Open mmpust opened 1 year ago
Hi Lukas,
very interesting approach! Is there any plan to incorporate this into the pytorch_geometric.explain module in the future? https://pytorch-geometric.readthedocs.io/en/latest/modules/explain.html
# Your code: # Create explainer explainer = explain.Explainer( model=model, adj=cg_dict["adj"], feat=cg_dict["feat"], label=cg_dict["label"], pred=cg_dict["pred"], train_idx=cg_dict["train_idx"], args=prog_args, writer=writer, print_training=True, graph_mode=graph_mode, graph_idx=prog_args.graph_idx, )
My input graphs are PyTorch Data objects, e.g. Data(x=x, edge_index=edge_index, ...) Is there an straightforward way to test your contrast method on this input type? Thanks!
Data(x=x, edge_index=edge_index, ...)
Hi Lukas,
very interesting approach! Is there any plan to incorporate this into the pytorch_geometric.explain module in the future? https://pytorch-geometric.readthedocs.io/en/latest/modules/explain.html
My input graphs are PyTorch Data objects, e.g.
Data(x=x, edge_index=edge_index, ...)
Is there an straightforward way to test your contrast method on this input type? Thanks!