PyTorch Geometric

Integrate W&B with PyTorch Geometric for graph visualization and experiment tracking in geometric deep learning.

PyTorch Geometric (PyG) is a library for geometric deep learning, and W&B works with it for visualizing graphs and tracking experiments.

This guide shows you how to authenticate to W&B, install the wandb library, visualize PyG graphs with PyVis or Plotly, and log training metrics from your PyG workflows. Use it to track experiments and share graph visualizations in W&B.

After you install PyTorch Geometric, follow these steps to get started.

Sign up and create an API key

An API key authenticates your machine to W&B. You can generate an API key from your user profile.

For a more streamlined approach, go to User Settings and create an API key. Copy the API key immediately and save it in a secure location such as a password manager.

1. Click your user profile icon in the upper right corner.
2. Select User Settings, then scroll to the API Keys section.

Install the wandb library and log in

To install the wandb library locally and log in:

Command Line

1. Set the WANDB_API_KEY environment variable to your API key. Replace values enclosed in <> with your own:

   export WANDB_API_KEY=<your_api_key>
   

2. Install the wandb library and log in.

   pip install wandb
   
   wandb login
   

Python

pip install wandb

import wandb
wandb.login()

Python notebook

!pip install wandb

import wandb
wandb.login()

Visualize the graphs

After you log in, you can begin sending graph visualizations and run data to W&B.

You can save details about the input graphs, including number of edges, number of nodes, and more. W&B supports logging Plotly charts and HTML panels, so you can also log any visualizations you create for your graph to W&B. The following sections show two common approaches: PyVis for interactive HTML visualizations and Plotly for chart-based visualizations.

Use PyVis

The following snippet shows how to do that with PyVis and HTML.

from pyvis.network import Network
import wandb

with wandb.init(project="graph_vis") as run:
    net = Network(height="750px", width="100%", bgcolor="#222222", font_color="white")

    # Add the edges from the PyG graph to the PyVis network
    for e in tqdm(g.edge_index.T):
        src = e[0].item()
        dst = e[1].item()

        net.add_node(dst)
        net.add_node(src)
        
        net.add_edge(src, dst, value=0.1)

    # Save the PyVis visualisation to a HTML file
    net.show("graph.html")
    run.log({"eda/graph": wandb.Html("graph.html")})

Use Plotly

To use Plotly to create a graph visualization, first convert the PyG graph to a networkx object. Then create Plotly scatter plots for both nodes and edges. Use the following snippet for this task.

def create_vis(graph):
    G = to_networkx(graph)
    pos = nx.spring_layout(G)

    edge_x = []
    edge_y = []
    for edge in G.edges():
        x0, y0 = pos[edge[0]]
        x1, y1 = pos[edge[1]]
        edge_x.append(x0)
        edge_x.append(x1)
        edge_x.append(None)
        edge_y.append(y0)
        edge_y.append(y1)
        edge_y.append(None)

    edge_trace = go.Scatter(
        x=edge_x, y=edge_y,
        line=dict(width=0.5, color='#888'),
        hoverinfo='none',
        mode='lines'
    )

    node_x = []
    node_y = []
    for node in G.nodes():
        x, y = pos[node]
        node_x.append(x)
        node_y.append(y)

    node_trace = go.Scatter(
        x=node_x, y=node_y,
        mode='markers',
        hoverinfo='text',
        line_width=2
    )

    fig = go.Figure(data=[edge_trace, node_trace], layout=go.Layout())

    return fig


with wandb.init(project="visualize_graph") as run:
    run.log({"graph": wandb.Plotly(create_vis(graph))})

Log metrics

In addition to graph visualizations, you can use W&B to track your experiments and related metrics, such as loss functions, accuracy, and more. Add the following lines to your training loop:

with wandb.init(project="my_project", entity="my_entity") as run:
    run.log({
        'train/loss': training_loss,
        'train/acc': training_acc,
        'val/loss': validation_loss,
        'val/acc': validation_acc
        })

With graph visualizations and training metrics logged to W&B, you can compare runs and share results from your PyG experiments in your W&B workspace.

More resources

The following W&B reports show PyG in action:

• Recommending Amazon Products using Graph Neural Networks in PyTorch Geometric
• Point Cloud Classification using PyTorch Geometric
• Point Cloud Segmentation using PyTorch Geometric