Tag: Graph Neural Networks

Researchers have developed IGA, an unsupervised graph alignment framework that uses isomorphism-aware neural networks to predict anchor links across social ...

Researchers at Central South University have developed an interpretable machine learning framework that fuses spatial and temporal process data to ...

A new graph-structured Transformer model trained with self-supervised learning and community-consensus pseudo-labeling achieves record F1-scores for detecting cryptocurrency money laundering ...

A new leakage-audited benchmark shows that random data splitting inflates toxicity model performance by up to 0.079 AUROC points while ...

Researchers in India combined convolutional neural networks, a bird-inspired optimization algorithm, and graph neural networks to identify four promising asthma ...

A new multiscale heterogeneous graph transformer called HierHGT-DTI achieves large gains in cold-start drug-target interaction prediction, especially for protein targets ...

A new causal graph neural network filters out camouflaged neighbour signals in transaction graphs, outperforming seven baselines on Bitcoin, YelpChi, ...

Researchers at IIT (ISM) Dhanbad have developed scDEAN, a lightweight deep clustering framework that adaptively fuses gene expression and cellular ...

Researchers have developed a dual-channel graph completion network that reconstructs missing node features and structure simultaneously while performing well even ...

Researchers at the Universidade de Lisboa have developed a graph neural network method that ranks metabolites by their impact on ...