Knowlege Graph Embedding by Flexible Translation

TL;DR

This paper introduces TransF, a flexible translation-based knowledge graph embedding method that improves handling complex relations and enhances scalability, demonstrating superior performance on benchmark tasks.

Contribution

The paper proposes TransF, a novel relation translation model with flexible magnitude, addressing limitations of prior models in complex relation types and scalability.

Findings

TransF outperforms state-of-the-art models in link prediction.

TransF effectively handles reflexive and complex relations.

Experimental results show significant performance improvements.

Abstract

Knowledge graph embedding refers to projecting entities and relations in knowledge graph into continuous vector spaces. State-of-the-art methods, such as TransE, TransH, and TransR build embeddings by treating relation as translation from head entity to tail entity. However, previous models can not deal with reflexive/one-to-many/many-to-one/many-to-many relations properly, or lack of scalability and efficiency. Thus, we propose a novel method, flexible translation, named TransF, to address the above issues. TransF regards relation as translation between head entity vector and tail entity vector with flexible magnitude. To evaluate the proposed model, we conduct link prediction and triple classification on benchmark datasets. Experimental results show that our method remarkably improve the performance compared with several state-of-the-art baselines.