mdanb
mdanb
@weihua916 Can you clarify the format for the files? I'm also wondering about this.
@wangzeyu135798 although they don't test all five together, they do mention that they tried combining contextpred and masking, and that it didn't improve performance
@TMorville I have the same problem. What did you end up doing?
Any updates on this? For me what worked (partially) was to run `set_cfg(cfg)` as @do-lania suggested
@nd7141 have you figured out how to run it on your own data? EDIT: It seems like [Pytorch geometric](https://pytorch-geometric.readthedocs.io/en/latest/notes/introduction.html) have this [implemented](https://pytorch-geometric.readthedocs.io/en/latest/_modules/torch_geometric/nn/models/gnn_explainer.html)!