Tag: node classification

Researchers developed HGSL-SPSE, a heterogeneous graph structure learning model that outperformed eight mainstream baselines across node classification and clustering benchmarks.

Researchers introduced OTGCL, an optimal transport augmentation framework that preserves node-level degree structure during graph contrastive learning.

Researchers report a graph contrastive learning framework called COIN that combines continuous orthogonal augmentation with an information-balancing training principle and ...

A controlled study of 3,600 runs finds normalization schemes help mainly at shallow depths while graph homophily predicts how accuracy ...

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

Researchers have developed CL3AN-GNN, a graph neural network that borrows curriculum learning from education to progressively disentangle features and boost ...

Researchers at Fuzhou University have developed RCGELM-AE, a graph embedding model that trains in closed form without gradient descent while ...

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

Researchers have developed BHyGNN+, a self-supervised framework that learns representations of heterophilic hypergraphs without labels by contrasting each hypergraph against ...

Researchers show that a randomly initialized, never-trained graph neural network paired with a lightweight streaming classifier outperforms state-of-the-art methods in ...