IVR regularizer shrinks intermediate variables in tensor-decomposition KGC models and improves MRR on three benchmarks, but its stated trace-norm upper bound is false for the alpha>2 settings used by most models.
Convolutional 2d knowledge graph embeddings
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Knowledge Graph Completion by Intermediate Variables Regularization
IVR regularizer shrinks intermediate variables in tensor-decomposition KGC models and improves MRR on three benchmarks, but its stated trace-norm upper bound is false for the alpha>2 settings used by most models.