Knowledge Representation Learning Papers
A curated collection of must-read academic papers on knowledge representation learning and knowledge embedding, with an associated open-source toolkit.
What is Knowledge Representation Learning Papers?
KRLPapers is a curated repository of academic papers focused on Knowledge Representation Learning (KRL) and Knowledge Embedding (KE). It compiles must-read research that explores methods for embedding entities and relations from knowledge graphs into continuous vector spaces, enabling tasks like link prediction, knowledge base completion, and relational reasoning. The project serves as a reference hub for the latest advancements and foundational work in the field.
Researchers, graduate students, and machine learning engineers working on knowledge graphs, representation learning, or semantic AI who need a structured overview of seminal and state-of-the-art KRL/KE literature.
It provides a centralized, vetted collection of papers that saves time in literature review, highlights key models and trends, and is maintained by contributors from a leading research institution (Tsinghua NLP). Its association with the OpenKE toolkit also offers a practical bridge from theory to implementation.
Overview
Must-read papers on knowledge representation learning (KRL) / knowledge embedding (KE)
Use Cases
Best For
- Researchers conducting literature reviews on knowledge graph embeddings
Related Projects
Found a gem we're missing?
Open-Awesome is built by the community, for the community. Submit a project, suggest an awesome list, or help improve the catalog on GitHub.
