Proposes Adaptive Margin Loss (AML) for TransE-style KG embeddings that uses a correntropy objective to adaptively expand the margin during training, requiring only a single center value instead of upper/lower bounds.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CL 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Adaptive Margin Ranking Loss for Knowledge Graph Embeddings via a Correntropy Objective Function
Proposes Adaptive Margin Loss (AML) for TransE-style KG embeddings that uses a correntropy objective to adaptively expand the margin during training, requiring only a single center value instead of upper/lower bounds.