Bridging the Space Gap: Unifying Geometry Knowledge Graph Embedding with Optimal Transport
Keywords: Knowledge Graph Embedding, Optimal Transport, Euclidean space, Hyperbolic Space
TL;DR: This paper introduces UniGE, a new method for better knowledge graph representation using both Euclidean and hyperbolic spaces, outperforming existing methods in experiments.
Abstract: Knowledge Graph Embedding (KGE) is a critical field aiming to transform the elements of knowledge graphs into continuous spaces, offering great potential for structured data representation. In contemporary KGE research, the utilization of either hyperbolic or Euclidean space for knowledge graph modeling is a common practice. However, Knowledge graphs encompass diverse geometric data structures, including chains and hierarchies, whose hybrid nature exceeds the capacity of a single embedding space to capture effectively. This paper introduces a groundbreaking and highly effective approach called Unified Geometry Knowledge Graph Embedding (UniGE). UniGE stands out as the pioneering KGE methodology that seamlessly integrates knowledge graph embeddings in both Euclidean and hyperbolic geometric spaces. We introduce an embedding alignment method and fusion strategy, which harnesses optimal transport techniques and Wasserstein barycenter method. Furthermore, we offer a comprehensive theoretical analysis to substantiate the superiority of our approach, as evident from a more robust error bound. To substantiate the strength of UniGE, we conducted comprehensive experiments on three benchmark datasets. The results consistently demonstrate that UniGE outperforms state-of-the-art methods, aligning with the conclusions drawn from our theoretical evaluation.
Track: Semantics and Knowledge
Submission Guidelines Scope: Yes
Submission Guidelines Blind: Yes
Submission Guidelines Format: Yes
Submission Guidelines Limit: Yes
Submission Guidelines Authorship: Yes
Student Author: Yes
Submission Number: 1465
Loading