Node Classification
This tutorial shows how to train a multi-layer GraphSAGE for node classification on ogbn-arxiv provided by Open Graph Benchmark (OGB). The dataset contains around 170 thousand nodes and 1 million edges.
By the end of this tutorial, you will be able to
Train a GNN model for node classification on a single GPU with DGL’s neighbor sampling components.
Install DGL package
[1]:
# Install required packages.
import os
import torch
import numpy as np
os.environ['TORCH'] = torch.__version__
os.environ['DGLBACKEND'] = "pytorch"
# Install the CPU version in default. If you want to install CUDA version,
# please refer to https://www.dgl.ai/pages/start.html and change runtime type
# accordingly.
device = torch.device("cpu")
!pip install --pre dgl -f https://data.dgl.ai/wheels-test/repo.html
try:
import dgl
import dgl.graphbolt as gb
installed = True
except ImportError as error:
installed = False
print(error)
print("DGL installed!" if installed else "DGL not found!")
Looking in links: https://data.dgl.ai/wheels-test/repo.html
Requirement already satisfied: dgl in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages/dgl-2.1.0-py3.8-linux-x86_64.egg (2.1.0)
Requirement already satisfied: numpy>=1.14.0 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from dgl) (1.24.4)
Requirement already satisfied: scipy>=1.1.0 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from dgl) (1.10.1)
Requirement already satisfied: networkx>=2.1 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from dgl) (3.1)
Requirement already satisfied: requests>=2.19.0 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from dgl) (2.31.0)
Requirement already satisfied: tqdm in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from dgl) (4.66.2)
Requirement already satisfied: psutil>=5.8.0 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from dgl) (5.9.8)
Requirement already satisfied: torchdata>=0.5.0 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from dgl) (0.7.1)
Requirement already satisfied: charset-normalizer<4,>=2 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from requests>=2.19.0->dgl) (3.3.2)
Requirement already satisfied: idna<4,>=2.5 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from requests>=2.19.0->dgl) (3.6)
Requirement already satisfied: urllib3<3,>=1.21.1 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from requests>=2.19.0->dgl) (2.2.1)
Requirement already satisfied: certifi>=2017.4.17 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from requests>=2.19.0->dgl) (2024.2.2)
Requirement already satisfied: torch>=2 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torchdata>=0.5.0->dgl) (2.0.0)
Requirement already satisfied: filelock in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (3.13.1)
Requirement already satisfied: typing-extensions in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (4.10.0)
Requirement already satisfied: sympy in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (1.12)
Requirement already satisfied: jinja2 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (3.1.3)
Requirement already satisfied: nvidia-cuda-nvrtc-cu11==11.7.99 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (11.7.99)
Requirement already satisfied: nvidia-cuda-runtime-cu11==11.7.99 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (11.7.99)
Requirement already satisfied: nvidia-cuda-cupti-cu11==11.7.101 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (11.7.101)
Requirement already satisfied: nvidia-cudnn-cu11==8.5.0.96 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (8.5.0.96)
Requirement already satisfied: nvidia-cublas-cu11==11.10.3.66 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (11.10.3.66)
Requirement already satisfied: nvidia-cufft-cu11==10.9.0.58 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (10.9.0.58)
Requirement already satisfied: nvidia-curand-cu11==10.2.10.91 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (10.2.10.91)
Requirement already satisfied: nvidia-cusolver-cu11==11.4.0.1 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (11.4.0.1)
Requirement already satisfied: nvidia-cusparse-cu11==11.7.4.91 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (11.7.4.91)
Requirement already satisfied: nvidia-nccl-cu11==2.14.3 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (2.14.3)
Requirement already satisfied: nvidia-nvtx-cu11==11.7.91 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (11.7.91)
Requirement already satisfied: triton==2.0.0 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from torch>=2->torchdata>=0.5.0->dgl) (2.0.0)
Requirement already satisfied: setuptools in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=2->torchdata>=0.5.0->dgl) (69.1.0)
Requirement already satisfied: wheel in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from nvidia-cublas-cu11==11.10.3.66->torch>=2->torchdata>=0.5.0->dgl) (0.42.0)
Requirement already satisfied: cmake in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from triton==2.0.0->torch>=2->torchdata>=0.5.0->dgl) (3.28.3)
Requirement already satisfied: lit in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from triton==2.0.0->torch>=2->torchdata>=0.5.0->dgl) (17.0.6)
Requirement already satisfied: MarkupSafe>=2.0 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from jinja2->torch>=2->torchdata>=0.5.0->dgl) (2.1.5)
Requirement already satisfied: mpmath>=0.19 in /home/ubuntu/prod-doc/readthedocs.org/user_builds/dgl/envs/2.1.x/lib/python3.8/site-packages (from sympy->torch>=2->torchdata>=0.5.0->dgl) (1.3.0)
DGL installed!
Loading Dataset
ogbn-arxiv is already prepared as BuiltinDataset in GraphBolt.
[2]:
dataset = gb.BuiltinDataset("ogbn-arxiv").load()
Downloading datasets/ogbn-arxiv.zip from https://data.dgl.ai/dataset/graphbolt/ogbn-arxiv.zip...
Extracting file to datasets
The dataset is already preprocessed.
Dataset consists of graph, feature and tasks. You can get the training-validation-test set from the tasks. Seed nodes and corresponding labels are already stored in each training-validation-test set. Other metadata such as number of classes are also stored in the tasks. In this dataset, there is only one task: node classification.
[3]:
graph = dataset.graph.to(device)
feature = dataset.feature.to(device)
train_set = dataset.tasks[0].train_set
valid_set = dataset.tasks[0].validation_set
test_set = dataset.tasks[0].test_set
task_name = dataset.tasks[0].metadata["name"]
num_classes = dataset.tasks[0].metadata["num_classes"]
print(f"Task: {task_name}. Number of classes: {num_classes}")
Task: node_classification. Number of classes: 40
How DGL Handles Computation Dependency¶
The computation dependency for message passing of a single node can be described as a series of message flow graphs (MFG).
Defining Neighbor Sampler and Data Loader in DGL
DGL provides tools to iterate over the dataset in minibatches while generating the computation dependencies to compute their outputs with the MFGs above. For node classification, you can use dgl.graphbolt.DataLoader for iterating over the dataset. It accepts a data pipe that generates minibatches of nodes and their labels, sample neighbors for each node, and generate the computation dependencies in the form of MFGs. Feature fetching, block creation and copying to target device are also
supported. All these operations are split into separate stages in the data pipe, so that you can customize the data pipeline by inserting your own operations.
Let’s say that each node will gather messages from 4 neighbors on each layer. The code defining the data loader and neighbor sampler will look like the following.
[4]:
def create_dataloader(itemset, shuffle):
datapipe = gb.ItemSampler(itemset, batch_size=1024, shuffle=shuffle)
datapipe = datapipe.copy_to(device, extra_attrs=["seed_nodes"])
datapipe = datapipe.sample_neighbor(graph, [4, 4])
datapipe = datapipe.fetch_feature(feature, node_feature_keys=["feat"])
return gb.DataLoader(datapipe)
You can iterate over the data loader and a MiniBatch object is yielded.
[5]:
data = next(iter(create_dataloader(train_set, shuffle=True)))
print(data)
MiniBatch(seeds=None,
seed_nodes=tensor([141764, 91419, 164174, ..., 73287, 25161, 132392]),
sampled_subgraphs=[SampledSubgraphImpl(sampled_csc=CSCFormatBase(indptr=tensor([ 0, 3, 3, ..., 6417, 6419, 6419], dtype=torch.int32),
indices=tensor([1024, 1025, 1026, ..., 7377, 7378, 3232], dtype=torch.int32),
),
original_row_node_ids=tensor([141764, 91419, 164174, ..., 141015, 36884, 138728]),
original_edge_ids=None,
original_column_node_ids=tensor([141764, 91419, 164174, ..., 5904, 63098, 63593]),
),
SampledSubgraphImpl(sampled_csc=CSCFormatBase(indptr=tensor([ 0, 3, 3, ..., 2248, 2252, 2252], dtype=torch.int32),
indices=tensor([1024, 1025, 1026, ..., 3230, 3231, 3232], dtype=torch.int32),
),
original_row_node_ids=tensor([141764, 91419, 164174, ..., 5904, 63098, 63593]),
original_edge_ids=None,
original_column_node_ids=tensor([141764, 91419, 164174, ..., 73287, 25161, 132392]),
)],
positive_node_pairs=None,
node_pairs_with_labels=None,
node_pairs=None,
node_features={'feat': tensor([[-0.1563, 0.0563, -0.3023, ..., 0.1291, -0.1312, -0.0135],
[-0.2477, -0.1770, -0.4544, ..., 0.0617, -0.0435, 0.0522],
[ 0.0323, 0.0589, -0.2649, ..., 0.0477, 0.0310, -0.1472],
...,
[ 0.0120, 0.1130, -0.3313, ..., 0.2248, 0.1721, -0.1161],
[-0.0046, 0.1149, -0.1955, ..., 0.2987, 0.0382, -0.3777],
[-0.0634, 0.1095, -0.1941, ..., 0.2271, -0.1723, -0.2619]])},
negative_srcs=None,
negative_node_pairs=None,
negative_dsts=None,
labels=tensor([38, 10, 32, ..., 34, 34, 28]),
input_nodes=tensor([141764, 91419, 164174, ..., 141015, 36884, 138728]),
indexes=None,
edge_features=[{},
{}],
compacted_seeds=None,
compacted_node_pairs=None,
compacted_negative_srcs=None,
compacted_negative_dsts=None,
blocks=[Block(num_src_nodes=7379, num_dst_nodes=3233, num_edges=6419),
Block(num_src_nodes=3233, num_dst_nodes=1024, num_edges=2252)],
)
You can get the input node IDs from MFGs.
[6]:
mfgs = data.blocks
input_nodes = mfgs[0].srcdata[dgl.NID]
print(f"Input nodes: {input_nodes}.")
Input nodes: tensor([141764, 91419, 164174, ..., 141015, 36884, 138728]).
Defining Model
Let’s consider training a 2-layer GraphSAGE with neighbor sampling. The model can be written as follows:
[7]:
import torch.nn as nn
import torch.nn.functional as F
from dgl.nn import SAGEConv
class Model(nn.Module):
def __init__(self, in_feats, h_feats, num_classes):
super(Model, self).__init__()
self.conv1 = SAGEConv(in_feats, h_feats, aggregator_type="mean")
self.conv2 = SAGEConv(h_feats, num_classes, aggregator_type="mean")
self.h_feats = h_feats
def forward(self, mfgs, x):
h = self.conv1(mfgs[0], x)
h = F.relu(h)
h = self.conv2(mfgs[1], h)
return h
in_size = feature.size("node", None, "feat")[0]
model = Model(in_size, 64, num_classes).to(device)
Defining Training Loop
The following initializes the model and defines the optimizer.
[8]:
opt = torch.optim.Adam(model.parameters())
When computing the validation score for model selection, usually you can also do neighbor sampling. We can just reuse our create_dataloader function to create two separate dataloaders for training and validation.
[9]:
train_dataloader = create_dataloader(train_set, shuffle=True)
valid_dataloader = create_dataloader(valid_set, shuffle=False)
import sklearn.metrics
The following is a training loop that performs validation every epoch. It also saves the model with the best validation accuracy into a file.
[10]:
from tqdm.auto import tqdm
for epoch in range(10):
model.train()
with tqdm(train_dataloader) as tq:
for step, data in enumerate(tq):
x = data.node_features["feat"]
labels = data.labels
predictions = model(data.blocks, x)
loss = F.cross_entropy(predictions, labels)
opt.zero_grad()
loss.backward()
opt.step()
accuracy = sklearn.metrics.accuracy_score(
labels.cpu().numpy(),
predictions.argmax(1).detach().cpu().numpy(),
)
tq.set_postfix(
{"loss": "%.03f" % loss.item(), "acc": "%.03f" % accuracy},
refresh=False,
)
model.eval()
predictions = []
labels = []
with tqdm(valid_dataloader) as tq, torch.no_grad():
for data in tq:
x = data.node_features["feat"]
labels.append(data.labels.cpu().numpy())
predictions.append(model(data.blocks, x).argmax(1).cpu().numpy())
predictions = np.concatenate(predictions)
labels = np.concatenate(labels)
accuracy = sklearn.metrics.accuracy_score(labels, predictions)
print("Epoch {} Validation Accuracy {}".format(epoch, accuracy))
Epoch 0 Validation Accuracy 0.4098795261585959
Epoch 1 Validation Accuracy 0.4990100338937548
Epoch 2 Validation Accuracy 0.5351186281418839
Epoch 3 Validation Accuracy 0.553441390650693
Epoch 4 Validation Accuracy 0.5551864156515319
Epoch 5 Validation Accuracy 0.5724017584482701
Epoch 6 Validation Accuracy 0.5728044565253868
Epoch 7 Validation Accuracy 0.5778717406624383
Epoch 8 Validation Accuracy 0.5787442531628578
Epoch 9 Validation Accuracy 0.5781402060471827
Conclusion
In this tutorial, you have learned how to train a multi-layer GraphSAGE with neighbor sampling.