Translating Embeddings for Modeling Multi-relational Data
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.
PDF AbstractCode
Tasks
FB15k
| Task | Dataset | Model | Metric Name | Metric Value | Global Rank | Benchmark |
|---|---|---|---|---|---|---|
| Link Prediction | FB122 | TransE | HITS@3 | 58.9 | # 5 | |
| Hits@5 | 64.2 | # 5 | ||||
| Hits@10 | 70.2 | # 5 | ||||
| MRR | 48.0 | # 5 | ||||
| Link Prediction | FB15k | TransE | MR | 125 | # 12 | |
| Hits@10 | 0.471 | # 25 | ||||
| Link Prediction | FB15k-237 | TransE | MRR | 0.2904 | # 55 | |
| Hits@10 | .4709 | # 55 | ||||
| Hits@1 | 0.1987 | # 48 | ||||
| Link Prediction | WN18 | TransE | Hits@10 | 0.754 | # 34 | |
| MR | 263 | # 10 | ||||
| Link Prediction | WN18RR | TransE | MRR | 0.4659 | # 48 | |
| Hits@10 | 0.5555 | # 45 | ||||
| Hits@1 | 0.4226 | # 46 |
