Hypernetwork Knowledge Graph Embeddings

21 Aug 2018Ivana BalaževićCarl AllenTimothy M. Hospedales

Knowledge graphs are graphical representations of large databases of facts, which typically suffer from incompleteness. Inferring missing relations (links) between entities (nodes) is the task of link prediction... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Link Prediction FB15k HypER MRR 0.790 # 9
[email protected] 0.885 # 8
[email protected] 0.829 # 5
[email protected] 0.734 # 5
Link Prediction FB15k-237 HypER MRR 0.341 # 18
[email protected] 0.520 # 19
[email protected] 0.376 # 11
[email protected] 0.252 # 11
Link Prediction WN18 HypER MRR 0.951 # 4
[email protected] 0.958 # 5
[email protected] 0.955 # 2
[email protected] 0.947 # 3
Link Prediction WN18RR HypER MRR 0.465 # 16
[email protected] 0.522 # 23
[email protected] 0.477 # 14
[email protected] 0.436 # 9
MR 5796 # 15

Methods used in the Paper