graph neural networks

Structurally Cascaded Physics‐Informed Graph Neural Networks for Mechanotransduction‐Aware Tumor Microenvironment Modeling

ABSTRACT Physics‐informed neural networks offer a useful mesh‐free approach for solving partial differential equations in complex multiphysics systems, such as the tumor microenvironment. These computational models can support future sustainable engineering applications and operations in precision medicine by enabling...

Jointly Predicting Civil Unrest Event Occurrence Probabilities and Potential Initiators via Multi-Task Learning

The eruption of civil unrest events often inflicts severe disruption on social stability. Accurate prediction of these events can assist decision-makers in proactively formulating countermeasures, thereby preventing violent incidents and mitigating property damage. Current event prediction methods often focus on predic...

Adversarial Robustness of Complex-Valued Graph Attention Beamformers: A Gradient Efficiency Study

Graph neural network (GNN) based beamformers have demonstrated near-optimal performance for multi-user MISO systems, yet their security under adversarial channel perturbations remains unexplored. We study the adversarial robustness of a complex-valued Graph Attention Network (GAT) beamformer trained via unsupervised La...

Design of a financial fraud detection model optimized by multi-task learning and graph neural networks

GN-MTNet, a novel financial fraud detection framework that synthesizes graph neural networks with multi-task learning, is introduced, furnishing essential technical underpinnings for the development of enterprise risk profiling and the enhancement of intelligent financial auditing systems.

Differentiable Spatial Autocorrelation in End-to-End Deep Learning for Hedonic Agricultural Land Pricing

We propose an end-to-end differentiable framework for hedonic agricultural land pricing that integrates deep learning-based land cover classification with spatial econometric modeling into a single neural architecture. Traditional hedonic pricing approaches typically separate land cover extraction from price regression...

Heterogeneous graph neural networks with biological prior knowledge for interpretable drug repurposing in triple-negative breast cancer

Paired Wilcoxon tests in 39 AURORA-US patients with matched primary and metastatic samples confirm that 4 of the 10 IG-identified TFs are significantly altered during metastatic progression after Bonferroni correction.

Analyzing and Mitigating Asymmetric Learning for Product Cold-Start in E-Commerce Purchase Prediction with Graph Neural Networks: Similarity-Driven History Augmentation

This paper proposes Similarity-Driven History Augmentation (SHA), a data-centric approach that assigns synthetic interaction histories to cold-start products by matching them with semantically similar established donors and introduces a decoupled hybrid framework alongside an enhanced SHA strategy that selectively filt...

AI-Driven Software Supply Chain Security and Risk Assessment

The growing complexity of software ecosystems has made the Software Supply Chain (SSC) a primary target for cyberattacks, as evidenced by SolarWinds, Log4Shell, and the XZ Utils backdoor. Traditional Software Composition Analysis (SCA) and static scanning tools are reactive and poorly suited to detecting novel or prove...

GATES: A Graph-Neural-Network Atmospheric Transport Emulation System

WIP release of the new version of GATES, including GATES-Background, the new boundary condition emulation work. Check the How To doc for info on setting up and running the boundary model with the training script, and see the folder with the trained model weights.

Vehicle Trajectory Prediction via Neural Fusion of Multiple EKF-based Trajectory Candidates

A framework that fuses the output of Trajectron++, a neural network-based trajectory predictor, with extended Kalman filter (EKF)-based multiple trajectory candidates at a late stage indicates that EKF-based trajectory candidates can effectively complement neural trajectory prediction through learned fusion.

PolyGraphPy: A unified Python framework for atomistic simulation and machine learning-driven polymer design

Polymers are indispensable materials with daily applications ranging from electronics to medicine, owing to their versatility, which can be tailored by adjusting their chemical composition and architecture. The design space for these compounds is vast and governed by factors such as monomer classes, copolymer configura...

Graph Convolutional Networks for Automated Anthropometric Measurement Estimation from Three-Dimensional Human Body Meshes