Introducing TensorFlow Graph Neural Networks

Today, we are excited to release TensorFlow Graph Neural Networks (GNNs), a library designed to make it easy to work with graph structured data using TensorFlow. We have used an earlier version of this library in production at Google in a variety of contexts (for example, spam and anomaly detection, traffic estimation, YouTube content labeling) and as a component in our scalable graph mining pipelines. In particular, given the myriad types of data at Google, our library was designed with heterogeneous graphs in mind.

We are releasing this library with the intention to encourage collaborations with researchers in industry.

11 Likes

Can we use the graph tag in the forum or that tag was for the TF graph and related and we need to introduce a new tag?

1 Like

After looking at the repository and the content, I think GNN or TF-GNN label would be more appropriate.

Also, need to add tutorials (initial guides are there) section.