GraphDPO applies direct preference optimization to knowledge graph embedding unlearning, using out-boundary sampling and boundary recall to forget triples while retaining neighbors.
Suchanek, Gjergji Kasneci, and Gerhard Weikum
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Unlearning of Knowledge Graph Embedding via Preference Optimization
GraphDPO applies direct preference optimization to knowledge graph embedding unlearning, using out-boundary sampling and boundary recall to forget triples while retaining neighbors.