SMiLE: Schema-augmented Multi-level Contrastive Learning for Knowledge Graph Link Prediction
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2022
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909126174441472 |
|---|---|
| author | Peng, Miao Liu, Ben Xie, Qianqian Xu, Wenjie Wang, Hua Peng, Min |
| author_facet | Peng, Miao Liu, Ben Xie, Qianqian Xu, Wenjie Wang, Hua Peng, Min |
| contents | Link prediction is the task of inferring missing links between entities in knowledge graphs. Embedding-based methods have shown effectiveness in addressing this problem by modeling relational patterns in triples. However, the link prediction task often requires contextual information in entity neighborhoods, while most existing embedding-based methods fail to capture it. Additionally, little attention is paid to the diversity of entity representations in different contexts, which often leads to false prediction results. In this situation, we consider that the schema of knowledge graph contains the specific contextual information, and it is beneficial for preserving the consistency of entities across contexts. In this paper, we propose a novel Schema-augmented Multi-level contrastive LEarning framework (SMiLE) to conduct knowledge graph link prediction. Specifically, we first exploit network schema as the prior constraint to sample negatives and pre-train our model by employing a multi-level contrastive learning method to yield both prior schema and contextual information. Then we fine-tune our model under the supervision of individual triples to learn subtler representations for link prediction. Extensive experimental results on four knowledge graph datasets with thorough analysis of each component demonstrate the effectiveness of our proposed framework against state-of-the-art baselines. The implementation of SMiLE is available at https://github.com/GKNL/SMiLE. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2210_04870 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | SMiLE: Schema-augmented Multi-level Contrastive Learning for Knowledge Graph Link Prediction Peng, Miao Liu, Ben Xie, Qianqian Xu, Wenjie Wang, Hua Peng, Min Computation and Language Artificial Intelligence Link prediction is the task of inferring missing links between entities in knowledge graphs. Embedding-based methods have shown effectiveness in addressing this problem by modeling relational patterns in triples. However, the link prediction task often requires contextual information in entity neighborhoods, while most existing embedding-based methods fail to capture it. Additionally, little attention is paid to the diversity of entity representations in different contexts, which often leads to false prediction results. In this situation, we consider that the schema of knowledge graph contains the specific contextual information, and it is beneficial for preserving the consistency of entities across contexts. In this paper, we propose a novel Schema-augmented Multi-level contrastive LEarning framework (SMiLE) to conduct knowledge graph link prediction. Specifically, we first exploit network schema as the prior constraint to sample negatives and pre-train our model by employing a multi-level contrastive learning method to yield both prior schema and contextual information. Then we fine-tune our model under the supervision of individual triples to learn subtler representations for link prediction. Extensive experimental results on four knowledge graph datasets with thorough analysis of each component demonstrate the effectiveness of our proposed framework against state-of-the-art baselines. The implementation of SMiLE is available at https://github.com/GKNL/SMiLE. |
| title | SMiLE: Schema-augmented Multi-level Contrastive Learning for Knowledge Graph Link Prediction |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2210.04870 |