While experimenting with various models while adjusting SbmBeamHandler.benchmarker_wrappers in sbm_config_mwe.gin, I found that models such as GIN, MLP, APPNP, SGC, and GATv2 in basic_gnn.py did not run except for GAT and GCN GraphSAGE. All raises "TypeError: 'NoneType' object is not subscriptable [while running 'Benchmark Simple GCN.']".
How to solve this case?
I modified SbmBeamHandler.benchmarker_wrappers as below to run ./main_local_mwe.sh
SbmBeamHandler.benchmarker_wrappers = [
@GAT_/NNNodeBenchmark,
@GIN_/NNNodeBenchmark,
@APPNP_/NNNodeBenchmark,
@GATv2_/NNNodeBenchmark,
]

Docker is not available in the Colab.
How should I use it in Colaboratory?

I am interested in analyzing some dataset's graph and node label metrics.
However, some of those did not include a reference, such as graphworld/src/graph_world/metrics/graph_metrics.py/feature_homogeneity.
Is it possible to include where these functions (metrics) come from and what they mean?
Thank you!

Is there a way to save all the benchmark graphs generated (preferably in networkx graph format)?