Easy Representation for Knowledge Graphs!
Knowledge Graph Representation Learning
Easy & Diverse
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. 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.
Knowledge Graph Embeddings
NeuralKG contains various Knowledge Graph Embedding methods and will be continuous updated with new KGEs.[Learn more]
Rule Enhanced Representations
NeuralKG contains a series of rule enhanced representation learning methods, making neural-symbolic reasoning easy. [Learn more]
Graph Neural Network Models
NeuralKG contains the most recently proposed graph neural network based representation learning methods for knowledge graph.[Learn more]
NeuralKG provides various functional modules and organizes all components by consistent frameworks.
Decoupled Modules. NeuralKG provides various decoupled modules that can be mixed and adapted to each other.
Diverse types of Models. NeuralKG includes conventional KGEs, GNN-based KGEs and Rule-injected KGEs.
What you can do with NeuralKG?
Knowledge Graphs are widely used in tasks related to entities, such as link prediction and recommendation. It also widely used in many domain applications such as e-commerce and bio-informatics. With NeuralKG, you can easy conduct reasoning over entities.
NeuralKG provide flexible methods for representing entities and relations in vector space and could be easily utilized in task models.[More]
With domain KGs, NeuralKG provides easy implementation to discover semantic relationships and relatedness between entities.[More]
We constantly write blogs related to NeuralKG, including updates of the toolkits, hands-on domain applications, project experience sharing, etc.
NeuralKG for KGQA
Knowledge Graphs (KG) consists of a large number of entities and relations among them as typed edges…
NeuralKG reproduces the conventional knowledge graph embedding models, namely C-KGEs, which are desi…
GNN-based KGE methods usually add a graph neural network (GNN) structure after the embeddings of ent…
NeuralKG core team provides long-term technical support. You can follow or contact us via Github, Gitee, Twitter, Email, etc. We welcome all contributions that will make NeuralKG better. Please feel free to contact us if there are any good suggestions.
NeuralKG Core Team
Wen Zhang, Xiangnan Chen, Zhen Yao, Mingyang Chen, Yushan Zhu, Hongtao Yu, Yufeng Huang, Zezhong Xu, Yajing Xu, Ningyu Zhang, Huajun Chen