KBGAN: Adversarial Learning for Knowledge Graph Embeddings

We introduce KBGAN, an adversarial learning framework to improve the performances of a wide range of existing knowledge graph embedding models. Because knowledge graphs typically only contain positive facts, sampling useful negative training examples is a non-trivial task... (read more)

PDF Abstract NAACL 2018 PDF NAACL 2018 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Link Prediction FB15k-237 KBGAN (TransD + ComplEx) MRR 0.277 # 29
[email protected] 0.458 # 28
Link Prediction WN18 KBGAN (TransD + ComplEx) MRR 0.779 # 18
[email protected] 0.948 # 11
Link Prediction WN18RR KBGAN (TransD + ComplEx) MRR 0.215 # 31
[email protected] 0.469 # 29

Methods used in the Paper