#18 · Primary category： Classical Machine Learning Frameworks
AmpliGraph
Python library for Representation Learning on Knowledge Graphs https://docs.ampligraph.org
Project last updated：08/06/26
GitHub Stars
2.2K
Forks
259
Contributors
21
License
Apache-2.0
Why we included this project
AmpliGraph is built for a specific problem: when your knowledge graph is missing statements, it learns vector embeddings for entities and relations and scores candidate links to predict what belongs. That makes it useful for completing sparse graphs, clustering similar concepts, and spotting near-duplicate entities without writing scoring logic yourself. The library bundles well-known embedding models like TransE, DistMult, ComplEx, and RotatE behind a Keras-style API on TensorFlow 2, so training and evaluating a model takes little code and swapping models is straightforward. Teams that maintain taxonomies, product catalogs, or research corpora as graphs will find its discovery helpers handy for surfacing novel facts and similar entities. Once your data is formatted as subject-predicate-object triples, the learning curve is modest.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
scikit-learn
scikit-learn: machine learning in Python
pyod
A Python library for anomaly detection across tabular, time series, graph, text, image, and audio data. 60+ detectors, benchmark-backed ADEngine orchestration, and an agentic workflow for AI agents.
dowhy
DoWhy is a Python library for causal inference that supports explicit modeling and testing of causal assumptions. DoWhy is based on a unified language for causal inference, combining causal graphical models and potential outcomes frameworks.
umap
Uniform Manifold Approximation and Projection
imbalanced-learn
A Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning