[pre-commit.ci] auto fixes from pre-commit.com hooks

for more information, see https://pre-commit.ci

examples/contrib/README.md

@@ -2,9 +2,9 @@
 
 This directory contains examples demonstrating the use of `torch_geometric.contrib` package. The `contrib` package of PyTorch Geometric is a staging area for early-stage, experimental code. Modules included here might be moved to the main library in the future.
 
-| Example                                                     | Description                                                                                                                          |
-| ----------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------ |
-| [`rbcd_attack_poisoning.py`](./rbcd_attack_poisoning.py)    | Demonstrates the RBCD (Resource-Based Critical Data) attack with data poisoning strategies. |
-| [`pgm_explainer_node_classification.py`](./pgm_explainer_node_classification.py) | Showcases the PGM (Probabilistic Graphical Model) Explainer for node classification tasks.   |
-| [`rbcd_attack.py`](./rbcd_attack.py)                        | Provides an example of an RBCD attack in network settings.              |
-| [`pgm_explainer_graph_classification.py`](./pgm_explainer_graph_classification.py) | Details the application of the PGM Explainer for graph classification.        |
+| Example                                                                            | Description                                                                                 |
+| ---------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------- |
+| [`rbcd_attack_poisoning.py`](./rbcd_attack_poisoning.py)                           | Demonstrates the RBCD (Resource-Based Critical Data) attack with data poisoning strategies. |
+| [`pgm_explainer_node_classification.py`](./pgm_explainer_node_classification.py)   | Showcases the PGM (Probabilistic Graphical Model) Explainer for node classification tasks.  |
+| [`rbcd_attack.py`](./rbcd_attack.py)                                               | Provides an example of an RBCD attack in network settings.                                  |
+| [`pgm_explainer_graph_classification.py`](./pgm_explainer_graph_classification.py) | Details the application of the PGM Explainer for graph classification.                      |

examples/distributed/README.md

@@ -3,4 +3,4 @@
 This directory contains examples for distributed graph learning. The examples are organized into two subdirectories:
 
 1. `graphlearn_for_pytorch`: Using GraphLearn-for-PyTorch (GLT) for Distributed Training with PyG.
-2. `pyg`: Distributed graph learning with PyG's `distributed` package.
+1. `pyg`: Distributed graph learning with PyG's `distributed` package.

examples/explain/README.md

@@ -2,12 +2,11 @@
 
 This directory contains examples demonstrating the use of `torch_geometric.explain` package. The `explain` package of PyTorch Geometric provides a set of tools to explain the predictions of a PyG model or to explain the underlying phenomenon of a dataset.
 
-| Example                                            | Description                                                                                   |
-| -------------------------------------------------- | --------------------------------------------------------------------------------------------- |
-| [`captum_explainer.py`](./captum_explainer.py)     | Demonstrates the use of Captum-based explainer for explaining Graph Neural Networks (GNN) model in node classification.                          |
-| [`captum_explainer_hetero_link.py`](./captum_explainer_hetero_link.py) | Demonstrates the use of Captum-based explainer for explaining GNN model in heterogenous link prediction.               |
-| [`gnn_explainer.py`](./gnn_explainer.py)           | Shows GNNExplainer applied to the Cora dataset for understanding GNN model.  |
-| [`gnn_explainer_ba_shapes.py`](./gnn_explainer_ba_shapes.py) | Shows GNNExplainer applied to the BA-Shapes dataset for understanding GNN model.       |
-| [`gnn_explainer_link_pred.py`](./gnn_explainer_link_pred.py) | Demonstrates the use of GNNExplainer for explaining GNN model in link prediction.                     |
-| [`graphmask_explainer.py`](./graphmask_explainer.py) | Demonstrates the use of GraphMask-Explainer for explaining GNN model in node classification. |
-
+| Example                                                                | Description                                                                                                             |
+| ---------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------- |
+| [`captum_explainer.py`](./captum_explainer.py)                         | Demonstrates the use of Captum-based explainer for explaining Graph Neural Networks (GNN) model in node classification. |
+| [`captum_explainer_hetero_link.py`](./captum_explainer_hetero_link.py) | Demonstrates the use of Captum-based explainer for explaining GNN model in heterogenous link prediction.                |
+| [`gnn_explainer.py`](./gnn_explainer.py)                               | Shows GNNExplainer applied to the Cora dataset for understanding GNN model.                                             |
+| [`gnn_explainer_ba_shapes.py`](./gnn_explainer_ba_shapes.py)           | Shows GNNExplainer applied to the BA-Shapes dataset for understanding GNN model.                                        |
+| [`gnn_explainer_link_pred.py`](./gnn_explainer_link_pred.py)           | Demonstrates the use of GNNExplainer for explaining GNN model in link prediction.                                       |
+| [`graphmask_explainer.py`](./graphmask_explainer.py)                   | Demonstrates the use of GraphMask-Explainer for explaining GNN model in node classification.                            |

examples/jit/README.md

@@ -2,9 +2,9 @@
 
 This directory contains examples demonstrating the use of Just-In-Time (JIT) compilation in different Graph Neural Network (GNN) models.
 
-| Example                | Description                                                                                     |
-| ---------------------- | ----------------------------------------------------------------------------------------------- |
+| Example                | Description                                                                              |
+| ---------------------- | ---------------------------------------------------------------------------------------- |
 | [`film.py`](./film.py) | Demonstrates the use of JIT compilation in [GNN-FiLM](https://arxiv.org/abs/1906.12192). |
-| [`gat.py`](./gat.py)   | Demonstrates the use of JIT compilation in GAT. |
-| [`gcn.py`](./gcn.py)   | Demonstrates the use of JIT compilation in GCN. |
-| [`gin.py`](./gin.py)   | Demonstrates the use of JIT compilation in GIN. |
+| [`gat.py`](./gat.py)   | Demonstrates the use of JIT compilation in GAT.                                          |
+| [`gcn.py`](./gcn.py)   | Demonstrates the use of JIT compilation in GCN.                                          |
+| [`gin.py`](./gin.py)   | Demonstrates the use of JIT compilation in GIN.                                          |

examples/pytorch_ignite/README.md

@@ -2,6 +2,6 @@
 
 This directory demonstrates the application of PyTorch Ignite in the context of Graph Neural Networks (GNNs).
 
-| Example                              | Description                                                                                       |
-| ------------------------------------ | ------------------------------------------------------------------------------------------------- |
-| [`gin.py`](./gin.py)                 | This script demonstrates how to implement the Graph Isomorphism Network (GIN) model using PyTorch Ignite. |
+| Example              | Description                                                                                               |
+| -------------------- | --------------------------------------------------------------------------------------------------------- |
+| [`gin.py`](./gin.py) | This script demonstrates how to implement the Graph Isomorphism Network (GIN) model using PyTorch Ignite. |

examples/pytorch_lightning/README.md

@@ -2,8 +2,8 @@
 
 This directory provides examples showcasing the integration of PyTorch Geometric with [PyTorch Lightning](https://github.com/Lightning-AI/pytorch-lightning).
 
-| Example                              | Description                                                                                       |
-| ------------------------------------ | ------------------------------------------------------------------------------------------------- |
-| [`gin.py`](./gin.py)                 | Demonstrates how to combine PyTorch Geometric and PyTorch Lightning for implementing the Graph Isomorphism Network (GIN) model. |
-| [`graph_sage.py`](./graph_sage.py)   | Demonstrates how to combine PyTorch Geometric and PyTorch Lightning for implementing the GraphSAGE model, suitable for scalable graph-structured data processing. |
-| [`relational_gnn.py`](./relational_gnn.py) | Demonstrates the use of PyTorch Geometric and PyTorch Lightning for building a Relational Graph Neural Network, emphasizing handling relational data in graphs. |
+| Example                                    | Description                                                                                                                                                       |
+| ------------------------------------------ | ----------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| [`gin.py`](./gin.py)                       | Demonstrates how to combine PyTorch Geometric and PyTorch Lightning for implementing the Graph Isomorphism Network (GIN) model.                                   |
+| [`graph_sage.py`](./graph_sage.py)         | Demonstrates how to combine PyTorch Geometric and PyTorch Lightning for implementing the GraphSAGE model, suitable for scalable graph-structured data processing. |
+| [`relational_gnn.py`](./relational_gnn.py) | Demonstrates the use of PyTorch Geometric and PyTorch Lightning for building a Relational Graph Neural Network, emphasizing handling relational data in graphs.   |