On The Expressive Power of Knowledge Graph Embedding Methods
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866914887955906560 |
|---|---|
| author | Gao, Jiexing Rodin, Dmitry Motolygin, Vasily Zaytsev, Denis |
| author_facet | Gao, Jiexing Rodin, Dmitry Motolygin, Vasily Zaytsev, Denis |
| contents | Knowledge Graph Embedding (KGE) is a popular approach, which aims to represent entities and relations of a knowledge graph in latent spaces. Their representations are known as embeddings. To measure the plausibility of triplets, score functions are defined over embedding spaces. Despite wide dissemination of KGE in various tasks, KGE methods have limitations in reasoning abilities. In this paper we propose a mathematical framework to compare reasoning abilities of KGE methods. We show that STransE has a higher capability than TransComplEx, and then present new STransCoRe method, which improves the STransE by combining it with the TransCoRe insights, which can reduce the STransE space complexity. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_16326 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | On The Expressive Power of Knowledge Graph Embedding Methods Gao, Jiexing Rodin, Dmitry Motolygin, Vasily Zaytsev, Denis Artificial Intelligence Machine Learning MCS 68T30 I.2.4 Knowledge Graph Embedding (KGE) is a popular approach, which aims to represent entities and relations of a knowledge graph in latent spaces. Their representations are known as embeddings. To measure the plausibility of triplets, score functions are defined over embedding spaces. Despite wide dissemination of KGE in various tasks, KGE methods have limitations in reasoning abilities. In this paper we propose a mathematical framework to compare reasoning abilities of KGE methods. We show that STransE has a higher capability than TransComplEx, and then present new STransCoRe method, which improves the STransE by combining it with the TransCoRe insights, which can reduce the STransE space complexity. |
| title | On The Expressive Power of Knowledge Graph Embedding Methods |
| topic | Artificial Intelligence Machine Learning MCS 68T30 I.2.4 |
| url | https://arxiv.org/abs/2407.16326 |