Table 2 The parameter settings of TransE and RotatE.
From: An enhanced framework for knowledge graph embedding based on negative sample analogical reasoning
Dataset | Model | Embedding dimension | \(\gamma\) | r | Negative samples |
|---|---|---|---|---|---|
FB15K-237 | TransE | 1000 | 9.0 | \(5e^{-5}\) | 256 |
RotatE | 1000 | 9.0 | \(5e^{-5}\) | 1024 | |
WN18RR | TransE | 500 | 6.0 | \(5e^{-5}\) | 256 |
RotatE | 500 | 6.0 | \(5e^{-5}\) | 1024 |
