routing recurrent graph of neural nodes gives more reasoning capacity per stored parameter than a weight-shared looped Transformer, plus a preregistered matched experimental protocol (not run). Built with AI agents; see README.

PIGNN3D: an accelerated physics-informed graph neural network for 3D thermal field simulation in data centers

Efficient thermal management is critical in data centers, where computational fluid dynamics (CFD) simulations provide high-fidelity airflow and temperature predictions but remain computationally demanding and time-intensive. While data-driven methods have emerged as promising alternatives, most existing works are limi...