Can I read MEGA: Meta-Graph Augmented Pre-Training Model for Knowledge Graph Completion on EtoBox?

MEGA: Meta-Graph Augmented Pre-Training Model for Knowledge Graph Completion by Yashen Wang; Xiaoye Ouyang; Dayu Guo; Xiaoling Zhu is a Computer Science article available to read on EtoBox.

What is MEGA: Meta-Graph Augmented Pre-Training Model for Knowledge Graph Completion about?

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 em

Who reads MEGA: Meta-Graph Augmented Pre-Training Model for Knowledge Graph Completion?

Author

Yashen Wang; Xiaoye Ouyang; Dayu Guo; Xiaoling Zhu

Publisher

ACM

Published

2023

Field

Computer Science (Physical Sciences)