# Knowledge Graph Embedding Bi-Vector Models for Symmetric Relation

## TL;DR

This paper introduces bi-vector models for knowledge graph embeddings that better handle symmetric relations by representing them as vector pairs, addressing a key limitation in existing models and improving reasoning tasks.

## Contribution

The paper proposes a novel bi-vector embedding approach for symmetric relations, enhancing the modeling of symmetry in knowledge graphs.

## Key findings

- Bi-vector models outperform baseline models in symmetric relation tasks.
- Generated benchmark datasets validate the effectiveness of the proposed models.
- Models show significant improvement in link prediction accuracy for symmetric relations.

## Abstract

Knowledge graph embedding (KGE) models have been proposed to improve the performance of knowledge graph reasoning. However, there is a general phenomenon in most of KGEs, as the training progresses, the symmetric relations tend to zero vector, if the symmetric triples ratio is high enough in the dataset. This phenomenon causes subsequent tasks, e.g. link prediction etc., of symmetric relations to fail. The root cause of the problem is that KGEs do not utilize the semantic information of symmetric relations. We propose KGE bi-vector models, which represent the symmetric relations as vector pair, significantly increasing the processing capability of the symmetry relations. We generate the benchmark datasets based on FB15k and WN18 by completing the symmetric relation triples to verify models. The experiment results of our models clearly affirm the effectiveness and superiority of our models against baseline.