Tag: graph neural networks

A multi-source graph neural network predicted regional hand-injury risk in Hunan with an R² of 0.83 and identified industrial concentration ...

A new graph neural network framework makes skin lesion classification more transparent, but candid reporting reveals serious weaknesses in melanoma ...

A probabilistic dynamic graph deep learning model developed on Prince Edward Island predicted potato crop coefficients with R² values up ...

Researchers have built a graph neural network that classifies scientific papers by combining intuitionistic fuzzy uncertainty, node-level Laplacian energy, and ...

Zhejiang University researchers report a physics-guided framework combining generative imputation, dynamic graph attention, and a constrained decoder that achieved zero ...

A physics-informed graph neural network classified simulated collector-line cascading-trip risk with 0.972 accuracy and 0.91 recall for high-risk events in ...

A computational benchmarking study found that SubPoE delivered the strongest average spatial-domain clustering results across eight paired spatial multi-omics datasets ...

GraphLane combined three-frame context, uncertainty-weighted graph reasoning and road-geometry constraints to improve lane-coordinate estimates in a CULane study, although its ...

A supervised graph-learning model combining metapath embeddings, graph convolution and attention outperformed 12 baselines on the DBLP and ACM academic-network ...

A synthetic simulation of scan-to-order transactions found that DS-GNN ranked privacy-leakage paths and estimated risk more accurately than four baselines, ...

A retrospective study of 15,000 companies found that the MFGCN machine-learning framework outperformed tested baselines in two-quarter financial-crisis warning while ...

A new spatio-temporal graph network models players and the ball as a dynamic graph, detecting key match events and tactical ...

A new neuro-symbolic framework called SymbolFusion applies explicit literary relation constraints to graph learning, achieving state-of-the-art performance in modeling symbolic ...

A new hybrid architecture combining graph convolutions with a lite capsule network delivers an average 9.1 percent improvement in link ...

Recommender systems quietly shape much of modern digital life, deciding which films appear in your queue, which products surface in ...

Kazakhstani researchers have built a trilingual AI knowledge graph that links university curricula, live job vacancies, and online courses, using ...

A new graph neural network framework shows that continuous emotional embeddings from disaster images can predict how far and how ...

Researchers at Zhejiang University and Hangzhou City University have developed DeepMoCo, a graph neural network framework that adaptively corrects both ...

A new framework combining deep reinforcement learning, graph neural networks, and blockchain-based verification synchronizes distributed accounting ledgers in real time ...

Researchers at Dalian Maritime University have developed ESTGCN, a graph neural network that dynamically rewires regional traffic relationships to deliver ...