StellarGraph is a Python library for machine learning on graphs and networks. The StellarGraph library offers state-of-the-art algorithms for graph machine learning, making it easy to discover patterns and answer questions about graph-structured data. Graph-structured data represent entities as nodes (or vertices) and relationships between them as edges (or links), and can include data associated with either as attributes. For example, a graph can contain people as nodes and friendships between them as links, with data like a person's age and the date a friendship was established. StellarGraph is built on TensorFlow 2 and its Keras high-level API, as well as Pandas and NumPy.

Is it just a way to feed the ego? In fact, I don't think people start building libraries just to mark their territory. Rather, I think each library aims to fill a gap or fill a particular need. This means that, depending on the problem I'm facing, I will judge one library to be better than another. Thus I need a problem.

We believe graph machine learning is at the intersection of art and science. We use cutting-edge engineering and data science to help reveal insight from data, and find innovative ways to enable our users to get the most from the experience. The StellarGraph team consists of engineers, data scientists, researchers, devops, product managers, and UX designers all driven to build amazing technology. Get in touch to meet the team and learn how we can partner.