[Submitted on 1 May 2020]
Abstract: Knowledge graph (KG) embeddings learn low-dimensional representations of
entities and relations to predict missing facts. KGs often exhibit hierarchical
and logical patterns which must be preserved in the embedding space. For
hierarchical data, hyperbolic embedding methods have shown promise for
high-fidelity and parsimonious representations. However, existing hyperbolic
embedding methods do not account for the rich logical patterns in KGs. In this
work, we introduce a class of hyperbolic KG embedding models that
simultaneously capture hierarchical and logical patterns. Our approach combines
hyperbolic reflections and rotations with attention to model complex relational
patterns. Experimental results on standard KG benchmarks show that our method
improves over previous Euclidean- and hyperbolic-based efforts by up to 6.1% in
mean reciprocal rank (MRR) in low dimensions. Furthermore, we observe that
different geometric transformations capture different types of relations while
attention-based transformations generalize to multiple relations. In high
dimensions, our approach yields new state-of-the-art MRRs of 49.6% on WN18RR
and 57.7% on YAGO3-10.
Submission history
From: Ines Chami [view email]
[v1]
Fri, 1 May 2020 18:00:02 UTC (1,018 KB)
