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)
PDFTASK | 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 |
|
METHOD | TYPE | |
---|---|---|
![]() |
Graph Embeddings |