Translating Embeddings for Modeling Multi-relational Data

Code

• github.com/pyg-team/pytorch_geometric/blob/master/torch_geometric/nn/kge/transe.py
  pytorch★ 0
• github.com/MindSpore-paper-code-3/code9/tree/main/transX
  mindspore★ 0
• github.com/yangyucheng000/TransX-2
  mindspore★ 0
• github.com/2023-MindSpore-1/ms-code-220/tree/main/transX
  mindspore★ 0
• github.com/wrk226/Translating-Embeddings-for-Modeling-Multi-relational-Data
  none★ 0
• github.com/yangyucheng000/transX
  mindspore★ 0

Abstract

We consider the problem of embedding entities and relationships of multi-relational data in low-dimensional vector spaces. Our objective is to propose a canonical model which is easy to train, contains a reduced number of parameters and can scale up to very large databases. Hence, we propose, TransE, a method which models relationships by interpreting them as translations operating on the low-dimensional embeddings of the entities. Despite its simplicity, this assumption proves to be powerful since extensive experiments show that TransE significantly outperforms state-of-the-art methods in link prediction on two knowledge bases. Besides, it can be successfully trained on a large scale data set with 1M entities, 25k relationships and more than 17M training samples.

Tasks

Reproductions