# thunlp/openke

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/thunlp-openke).**

_How this analysis was created: the description and tags below were written by an AI model that read this project's README and public documentation pages; stars, license and language come straight from the GitHub API. The model does not read the source code._

4,058 stars · 986 forks · Python

## Links

- GitHub: https://github.com/thunlp/OpenKE
- awesome-repositories: https://awesome-repositories.com/repository/thunlp-openke.md

## Topics

`knowledge-embedding`

## Description

OpenKE is a knowledge graph embedding framework designed to transform structured knowledge graphs into low-dimensional vector representations. It functions as a library for representation learning and a toolset for converting entities and relations into numerical embeddings.

The project includes a link prediction engine to evaluate the likelihood of relationships between entities and identify missing facts in large-scale graphs. It provides a dedicated preprocessing tool to map raw entity and relation strings into numerical identifiers for machine learning training.

The framework's capabilities cover the full lifecycle of graph embedding, including data preprocessing, representation learning, and link prediction analysis.

## Tags

### Part of an Awesome List

- [Knowledge Graph Embeddings](https://awesome-repositories.com/f/awesome-lists/ai/knowledge-graph-embeddings.md) — Provides a comprehensive framework for learning low-dimensional vector representations of structured knowledge graphs.
- [Graph Representation Learning](https://awesome-repositories.com/f/awesome-lists/ai/graph-representation-learning.md) — Transforms structured knowledge graphs into low-dimensional embeddings using specialized representation learning models. ([source](https://github.com/thunlp/openke#readme))
- [Preprocessing Utilities](https://awesome-repositories.com/f/awesome-lists/devtools/knowledge-graph-tools/preprocessing-utilities.md) — Provides a utility to convert raw entity and relation names into numerical identifiers for training.
- [Knowledge Graph Tools](https://awesome-repositories.com/f/awesome-lists/devtools/knowledge-graph-tools.md) — Provides a comprehensive platform for knowledge graph embedding and representation learning.

### Artificial Intelligence & ML

- [Embedding-Based Knowledge Representation Learning](https://awesome-repositories.com/f/artificial-intelligence-ml/embedding-based-knowledge-representation-learning.md) — Learns numerical representations of entities and relations to capture semantic patterns within a knowledge base.
- [Embedding-Based Representations](https://awesome-repositories.com/f/artificial-intelligence-ml/fact-based-knowledge-representation/embedding-based-representations.md) — Provides the mechanism to map entities and relations into low-dimensional vectors for semantic similarity analysis.
- [Link Prediction](https://awesome-repositories.com/f/artificial-intelligence-ml/model-predictions/link-prediction.md) — Calculates the probability of relationships between entities using geometric or algebraic score functions to predict missing links.
- [Negative](https://awesome-repositories.com/f/artificial-intelligence-ml/sampling-strategies/negative.md) — Generates corrupted triplets using random sampling to improve the model's ability to discriminate between true and false facts.
- [Stochastic Gradient Descent](https://awesome-repositories.com/f/artificial-intelligence-ml/stochastic-gradient-descent.md) — Employs stochastic gradient descent to iteratively update embedding vectors by minimizing a loss function.

### Data & Databases

- [Embedding Preprocessing](https://awesome-repositories.com/f/data-databases/knowledge-graph-indexers/embedding-preprocessing.md) — Transforms raw entity and relation strings into numerical identifiers required for machine learning training.
- [Triplet Preparation](https://awesome-repositories.com/f/data-databases/knowledge-graph-indexers/triplet-preparation.md) — Converts raw entity and relation names into numerical identifiers to prepare training and testing triplets. ([source](https://github.com/thunlp/openke#readme))
- [Knowledge Graph Recommendations](https://awesome-repositories.com/f/data-databases/knowledge-graph-indexers/knowledge-graph-builders/knowledge-graph-recommendations.md) — Identifies missing facts by analyzing the likelihood of relationships between entities in a structured graph. ([source](https://github.com/thunlp/openke#readme))
