InteractE: Improving Convolution-based Knowledge Graph Embeddings by Increasing Feature Interactions

1 Nov 2019Shikhar VashishthSoumya SanyalVikram NitinNilesh AgrawalPartha Talukdar

Most existing knowledge graphs suffer from incompleteness, which can be alleviated by inferring missing links based on known facts. One popular way to accomplish this is to generate low-dimensional embeddings of entities and relations, and use these to make inferences... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT LEADERBOARD
Link Prediction FB15k-237 InteractE MRR 0.354 # 11
[email protected] 0.535 # 12
[email protected] 0.263 # 7
MR 172 # 4
Link Prediction WN18RR InteractE MRR 0.463 # 17
[email protected] 0.528 # 17
[email protected] 0.430 # 12
MR 5202 # 12
Link Prediction YAGO3-10 InteractE MRR 0.541 # 4
[email protected] 0.687 # 4
[email protected] 0.462 # 2