tf-gnns 0.1.6a0

A hackable graphnets library for tensorflow-keras.

Tensorflow versions and tf_gnns

tf	Tests status
2.13
2.14
2.15
2.17

Further info

There are some un-resolved bugs with the latest tensorflow versions, due to the on-going transition from keras 2 to keras 3 some of the problems are already resolved, but there are some flaky parts in the code currently. Since I develop this single-handedly, I will wait for the dust to settle with keras 3. At the moment it is recommended to use version `tensorflow==2.15` or earlier.

tf_gnns - A Hackable GraphNets library

A library for easy construction of message-passing networks in tensorflow keras. It is inspired largely by this DeepMind paper and the corresponding open-sourced library (original graph_nets library)

The tf_gnns library has no external dependencies except tensorflow 2.x (there is no support for tf 1.x graphs/sessions-based computation). It implements some alternative design constraints from graph_nets taking advantage of some facilities keras provides to make complex models easily and without large drops in performance.

tf_gnns is built to support arbitrary node/edge/global attributes and update functions. A set of convenience functions providing MLP construction with keras are also provided (i.e., handling input/output sizes for valid networks) that replaces sonnet.

The main motivation for this library was the absense of a relatively short and efficient implementation of GNNs that was explicitly created to take advantage of keras's functionalities. GNN implementations which take advantage of tensorflow_probability functionality are to be released in the future (as the one used in [2]).

Installing tf_gnns

Currently tensorflow==2.17 and tensorflow_probability==0.24 are not supported since there are some bugs introduced which I haven't resolved. All tests pass with tensorflow==2.15 and tensorflow_probability==0.22. Install with pip:

pip install tensorflow==2.15
pip install tensorflow_probability==0.22
pip install tf_gnns

Use through Docker

You can run build a dockerfile that uses tf_gnns with the following command, based on an Ubuntu22 OS:

docker build . -t tf_gnns_215 --network host  --build-arg TENSORFLOW_VERSION=2.15

The container implements some logic to sort out the necessary dependencies. Namely,

• Numpy 1.x is required for tf <= 2.14
• Keras 2 support needs to be enabled for tf >= 2.16
• The tensorflow_probability version is selected through a mapping given the tensorflow version.

Examples

tf_gnns basics

You may inspect some basic functionality on the following colab notebook:

list sorting example

(Example from the original deepmind/graph_nets library) If you are familiar with the original graph_nets library, this example will help you understand how you can transition to tf_gnns.

Sort a list of elements. This notebook and the accompanying code demonstrates how to use the Graph Nets library to learn to sort a list of elements.

A list of elements is treated as a fully connected graph between the elements. The network is trained to label the start node, and which (directed) edges correspond to the links to the next largest element, for each node.

After training, the prediction ability is tested by comparing its output to true sorted lists. Then the network's ability to generalise is tested, by using it to sort larger lists.

Performance

From some initial tests the performance of the tf_gnns library seems to be at least as good as deepmind/graph_nets when using tensor dictionaries.

Publications using tf_gnns

The library has been used so far in the following publications:

[1] Bayesian graph neural networks for strain-based crack localization

[2] Remaining Useful Life Estimation Under Uncertainty with Causal GraphNets [3] Relational VAE: A Continuous Latent Variable Model for Graph Structured Data