[Feature request] Examples of Generative Model

[nashid]

Spektral certainly seems promising and easy to get started. Also, it has some good examples for predictive tasks. However, Spektral lacks examples of generative models.

That said, other libraries on GNN also lack examples of generative models and it would be awesome if Spektral can add generative models!

I am wondering whether there are any plans to include any of the following models:

• GraphRNN: https://github.com/JiaxuanYou/graph-generation

Also, Spektral lacks examples of Graph2Seq based models. It would be awesome to include consider any of the following Graph2Seq based generative models.

• Graph-to-Sequence Learning using Gated Graph Neural Networks, ACL’18 https://github.com/beckdaniel/acl2018_graph2seq Using MXNet

• Densely Connected Graph Convolutional Networks for Graph-to-Sequence Learning, ACL’19 https://github.com/Cartus/DCGCN Using MXNet 1.3.0

• Heterogeneous Graph Transformer for Graph-to-Sequence Learning, ACL’18 https://github.com/QAQ-v/HetGT Using OpenNMT

I'm happy to contribute as well.

[danielegrattarola]

Hi,

thanks for pointing this out, I have marked this as a feature request so that I'll eventually get around to working on it (or someone else will, hopefully). I can't give you a timeline for this, unfortunately.

Cheers

[nashid]

@danielegrattarola FYI only - OpenNMT has a GGNN implementation. https://opennmt.net/OpenNMT-py/examples/GGNN.html

I think having a similar model would be a great starting point.