Relation operators in knowledge graphs are Kraus channels obeying three axioms, enabling KrausKGE which outperforms baselines on N-to-N relations and supplies a rank-based complexity measure.
Neural bellman-ford networks: A general graph neural network framework for link prediction.Advances in neural information processing systems, 34:29476–29490
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1roles
background 1polarities
background 1representative citing papers
citing papers explorer
-
Relations Are Channels: Knowledge Graph Embedding via Kraus Decompositions
Relation operators in knowledge graphs are Kraus channels obeying three axioms, enabling KrausKGE which outperforms baselines on N-to-N relations and supplies a rank-based complexity measure.