Perforated AI OGBN Example

[RorryB]

This PR is to include an example of how Perforated Backpropagation can be used to improve pytorch_geometric models. It adds on the previous PR which added a scheduler, 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 .
pip install safetensors
pip install perforatedai

Ran original with:

CUDA_VISIBLE_DEVICES=0 python examples/ogbn_train_perforatedai.py --dataset ogbn-products --batch_size 128

Results:

Test Accuracy: 77.19%

Run PAI with:

PAIEMAIL=YourEmail PAITOKEN=YourToken CUDA_VISIBLE_DEVICES=0 python ogbn_train_perforatedai.py --dataset ogbn-products --batch_size 128 --saveName ogbnPAI

Results:

Test Accuracy: 78.37%

[puririshi98]

ERROR: Could not find a version that satisfies the requirement perforatedai (from versions: none)

[notice] A new release of pip is available: 24.3.1 -> 25.0
[notice] To update, run: python -m pip install --upgrade pip
ERROR: No matching distribution found for perforatedai

using the copypastes given inside your fork