.png){kind=icon}
Return
MEGA: Meta-Graph Augmented Pre-Training Model for Knowledge Graph Completion
.png){kind=icon}
PRE
AI
DOI：10.1145/3617379.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Nowadays, a large number of Knowledge Graph Completion (KGC) methods have been proposed by using embedding based manners, to overcome the incompleteness problem faced with knowledge graph (KG). One important recent innovation in Natural Language Processing (NLP) domain is the employ of deep neural models that make the most of pre-training, culminating in BERT, the most popular example of this line of approaches today. Recently, a series of new KGC methods introducing a pre-trained language model, such as KG-BERT, have been developed and released compelling performance. However, previous pre-training based KGC methods usually train the model by using simple training task and only utilize one-hop relational signals in KG, which leads that they cannot model high-order semantic contexts and multi-hop complex relatedness. To overcome this problem, this article presents a novel pre-training framework for KGC task, which especially consists of both one-hop relation level task (low-order) and multi-hop meta-graph level task (high-order). Hence, the proposed method can capture not only the elaborate sub-graph structure but also the subtle semantic information on the given KG. The empirical results show the efficiency of the proposed method on the widely used real-world datasets.
Keywords:
Knowledge graph completion
meta-graph
pre-training model
multi-task learning
semantic enhancement
Journal
IF:
4.8
Papers:
1.3K
Citations:
4.4K
Organization
No organization information available
Cited Papers
.png){kind=icon}
ShareSaveShareSave
ShareSaveInSight coordinates determination from direct-to-Earth radio-tracking and Mars topography model
PREAI
ShareSaveShareSave
View more