[GraphBolt][PyG] Support for Heterogeneous Graphs in to_pyg_data #7711 Open mfbalin closed this as completed in #7745 Aug 26, 2024 mfbalin changed the title [GraphBolt][PyG] Add gb.convert_to_pyg. [GraphBolt][PyG] Add SampledSubgraph.to_pyg. Aug 26, 2024 Sign...
nn.models.graph_mixer import ( LinkEncoder, NodeEncoder, get_latest_k_edge_attrs, get_latest_k_edge_attr, ) @@ -14,6 +14,7 @@ def test_node_encoder(): seed_time = torch.tensor([2, 2, 2, 2]) encoder = NodeEncoder(time_window=2) encoder.reset_parameters() assert str(encoder...
🚀 The feature, motivation and pitch I wonder how to train AttributedGraphDataset. I cannot find any examples of it. I met some problems when I tried to write it by myself. dataset = AttributedGraphDataset(conf.root, "mag") data.x.train_i...
According to the doc Furthermore, tensors passed to [propagate()](https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#torch_geometric.nn.conv.MessagePassing.propagate) can be mapped to the respective nodes and by appending _i or _j to the variable name, .e.g. x_i and x...
❓ Questions & Help Hi, I'm new to pytorch_geometric, while trying to call knn_graph() I encountered the following error: TypeError: knn_graph() takes from 2 to 6 positional arguments but 7 were given It is raises from the initialization ...