We’ve just released Neo4j’s Graph Data Science Library version 1.4, which improves predictions for better decisions and innovation with data you already have. It now includes graph-native machine learning, which enables you to uncover insights that you didn’t even know to look for.
We support Fast RP, Node2Vec and most impressively GraphSAGE embedding algorithms. Have a look at the cheat sheet below to see which algorithm is best to use for your use case.
To really capitalize on what GraphSAGE can do, we added a catalog to store and reference these predictive models. This model catalog lives in the Neo4j analytics workspace and contains versioning and time stamp information.
Want to dive deeper and test yourself?
- Check out the GraphSAGE session from our recent NODES event.
- To get your hands on the latest from the GDS Library, visit our download center or go straight to our GitHub repository.
- Join the webinar Graph Embeddings for Graph-Native Machine Learning on December 3 with me and Alicia Frame! We’ll be answering your questions live throughout the webinar.