.png){kind=icon}
.png){kind=icon}
Return
EwLoss: A Exponential Weighted Loss Function for Knowledge Graph Embedding Models
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2023.3322204.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Knowledge graphs have been widely used in various domains such as intelligent question answering, information retrieval, transportation, medicine, e-commerce, and others, and have achieved significant success. To support these applications with a high-quality vector representation, numerous studies have proposed various knowledge graph embedding (KGE) models. However, most of these models primarily focus on the design of new scoring functions, disregarding the crucial role of the loss function during the model training stage. In light of this, we propose a new exponential weight coefficient loss function, named EwLoss, which can be incorporated into any typical KGE model. This loss function enables the model to better distinguish between triplets that are otherwise difficult to differentiate. Consequently, the model can learn the features of these challenging triplets more effectively, leading to improved embedding vectors. By conducting experiments on four commonly used data sets, where EwLoss is applied to six representative models, we demonstrate the superiority of EwLoss in distinguishing such hard-to-distinguish triplets. Moreover, we observe that the performance of the embedding models is significantly enhanced when utilizing EwLoss.
Keywords:
Difficult-to-distinguish samples
easy-to-distinguish samples
knowledge graph
knowledge graph embedding model
loss function
negative triplets
negative sampling