Graph Neural Networks

Introduction

GNNs process graph-structured data for social networks, molecular properties, and recommendations.

PyTorch Geometric

import torch
from torch_geometric.datasets import KarateClub
from torch_geometric.nn import GCNConv

dataset = KarateClub()
data = dataset[0]

class GCN(torch.nn.Module):
    def __init__(self):
        super().__init__()
        self.conv1 = GCNConv(dataset.num_features, 16)
        self.conv2 = GCNConv(16, dataset.num_classes)
    
    def forward(self, data):
        x, edge_index = data.x, data.edge_index
        x = self.conv1(x, edge_index)
        x = torch.relu(x)
        x = self.conv2(x, edge_index)
        return x

Message Passing

from torch_geometric.nn import MessagePassing

class MyConv(MessagePassing):
    def __init__(self):
        super().__init__(aggr="add")
    
    def forward(self, x, edge_index):
        return self.propagate(edge_index, x=x)
    
    def message(self, x_j):
        return x_j

Practice Problems

1. Load graph datasets
2. Implement GCN layer
3. Train node classification
4. Visualize graph embeddings
5. Create custom message passing