$\mu\text{KG}$: A Library for Multi-source Knowledge Graph Embeddings and Applications

TL;DR

$ ext{μKG}$ is a comprehensive open-source Python library supporting multi-source knowledge graph embeddings, multiple models, tasks, and computing modes, facilitating research and applications in knowledge graph representation learning.

Contribution

The paper introduces $ ext{μKG}$, a versatile library that integrates 26 models, multiple tasks, and parallel computing, surpassing existing tools in scope and usability.

Findings

Joint embeddings improve downstream tasks like question answering.

$ ext{μKG}$ enables thorough model comparison and analysis.

Supports multi-source knowledge graphs and various embedding tasks.

Abstract

This paper presents $\mu\text{KG}$, an open-source Python library for representation learning over knowledge graphs. $\mu\text{KG}$ 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. $\mu\text{KG}$ provides advanced implementations of embedding techniques with simplified pipelines of different tasks. It also comes with high-quality documentation for ease of use. $\mu\text{KG}$ 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 $\mu\text{KG}$.