updated changelog and intro comment

CHANGELOG.md

@@ -851,6 +851,8 @@ The format is based on [Keep a Changelog](http://keepachangelog.com/en/1.0.0/).
 - Fixed mini-batching with empty lists as attributes ([#4293](https://github.com/pyg-team/pytorch_geometric/pull/4293))
 - Fixed a bug in which `GCNConv` could not be combined with `to_hetero` on heterogeneous graphs with one node type ([#4279](https://github.com/pyg-team/pytorch_geometric/pull/4279))
 - Added a scheduler to the Graph Sage OGBN Example [#9877](https://github.com/pyg-team/pytorch_geometric/pull/9877)
+- Added Perforated AI OGBN example to examples repository [#9926](https://github.com/pyg-team/pytorch_geometric/pull/9926)
+
 
 ### Removed
 

examples/ogbn_train_perforatedai.py

@@ -20,51 +20,6 @@
 
 
 
-'''
-This PR is to include an example of how Perforated Backpropagation can be used to improve pytorch_geometric models.  As well as adding a scheduler to the original example.  Both of which improve upon the original results.
-
-Run docker from torch_geometric directory
-
-   docker run --gpus all -i --shm-size=8g -v .:/pai -w /pai -t nvcr.io/nvidia/pyg:24.11-py3 /bin/bash
-
-Within Docker
-
-    pip install -e .
-    cd examples
-    pip install PAI wheel file
-    
-Run original with:
-
-    CUDA_VISIBLE_DEVICES=0 python ogbn_train_original.py --dataset ogbn-products --batch_size 128
-
-Results:
-
-    Test Accuracy: 75.52%
-    
-Run original scheduler with:
-
-    CUDA_VISIBLE_DEVICES=0 python ogbn_train_scheduler.py --dataset ogbn-products --batch_size 128
-
-Results:
-
-    Test Accuracy: 77.51%
-    
-    
-Run PAI with:
-
-    CUDA_VISIBLE_DEVICES=0 python ogbn_trainPAI.py --dataset ogbn-products --batch_size 128 --saveName ogbnPAI
-    
-Results:
-
-    Test Accuracy: 78.10%
-'''
-
-
-
-
-
-
-
 
 '''
 PAI README: