Tag: Graph Neural Networks

A new systematic review and meta-analysis of 23 studies finds that machine learning models for peptide–target interaction prediction achieve strong ...

A hybrid graph neural network and deep unrolling architecture achieves 98 percent success in super-resolution direction-of-arrival estimation while remaining robust ...

A topology-aware deep reinforcement learning framework that encodes drainage networks as graphs cut simulated flood overflow by over 31 percent ...

A new study shows that deep learning models can accurately predict the mechanical strength of biodegradable magnesium alloys while clearly ...

Researchers at Central South University have developed a cluster-based domain adaptation method that aligns only semantically similar portions of source ...

A new multimodal AI framework called MEGH-DDI combines chemical language models with graph neural networks to predict drug–drug interactions with ...

Researchers at Liaoning Normal University have developed MCC-ED, a multi-module AI framework that combines contextual interaction, closed-loop graph fusion, and ...

Researchers in Zhengzhou have built a graph neural network that encodes the measured noise of superconducting quantum processors to correct ...

A new deep learning architecture called Hessian Interatomic Potentials predicts the full molecular Hessian directly, delivering one to two orders ...

A systematic study finds that large language models consistently fail to learn spatial coordinate information in materials property prediction, with ...