Using Pairwise Occurrence Information to Improve Knowledge Graph Completion on Large-Scale Datasets

IJCNLP 2019 Esma BalkirMasha NaslidnykDave PalfreyArpit Mittal

Bilinear models such as DistMult and ComplEx are effective methods for knowledge graph (KG) completion. However, they require large batch sizes, which becomes a performance bottleneck when training on large scale datasets due to memory constraints... (read more)

PDF Abstract IJCNLP 2019 PDF IJCNLP 2019 Abstract

Code


No code implementations yet. Submit your code now

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK BENCHMARK
Link Prediction FB15k JoBi ComplEx MRR 0.761 # 14
[email protected] 0.883 # 10
[email protected] 0.824 # 7
[email protected] 0.681 # 9
Link Prediction FB15k-237 JoBi ComplEx MRR 0.29 # 26
[email protected] 0.479 # 23
[email protected] 0.319 # 17
[email protected] 0.199 # 19

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