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

TL;DR

The paper introduces MEIM, an advanced knowledge graph embedding model that enhances expressiveness and efficiency beyond existing tensor formats, achieving state-of-the-art link prediction results with smaller embeddings.

Contribution

It proposes MEIM, a novel multi-partition embedding interaction model with independent core tensors and soft orthogonality, improving upon the block term tensor format for knowledge graph embedding.

Findings

Outperforms strong baselines on link prediction benchmarks.

Achieves state-of-the-art results with smaller embedding sizes.

Maintains high efficiency while increasing expressiveness.

Abstract

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.