MEIM: Multi-partition Embedding Interaction Beyond Block Term Format for Efficient and Expressive Link Prediction

30 Sep 2022  ·  Hung Nghiep Tran, Atsuhiro Takasu ·

Knowledge graph embedding aims to predict the missing relations between entities in knowledge graphs. Tensor-decomposition-based models, such as ComplEx, provide a good trade-off between efficiency and expressiveness, that is crucial because of the large size of real world knowledge graphs. The recent multi-partition embedding interaction (MEI) model subsumes these models by using the block term tensor format and provides a systematic solution for the trade-off. However, MEI has several drawbacks, some of which carried from its subsumed tensor-decomposition-based models. In this paper, we address these drawbacks and introduce the Multi-partition Embedding Interaction iMproved beyond block term format (MEIM) model, with independent core tensor for ensemble effects and soft orthogonality for max-rank mapping, in addition to multi-partition embedding. MEIM improves expressiveness while still being highly efficient, helping it to outperform strong baselines and achieve state-of-the-art results on difficult link prediction benchmarks using fairly small embedding sizes. The source code is released at https://github.com/tranhungnghiep/MEIM-KGE.

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Link Prediction FB15k-237 MEIM MRR 0.369 # 9
Hits@10 0.557 # 7
Hits@3 0.406 # 5
Hits@1 0.274 # 8
Link Prediction WN18RR MEIM MRR 0.499 # 7
Hits@10 0.577 # 26
Hits@3 0.518 # 8
Hits@1 0.458 # 6
Link Prediction YAGO3-10 MEIM MRR 0.585 # 1
Hits@10 0.716 # 1
Hits@1 0.514 # 1
Hits@3 0.625 # 1

Methods