Convolutional 2D Knowledge Graph Embeddings

Link prediction for knowledge graphs is the task of predicting missing relationships between entities. Previous work on link prediction has focused on shallow, fast models which can scale to large knowledge graphs... (read more)

PDF Abstract

Datasets


Introduced in the Paper:

WN18RR

Mentioned in the Paper:

FB15k YAGO WN18

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Link Prediction FB15k ConvE MR 51 # 6
MRR 0.657 # 19
Hits@10 0.831 # 18
Hits@3 0.723 # 13
Hits@1 0.558 # 14
Link Prediction FB15k Inverse Model MR 2501 # 11
MRR 0.660 # 18
Hits@10 0.660 # 20
Hits@3 0.659 # 14
Hits@1 0.658 # 12
Link Prediction FB15k-237 ConvE MRR 0.325 # 29
Hits@10 0.501 # 30
Hits@3 0.356 # 21
Hits@1 0.237 # 24
Link Prediction FB15k-237 Inverse Model MRR 0.010 # 41
Hits@10 0.014 # 44
Hits@3 0.011 # 25
Hits@1 0.007 # 31
MR 7030 # 22
Link Prediction WN18 Inverse Model MRR 0.963 # 1
Hits@10 0.964 # 1
Hits@3 0.964 # 1
Hits@1 0.953 # 1
MR 740 # 15
Link Prediction WN18 ConvE MRR 0.943 # 12
Hits@10 0.956 # 12
Hits@3 0.946 # 10
Hits@1 0.935 # 13
MR 374 # 13
Link Prediction WN18RR Inverse Model MRR 0.35 # 37
Hits@10 0.35 # 36
Hits@3 0.35 # 24
Hits@1 0.35 # 30
MR 13526 # 19
Link Prediction WN18RR ConvE MRR 0.430 # 33
Hits@10 0.520 # 31
Hits@3 0.440 # 23
Hits@1 0.400 # 26
Link Prediction YAGO3-10 ConvE MRR 0.44 # 10
Hits@10 0.62 # 9

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet