NeuralKG: An Open Source Library for Diverse Representation Learning of Knowledge Graphs

TL;DR

NeuralKG is an open-source Python library that simplifies the implementation and comparison of diverse knowledge graph embedding methods, including GNN and rule-based approaches, facilitating research and development in KG representation learning.

Contribution

It provides a unified, extensible framework for reproducing and developing KGE models, especially those originally in non-Python languages, with a shared community platform.

Findings

Successfully reproduces link prediction results on benchmarks

Highly configurable and modular design for model development

Supports diverse KGE methods including GNN and rule-based approaches

Abstract

NeuralKG is an open-source Python-based library for diverse representation learning of knowledge graphs. It implements three different series of Knowledge Graph Embedding (KGE) methods, including conventional KGEs, GNN-based KGEs, and Rule-based KGEs. With a unified framework, NeuralKG successfully reproduces link prediction results of these methods on benchmarks, freeing users from the laborious task of reimplementing them, especially for some methods originally written in non-python programming languages. Besides, NeuralKG is highly configurable and extensible. It provides various decoupled modules that can be mixed and adapted to each other. Thus with NeuralKG, developers and researchers can quickly implement their own designed models and obtain the optimal training methods to achieve the best performance efficiently. We built an website in http://neuralkg.zjukg.cn to organize an open and shared KG representation learning community. The source code is all publicly released at https://github.com/zjukg/NeuralKG.