Tag: link prediction

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

A clustering-assisted knowledge graph embedding framework reduced the semantic web service search space by 82.73 percent while improving retrieval quality ...

A new graph neural network method called MADPGraph combines relation-aware multi-head attention with adaptive dynamic pruning to improve link prediction ...

A comparative study evaluates link prediction, hyperlink prediction and ERGM estimation for inferring missing connections in partially observed email and ...

A new contrastive learning framework called VMCL improves knowledge graph embedding for unseen entities and shows smooth, predictable gains as ...

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

Researchers have developed MMA-HNS, a framework that keeps multimodal knowledge graph completion accurate even when the textual descriptions of entities ...

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

In an exciting advance for the field of biomedical informatics, researchers have unveiled a groundbreaking method aimed at enhancing link ...