The year is 2022, and graph machine learning is one of the rising trends in data analytics. While Neo4j has a Graph Data Science library that supports multiple graph algorithms and machine learning workflows, sometimes you want to export data from Neo4j and run it through your favorite machine learning frameworks like PyTorch or TensorFlow. In that scenario, you want to be able to export data from Neo4j in a fast and scalable way. But, unfortunately, using the Neo4j Python driver is not the most efficient way of retrieving data. However, no need to worry, Dave Voutila has got your back.

In my previous post we discussed the purpose and nature of graph embeddings. The main idea is that to do machine learning on a graph we need to convert the graph into a series of vectors (embeddings) that we can then use to train our machine learning (ML) models. The catch is that graph embeddings can be difficult to tune. Similar to other ways to create embeddings and the models they are used for, there are a lot of hyperparameters that we need to consider and optimizing them to the specific application takes time. The subject of tuning the embeddings is something I will save for a future post.