graph neural networks

Out-of-Distribution Inverse Design of Elastic Networks with Differentiable Graph Neural Network Molecular Dynamics

Machine-learning-based inverse design can accelerate the discovery of materials with targeted properties, but conventional structure--property models often require large training datasets and generalize poorly beyond their training distribution. Here, we present a differentiable inverse design framework based on a grap...

Machine Learning-Assisted Performance Prediction and Design of MXene Materials

Here, reported ML-assisted studies on MXene prediction and design are organized by target property and workflow, and ML–DFT screening, graph neural networks, uncertainty quantification, active learning, and interpretability are examined.

Connectome Wiring Shapes Motor Lesion Phenotypes in Embodied Drosophila Locomotion

A central controversy in computational neuroscience—recently formalized as The Digital Sphinx debate (Brunton,Abe, Hu, & Tuthill, 2026)—asserts that deep reinforcement learning (DRL) can optimize arbitrary artificial neural networktopologies to generate realistic animal locomotion. Consequently, high-level behavioral r...

développement d’un GNN pour la reconnaissance faciale

Le rapport présente le développement d’une solution basée sur les Graph Neural Networks (GNN) pour l’exploitation de données géométriques. Après un état de l’art détaillant la représentation des données sous forme de graphes et les notions clés des GNN (message passing, mise à jour des nœuds, architectures GCN, GAT, Gr...

Propagation Structure as a Signal for Misinformation Detection with Graph Neural Networks and Edgeless Baselines (Technical Report)

Propagation-based detectors classify a story from the shape of the cascade that carries it, and they report strong benchmark figures. This article measures what those figures are worth. On UPFD, a bidirectional graph convolutional network reaches macro-F1 0.832 on PolitiFact and 0.920 on GossipCop. Handed the same node...

secrierlab/SPiCe: SPiCe release 1.1

A computational framework for modelling intrinsic and extrinsic factors driving cell plasticity using spatial transcriptomics data, graph neural networks (GNNs) and geostatistical regression.

GATES-Background 0.2.0: Emulating background greenhouse gas mole fractions for regional atmospheric inverse modelling with graph neural networks

Abstract. Regional atmospheric trace gas inverse modelling frameworks depend on accurately simulating mole fractions, which result from transporting surface fluxes within a domain and carrying mole fractions into the region from its boundaries. With the aim of improving the computational efficiency of inverse modelling...

An extremely short-term ship motion prediction method based on an IDE-optimized dynamic coupling filtering graph neural network

Deep Learning Applications for Circuit Optimization and Hardware Organization

Abstract Traditional Electronic Design Automation (EDA) logic synthesis struggles with NP-hard state-space explosions as hardware scales to billions of gates. This paper explores deep learning paradigms specifically Graph Neural Networks (GNNs), Reinforcement Learning (RL), and generative transformers to accelerate dig...

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...

Connectome Wiring Shapes Motor Lesion Phenotypes in Embodied Drosophila Locomotion

A central controversy in computational neuroscience—recently formalized as The Digital Sphinx debate (Brunton,Abe, Hu, & Tuthill, 2026)—asserts that deep reinforcement learning (DRL) can optimize arbitrary artificial neural networktopologies to generate realistic animal locomotion. Consequently, high-level behavioral r...

An Adaptive Bias-Corrected Pseudo-Random Number Generator Derived from Nondegenerate Chaotic Systems

The Pseudo-Random Number Generator (PRNG) designed using chaotic systems has been widely used in the field of security communication and some other privacy-required applications because of its excellent nonlinear dynamics. However, in practical engineering applications, the digital realization of chaotic systems on fin...