论文标题
$μ\ text {kg} $：用于多源知识图形嵌入和应用程序的库
$μ\text{KG}$: A Library for Multi-source Knowledge Graph Embeddings and Applications
论文作者
论文摘要
本文介绍了$μ\ text {kg} $，这是一个开源python库，用于在知识图上进行表示。 $μ\ text {kg} $支持通过多源知识图（以及单个知识图），多个深度学习库（Pytorch和Tensorflow2），多个嵌入任务（链接预测，实体对齐，实体键入，多源链接预测）和多个平行模式（多数计算）（多）和多名计算。它目前实现26个流行知识图嵌入模型，并支持16个基准数据集。 $μ\ text {kg} $提供了具有不同任务的简化管道的嵌入技术的高级实现。它还带有高质量的文档，以易于使用。 $μ\ text {kg} $比嵌入库的现有知识图更全面。它对于对各种嵌入模型和任务进行彻底比较和分析非常有用。我们表明，共同学习的嵌入可以极大地帮助知识驱动的下游任务，例如多跳知识图形答案。我们将与相关领域的最新发展保持一致，并将其纳入$μ\ text {kg} $中。
This paper presents $μ\text{KG}$, an open-source Python library for representation learning over knowledge graphs. $μ\text{KG}$ supports joint representation learning over multi-source knowledge graphs (and also a single knowledge graph), multiple deep learning libraries (PyTorch and TensorFlow2), multiple embedding tasks (link prediction, entity alignment, entity typing, and multi-source link prediction), and multiple parallel computing modes (multi-process and multi-GPU computing). It currently implements 26 popular knowledge graph embedding models and supports 16 benchmark datasets. $μ\text{KG}$ provides advanced implementations of embedding techniques with simplified pipelines of different tasks. It also comes with high-quality documentation for ease of use. $μ\text{KG}$ is more comprehensive than existing knowledge graph embedding libraries. It is useful for a thorough comparison and analysis of various embedding models and tasks. We show that the jointly learned embeddings can greatly help knowledge-powered downstream tasks, such as multi-hop knowledge graph question answering. We will stay abreast of the latest developments in the related fields and incorporate them into $μ\text{KG}$.
