Knowledge Graph Embeddings with Representing Relations as Annular Sectors

TL;DR

SectorE introduces a novel polar coordinate embedding model for knowledge graphs, representing relations as annular sectors to better encode semantic hierarchies and improve link prediction tasks.

Contribution

The paper proposes SectorE, a new geometric embedding approach that models relations as annular sectors in polar coordinates, capturing hierarchical semantics more effectively.

Findings

Achieves competitive results on FB15k-237, WN18RR, and YAGO3-10 datasets.

Effectively encodes semantic hierarchies within knowledge graph embeddings.

Demonstrates strengths in semantic modeling compared to existing models.

Abstract

Knowledge graphs (KGs), structured as multi-relational data of entities and relations, are vital for tasks like data analysis and recommendation systems. Knowledge graph completion (KGC), or link prediction, addresses incompleteness of KGs by inferring missing triples (h, r, t). It is vital for downstream applications. Region-based embedding models usually embed entities as points and relations as geometric regions to accomplish the task. Despite progress, these models often overlook semantic hierarchies inherent in entities. To solve this problem, we propose SectorE, a novel embedding model in polar coordinates. Relations are modeled as annular sectors, combining modulus and phase to capture inference patterns and relation attributes. Entities are embedded as points within these sectors, intuitively encoding hierarchical structure. Evaluated on FB15k-237, WN18RR, and YAGO3-10, SectorE achieves competitive performance against various kinds of models, demonstrating strengths in semantic modeling capability.