StellarGraph is a commercial grade, open source
graph machine learning library written in Python for
data scientists, analysts and data engineers.
Many real-world datasets can be naturally represented as graphs, with nodes representing entities and links representing
relationships or interactions between entities.
In predictive tasks, this graph representation of data
can help improve the predictive power if the underlying graph structure can be fully utilised by machine learning algorithms.
But bridging the gap between graph analytics tools and
machine learning frameworks can be challenging.
We've developed an open-source python library to democratise machine learning on graphs for data scientists, analysts and data engineers wanting to experiment with graph machine learning techniques, and/or apply them to their graph-structured data.
ALGORITHMS / CAPABILITIES
Multiple variants of Graph Neural Networks (GCN, GAT, GraphSAGE, GraphWave, APPNP)
Support for both homogeneous and heterogeneous graphs
Probabilistic inference and model calibration
Comprehensive demos including node classification, link prediction, unsupervised representation learning / graph embeddings, and interpretability.
Python | TensorFlow | Keras | NetworkX | scikit-learn
Free to use
(Apache 2.0 license)
and maintained by the StellarGraph team
EASY TO USE
Modular and extendable Python code, with a comprehensive set of demos
Research backed, engineering-proven algorithms