• using TF 2.0
• using tf api, rather than the keras
• save model
• save checkpoints

Overall, if we have two sparse matrices, then the multiplication should be sparse as well, in order to improve the performance.
Example like https://github.com/scipy/scipy/blob/a03f15fe43cb68c132192af22deb73b69ef201bf/scipy/sparse/compressed.py#L496-L530
And the spspmm function in the pytorch-sparse package. https://github.com/rusty1s/pytorch_sparse/blob/master/torch_sparse/spspmm.py

While in TF2.x, no matter the matmul (sparsetensor, sparsetensor) or the sparse.sparse_dense_matmul(sparsetensor, tensor) function return a Tensor instead of SparseTensor.

This is the one of the reasons why the PyG is much faster in the implementation of tensorflow or DGL.

Performance issue need to be resolved.

Trying to save with:
tf.saved_model.save(gcn, "trained_model/")

Gives the below error:

Traceback (most recent call last):
File "train_gcn.py", line 81, in
app.run(main)
File "/home/mtare/Documents/Projects/document-trainer-gcn/venv/lib/python3.6/site-packages/absl/app.py", line 299, in run
_run_main(main, args)
File "/home/mtare/Documents/Projects/document-trainer-gcn/venv/lib/python3.6/site-packages/absl/app.py", line 250, in _run_main
sys.exit(main(argv))
File "train_gcn.py", line 70, in main
tf.saved_model.save(gcn, "trained_model/")
File "/home/mtare/Documents/Projects/document-trainer-gcn/venv/lib/python3.6/site-packages/tensorflow/python/saved_model/save.py", line 951, in save
obj, export_dir, signatures, options, meta_graph_def)
File "/home/mtare/Documents/Projects/document-trainer-gcn/venv/lib/python3.6/site-packages/tensorflow/python/saved_model/save.py", line 1001, in _build_meta_graph
"Expected a Trackable object for export, got {}.".format(obj))
ValueError: Expected a Trackable object for export, got <models.gcn.GCN object at 0x7fd6651fd908>.