[CS224w] Colab 2 - PyG, OGB, GNN

 

 

Device

런타임 > 런타임 유형 변경 > 하드웨어 가속기 > GPU로 설정하고 저장

Setup

import torch
import os
print("PyTorch has version {}".format(torch.__version__))

PyTorch has version 1.13.1+cu116

# Install torch geometric
if 'IS_GRADESCOPE_ENV' not in os.environ:
  !pip install torch-scatter -f https://pytorch-geometric.com/whl/torch-1.13.1+cu116.html
  !pip install torch-sparse -f https://pytorch-geometric.com/whl/torch-1.13.1+cu116.html
  !pip install torch-geometric
  !pip install ogb
  
  
from torch_geometric.datasets import TUDataset

if 'IS_GRADESCOPE_ENV' not in os.environ:
  root = './enzymes'
  name = 'ENZYMES'

  # The ENZYMES dataset
  pyg_dataset= TUDataset(root, name)

  # You will find that there are 600 graphs in this dataset
  print(pyg_dataset)
  
Downloading https://www.chrsmrrs.com/graphkerneldatasets/ENZYMES.zip
Extracting enzymes/ENZYMES/ENZYMES.zip
Processing...
ENZYMES(600)
Done!

get_summary() 메소드를 이용하여 간단한 정보를 볼 수 있다.

print(pyg_dataset.get_summary())
TUDataset (#graphs=600):
+------------+----------+----------+
|            |   #nodes |   #edges |
|------------+----------+----------|
| mean       |     32.6 |    124.3 |
| std        |     15.3 |     51   |
| min        |      2   |      2   |
| quantile25 |     22   |     86   |
| median     |     32   |    120   |
| quantile75 |     41   |    164   |
| max        |    126   |    298   |
+------------+----------+----------+

Question 1: What is the number of classes and number of features in the ENZYMES dataset?

def get_num_classes(pyg_dataset):
  # TODO: Implement a function that takes a PyG dataset object
  # and returns the number of classes for that dataset.

  num_classes = 0

  ############# Your code here ############
  ## (~1 line of code)
  ## Note
  ## 1. Colab autocomplete functionality might be useful.
  num_classes = pyg_dataset.num_classes
  #########################################

  return num_classes

def get_num_features(pyg_dataset):
  # TODO: Implement a function that takes a PyG dataset object
  # and returns the number of features for that dataset.

  num_features = 0

  ############# Your code here ############
  ## (~1 line of code)
  ## Note
  ## 1. Colab autocomplete functionality might be useful.
  num_features = pyg_dataset.num_features
  #########################################

  return num_features

if 'IS_GRADESCOPE_ENV' not in os.environ:
  num_classes = get_num_classes(pyg_dataset)
  num_features = get_num_features(pyg_dataset)
  print("{} dataset has {} classes".format(name, num_classes))
  print("{} dataset has {} features".format(name, num_features))
  
ENZYMES dataset has 6 classes
ENZYMES dataset has 3 features

※ PyG dataset은 여러가지 유용한 멤버변수를 갖는다.

• num_classes, num_features
• num_edge_attributes, num_edge_features, num_edge_labels
• num_node_attributes, num_node_features, num_node_labels

 

Question 2: What is the label of the graph with index 100 in the ENZYMES dataset?

아래 torch_geometric 도큐먼트를 통해 기본적인 파라미터가 있다는 것을 알 수 있다.

https://pytorch-geometric.readthedocs.io/en/latest/generated/torch_geometric.data.Data.html#torch_geometric.data.Data

torch_geometric.data.Data — pytorch_geometric documentation

• x
• edge_index
• edge_attr
• y
• pos
• **kwargs

def get_graph_class(pyg_dataset, idx):
  # TODO: Implement a function that takes a PyG dataset object,
  # an index of a graph within the dataset, and returns the class/label 
  # of the graph (as an integer).

  label = -1

  ############# Your code here ############
  ## (~1 line of code)
  label = pyg_dataset[idx].y
  #########################################

  return label

# Here pyg_dataset is a dataset for graph classification
if 'IS_GRADESCOPE_ENV' not in os.environ:
  graph_0 = pyg_dataset[0]
  print(graph_0)
  idx = 100
  label = get_graph_class(pyg_dataset, idx)
  print('Graph with index {} has label {}'.format(idx, label))
  
Data(edge_index=[2, 168], x=[37, 3], y=[1])
Graph with index 100 has label tensor([4])

 

Question 3. How many edges does the graph with index 200 have?

그래프가 방향그래프(directed graph)라면 위에 언급한 대로 num_edges를 호출하면 된다.

하지만 무뱡향그래프라면(undirected graph) 중복되는 edge를 세지 않아야 하기 때문에 $2$로 나누어야한다.

is_directed 를 통해 edge 속성을 파악하여 edge의 개수를 계산한다.

def get_graph_num_edges(pyg_dataset, idx):
  # TODO: Implement a function that takes a PyG dataset object,
  # the index of a graph in the dataset, and returns the number of 
  # edges in the graph (as an integer). You should not count an edge 
  # twice if the graph is undirected. For example, in an undirected 
  # graph G, if two nodes v and u are connected by an edge, this edge
  # should only be counted once.

  num_edges = 0

  ############# Your code here ############
  ## Note:
  ## 1. You can't return the data.num_edges directly
  ## 2. We assume the graph is undirected
  ## 3. Look at the PyG dataset built in functions
  ## (~4 lines of code)
  if pyg_dataset[idx].is_directed():
    num_edges = pyg_dataset[idx].num_edges
  else:
    num_edges = pyg_dataset[idx].num_edges // 2
  #########################################

  return num_edges

if 'IS_GRADESCOPE_ENV' not in os.environ:
  idx = 200
  num_edges = get_graph_num_edges(pyg_dataset, idx)
  print('Graph with index {} has {} edges'.format(idx, num_edges))
  
  
Graph with index 200 has 53 edges

 

2) Open Graph Benchmark (OGB)

Dataset and Data

import torch_geometric.transforms as T
from ogb.nodeproppred import PygNodePropPredDataset

if 'IS_GRADESCOPE_ENV' not in os.environ:
  dataset_name = 'ogbn-arxiv'
  # Load the dataset and transform it to sparse tensor
  dataset = PygNodePropPredDataset(name=dataset_name,
                                  transform=T.ToSparseTensor())
  print('The {} dataset has {} graph'.format(dataset_name, len(dataset)))

  # Extract the graph
  data = dataset[0]
  print(data)
  
Downloading http://snap.stanford.edu/ogb/data/nodeproppred/arxiv.zip
Downloaded 0.08 GB: 100%|██████████| 81/81 [00:07<00:00, 10.64it/s]
Extracting dataset/arxiv.zip
Processing...
Loading necessary files...
This might take a while.
Processing graphs...
100%|██████████| 1/1 [00:00<00:00, 1778.75it/s]
Converting graphs into PyG objects...
100%|██████████| 1/1 [00:00<00:00, 4871.43it/s]Saving...

Done!
The ogbn-arxiv dataset has 1 graph
Data(num_nodes=169343, x=[169343, 128], node_year=[169343, 1], y=[169343, 1], adj_t=[169343, 169343, nnz=1166243])

 

Question 4. How many features are in the obgn-arxiv graph?

def graph_num_features(data):
  # TODO: Implement a function that takes a PyG data object,
  # and returns the number of features in the graph (as an integer).

  num_features = 0

  ############# Your code here ############
  ## (~1 line of code)
  num_features = data.num_features
  #########################################

  return num_features

if 'IS_GRADESCOPE_ENV' not in os.environ:
  num_features = graph_num_features(data)
  print('The graph has {} features'.format(num_features))
  
  
The graph has 128 features

 

3) GNN: Node Property Prediction

Setup

import torch
import pandas as pd
import torch.nn.functional as F
print(torch.__version__)

# The PyG built-in GCNConv
from torch_geometric.nn import GCNConv

import torch_geometric.transforms as T
from ogb.nodeproppred import PygNodePropPredDataset, Evaluator

Load and Preprocess the Dataset

if 'IS_GRADESCOPE_ENV' not in os.environ:
  dataset_name = 'ogbn-arxiv'
  dataset = PygNodePropPredDataset(name=dataset_name,
                                  transform=T.ToSparseTensor())
  data = dataset[0]

  # Make the adjacency matrix to symmetric
  data.adj_t = data.adj_t.to_symmetric()

  device = 'cuda' if torch.cuda.is_available() else 'cpu'

  # If you use GPU, the device should be cuda
  print('Device: {}'.format(device))

  data = data.to(device)
  split_idx = dataset.get_idx_split()
  train_idx = split_idx['train'].to(device)
  
Device: cuda

 

GCN Model

아래 그림의 구조를 따르는 GCN model을 구현해보자.

코드 주석에 적힌 instruction을 보면, 

• init
  • torch.nn.ModuleList를 이용하여 self.convs와 self.bns를 구현한다.
  • activation function은 log-softmax를 이용한다.
• forward
  • 위 그림 구조대로 그래프를 구현한다
  • dropout의 파라미터로 self.training을 포함한다
  • return_emb가 True라면, log-softmax를 생략하고 리턴한다. 

class GCN(torch.nn.Module):
    def __init__(self, input_dim, hidden_dim, output_dim, num_layers,
                 dropout, return_embeds=False):
        # TODO: Implement a function that initializes self.convs, 
        # self.bns, and self.softmax.

        super(GCN, self).__init__()

        # A list of GCNConv layers
        self.convs = None

        # A list of 1D batch normalization layers
        self.bns = None

        # The log softmax layer
        self.softmax = None

        ############# Your code here ############
        ## Note:
        ## 1. You should use torch.nn.ModuleList for self.convs and self.bns
        ## 2. self.convs has num_layers GCNConv layers
        ## 3. self.bns has num_layers - 1 BatchNorm1d layers
        ## 4. You should use torch.nn.LogSoftmax for self.softmax
        ## 5. The parameters you can set for GCNConv include 'in_channels' and 
        ## 'out_channels'. For more information please refer to the documentation:
        ## https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#torch_geometric.nn.conv.GCNConv
        ## 6. The only parameter you need to set for BatchNorm1d is 'num_features'
        ## For more information please refer to the documentation: 
        ## https://pytorch.org/docs/stable/generated/torch.nn.BatchNorm1d.html
        ## (~10 lines of code)
        self.convs = [GCNConv(input_dim, hidden_dim)]\
        + [GCNConv(hidden_dim, hidden_dim) for _ in range(num_layers - 2)]\
        + [GCNConv(hidden_dim, output_dim)]
        self.convs = torch.nn.ModuleList(self.convs)

        self.bns = torch.nn.ModuleList([torch.nn.BatchNorm1d(hidden_dim) for _ in range(num_layers - 1)])
        self.softmax = torch.nn.LogSoftmax(dim=1)

        #########################################

        # Probability of an element getting zeroed
        self.dropout = dropout

        # Skip classification layer and return node embeddings
        self.return_embeds = return_embeds

    def reset_parameters(self):
        for conv in self.convs:
            conv.reset_parameters()
        for bn in self.bns:
            bn.reset_parameters()

    def forward(self, x, adj_t):
        # TODO: Implement a function that takes the feature tensor x and
        # edge_index tensor adj_t and returns the output tensor as
        # shown in the figure.

        out = None

        ############# Your code here ############
        ## Note:
        ## 1. Construct the network as shown in the figure
        ## 2. torch.nn.functional.relu and torch.nn.functional.dropout are useful
        ## For more information please refer to the documentation:
        ## https://pytorch.org/docs/stable/nn.functional.html
        ## 3. Don't forget to set F.dropout training to self.training
        ## 4. If return_embeds is True, then skip the last softmax layer
        ## (~7 lines of code)
        for conv, bn in zip(self.convs[:-1], self.bns):
          x = conv(x, adj_t)
          x = bn(x)
          x = F.relu(x)
          x = F.dropout(x, p=self.dropout, training=self.training)
        x = self.convs[-1](x, adj_t)
        out = x if self.return_embeds else self.softmax(x)
        #########################################

        return out

def train(model, data, train_idx, optimizer, loss_fn):
    # TODO: Implement a function that trains the model by 
    # using the given optimizer and loss_fn.
    model.train()
    loss = 0

    ############# Your code here ############
    ## Note:
    ## 1. Zero grad the optimizer
    ## 2. Feed the data into the model
    ## 3. Slice the model output and label by train_idx
    ## 4. Feed the sliced output and label to loss_fn
    ## (~4 lines of code)
    optimizer.zero_grad()
    out = model(data.x, data.adj_t)
    y_pred, y_true = out[train_idx], data.y[train_idx].squeeze()
    loss = loss_fn(y_pred, y_true)
    #########################################

    loss.backward()
    optimizer.step()

    return loss.item()

# Test function here
@torch.no_grad()
def test(model, data, split_idx, evaluator, save_model_results=False):
    # TODO: Implement a function that tests the model by 
    # using the given split_idx and evaluator.
    model.eval()

    # The output of model on all data
    out = None

    ############# Your code here ############
    ## (~1 line of code)
    ## Note:
    ## 1. No index slicing here
    out = model(data.x, data.adj_t)
    #########################################

    y_pred = out.argmax(dim=-1, keepdim=True)

    train_acc = evaluator.eval({
        'y_true': data.y[split_idx['train']],
        'y_pred': y_pred[split_idx['train']],
    })['acc']
    valid_acc = evaluator.eval({
        'y_true': data.y[split_idx['valid']],
        'y_pred': y_pred[split_idx['valid']],
    })['acc']
    test_acc = evaluator.eval({
        'y_true': data.y[split_idx['test']],
        'y_pred': y_pred[split_idx['test']],
    })['acc']

    if save_model_results:
      print ("Saving Model Predictions")

      data = {}
      data['y_pred'] = y_pred.view(-1).cpu().detach().numpy()

      df = pd.DataFrame(data=data)
      # Save locally as csv
      df.to_csv('ogbn-arxiv_node.csv', sep=',', index=False)


    return train_acc, valid_acc, test_acc

# Please do not change the args
if 'IS_GRADESCOPE_ENV' not in os.environ:
  args = {
      'device': device,
      'num_layers': 3,
      'hidden_dim': 256,
      'dropout': 0.5,
      'lr': 0.01,
      'epochs': 100,
  }
  args

# Please do not change these args
# Training should take <10min using GPU runtime
import copy
if 'IS_GRADESCOPE_ENV' not in os.environ:
  # reset the parameters to initial random value
  model.reset_parameters()

  optimizer = torch.optim.Adam(model.parameters(), lr=args['lr'])
  loss_fn = F.nll_loss

  best_model = None
  best_valid_acc = 0

  for epoch in range(1, 1 + args["epochs"]):
    loss = train(model, data, train_idx, optimizer, loss_fn)
    result = test(model, data, split_idx, evaluator)
    train_acc, valid_acc, test_acc = result
    if valid_acc > best_valid_acc:
        best_valid_acc = valid_acc
        best_model = copy.deepcopy(model)
    print(f'Epoch: {epoch:02d}, '
          f'Loss: {loss:.4f}, '
          f'Train: {100 * train_acc:.2f}%, '
          f'Valid: {100 * valid_acc:.2f}% '
          f'Test: {100 * test_acc:.2f}%')

 

Epoch: 01, Loss: 4.0002, Train: 24.64%, Valid: 28.32% Test: 25.51%
Epoch: 02, Loss: 2.3358, Train: 27.88%, Valid: 25.51% Test: 30.40%
Epoch: 03, Loss: 1.9505, Train: 31.58%, Valid: 31.26% Test: 34.20%
.
.
.
Epoch: 98, Loss: 0.9150, Train: 73.72%, Valid: 71.79% Test: 71.10%
Epoch: 99, Loss: 0.9133, Train: 73.78%, Valid: 71.51% Test: 70.63%
Epoch: 100, Loss: 0.9114, Train: 73.67%, Valid: 70.93% Test: 69.87%

Question 5: What are your best_model validation and test accuracies?

if 'IS_GRADESCOPE_ENV' not in os.environ:
  best_result = test(best_model, data, split_idx, evaluator, save_model_results=True)
  train_acc, valid_acc, test_acc = best_result
  print(f'Best model: '
        f'Train: {100 * train_acc:.2f}%, '
        f'Valid: {100 * valid_acc:.2f}% '
        f'Test: {100 * test_acc:.2f}%')
        
        
Saving Model Predictions
Best model: Train: 72.51%, Valid: 72.36% Test: 71.94%

 

4) GNN: Graph Property Prediction

Load and preprocess the dataset

from ogb.graphproppred import PygGraphPropPredDataset, Evaluator
from torch_geometric.data import DataLoader
from tqdm.notebook import tqdm

if 'IS_GRADESCOPE_ENV' not in os.environ:
  # Load the dataset 
  dataset = PygGraphPropPredDataset(name='ogbg-molhiv')

  device = 'cuda' if torch.cuda.is_available() else 'cpu'
  print('Device: {}'.format(device))

  split_idx = dataset.get_idx_split()

  # Check task type
  print('Task type: {}'.format(dataset.task_type))
  
Device: cuda
Task type: binary classification

# Load the dataset splits into corresponding dataloaders
# We will train the graph classification task on a batch of 32 graphs
# Shuffle the order of graphs for training set
if 'IS_GRADESCOPE_ENV' not in os.environ:
  train_loader = DataLoader(dataset[split_idx["train"]], batch_size=32, shuffle=True, num_workers=0)
  valid_loader = DataLoader(dataset[split_idx["valid"]], batch_size=32, shuffle=False, num_workers=0)
  test_loader = DataLoader(dataset[split_idx["test"]], batch_size=32, shuffle=False, num_workers=0)

if 'IS_GRADESCOPE_ENV' not in os.environ:
  # Please do not change the args
  args = {
      'device': device,
      'num_layers': 5,
      'hidden_dim': 256,
      'dropout': 0.5,
      'lr': 0.001,
      'epochs': 30,
  }
  args

from ogb.graphproppred.mol_encoder import AtomEncoder
from torch_geometric.nn import global_add_pool, global_mean_pool

### GCN to predict graph property
class GCN_Graph(torch.nn.Module):
    def __init__(self, hidden_dim, output_dim, num_layers, dropout):
        super(GCN_Graph, self).__init__()

        # Load encoders for Atoms in molecule graphs
        self.node_encoder = AtomEncoder(hidden_dim)

        # Node embedding model
        # Note that the input_dim and output_dim are set to hidden_dim
        self.gnn_node = GCN(hidden_dim, hidden_dim,
            hidden_dim, num_layers, dropout, return_embeds=True)

        self.pool = None

        ############# Your code here ############
        ## Note:
        ## 1. Initialize self.pool as a global mean pooling layer
        ## For more information please refer to the documentation:
        ## https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#global-pooling-layers
        self.pool = global_mean_pool
        #########################################

        # Output layer
        self.linear = torch.nn.Linear(hidden_dim, output_dim)


    def reset_parameters(self):
      self.gnn_node.reset_parameters()
      self.linear.reset_parameters()

    def forward(self, batched_data):
        # TODO: Implement a function that takes as input a 
        # mini-batch of graphs (torch_geometric.data.Batch) and 
        # returns the predicted graph property for each graph. 
        #
        # NOTE: Since we are predicting graph level properties,
        # your output will be a tensor with dimension equaling
        # the number of graphs in the mini-batch

    
        # Extract important attributes of our mini-batch
        x, edge_index, batch = batched_data.x, batched_data.edge_index, batched_data.batch
        embed = self.node_encoder(x)

        out = None

        ############# Your code here ############
        ## Note:
        ## 1. Construct node embeddings using existing GCN model
        ## 2. Use the global pooling layer to aggregate features for each individual graph
        ## For more information please refer to the documentation:
        ## https://pytorch-geometric.readthedocs.io/en/latest/modules/nn.html#global-pooling-layers
        ## 3. Use a linear layer to predict each graph's property
        ## (~3 lines of code)
        out = self.gnn_node(embed, edge_index)
        out = self.pool(out, batch)
        out = self.linear(out)
        #########################################

        return out

train

1. optimizer의 변화도 0으로 하기
   1. optimzier.zero_grad()
2. model에 data 입력
   1. out = model(batch)
3. is_labaled로 마스킹된 데이터의 output과 label을 구하기
   1. out = out[is_labeled]
   2. label = batch.y[is_labeled]
4. 데이터 타입을 torch.float32로 해야할 것이다.
   1. label = batch.y[is_labeled].type(torch.float32).do(device)
5. output과 label을 손실함수 loss_fn에 넣기

def train(model, device, data_loader, optimizer, loss_fn):
    # TODO: Implement a function that trains your model by 
    # using the given optimizer and loss_fn.
    model.train()
    loss = 0

    for step, batch in enumerate(tqdm(data_loader, desc="Iteration")):
      batch = batch.to(device)

      if batch.x.shape[0] == 1 or batch.batch[-1] == 0:
          pass
      else:
        ## ignore nan targets (unlabeled) when computing training loss.
        is_labeled = batch.y == batch.y

        ############# Your code here ############
        ## Note:
        ## 1. Zero grad the optimizer
        ## 2. Feed the data into the model
        ## 3. Use `is_labeled` mask to filter output and labels
        ## 4. You may need to change the type of label to torch.float32
        ## 5. Feed the output and label to the loss_fn
        ## (~3 lines of code)
        optimizer.zero_grad()
        out = model(batch)
        loss = loss_fn(out[is_labeled], batch.y[is_labeled].type(torch.float32).to(device))
        #########################################

        loss.backward()
        optimizer.step()

    return loss.item()

# The evaluation function
def eval(model, device, loader, evaluator, save_model_results=False, save_file=None):
    model.eval()
    y_true = []
    y_pred = []

    for step, batch in enumerate(tqdm(loader, desc="Iteration")):
        batch = batch.to(device)

        if batch.x.shape[0] == 1:
            pass
        else:
            with torch.no_grad():
                pred = model(batch)

            y_true.append(batch.y.view(pred.shape).detach().cpu())
            y_pred.append(pred.detach().cpu())

    y_true = torch.cat(y_true, dim = 0).numpy()
    y_pred = torch.cat(y_pred, dim = 0).numpy()

    input_dict = {"y_true": y_true, "y_pred": y_pred}

    if save_model_results:
        print ("Saving Model Predictions")
        
        # Create a pandas dataframe with a two columns
        # y_pred | y_true
        data = {}
        data['y_pred'] = y_pred.reshape(-1)
        data['y_true'] = y_true.reshape(-1)

        df = pd.DataFrame(data=data)
        # Save to csv
        df.to_csv('ogbg-molhiv_graph_' + save_file + '.csv', sep=',', index=False)

    return evaluator.eval(input_dict)

if 'IS_GRADESCOPE_ENV' not in os.environ:
  model = GCN_Graph(args['hidden_dim'],
              dataset.num_tasks, args['num_layers'],
              args['dropout']).to(device)
  evaluator = Evaluator(name='ogbg-molhiv')

# Please do not change these args
# Training should take <10min using GPU runtime
import copy

if 'IS_GRADESCOPE_ENV' not in os.environ:
  model.reset_parameters()

  optimizer = torch.optim.Adam(model.parameters(), lr=args['lr'])
  loss_fn = torch.nn.BCEWithLogitsLoss()

  best_model = None
  best_valid_acc = 0

  for epoch in range(1, 1 + args["epochs"]):
    print('Training...')
    loss = train(model, device, train_loader, optimizer, loss_fn)

    print('Evaluating...')
    train_result = eval(model, device, train_loader, evaluator)
    val_result = eval(model, device, valid_loader, evaluator)
    test_result = eval(model, device, test_loader, evaluator)

    train_acc, valid_acc, test_acc = train_result[dataset.eval_metric], val_result[dataset.eval_metric], test_result[dataset.eval_metric]
    if valid_acc > best_valid_acc:
        best_valid_acc = valid_acc
        best_model = copy.deepcopy(model)
    print(f'Epoch: {epoch:02d}, '
          f'Loss: {loss:.4f}, '
          f'Train: {100 * train_acc:.2f}%, '
          f'Valid: {100 * valid_acc:.2f}% '
          f'Test: {100 * test_acc:.2f}%')

Question 6: What are your best model validation and test ROC-AUC scores?

if 'IS_GRADESCOPE_ENV' not in os.environ:
  train_acc = eval(best_model, device, train_loader, evaluator)[dataset.eval_metric]
  valid_acc = eval(best_model, device, valid_loader, evaluator, save_model_results=True, save_file="valid")[dataset.eval_metric]
  test_acc  = eval(best_model, device, test_loader, evaluator, save_model_results=True, save_file="test")[dataset.eval_metric]

  print(f'Best model: '
      f'Train: {100 * train_acc:.2f}%, '
      f'Valid: {100 * valid_acc:.2f}% '
      f'Test: {100 * test_acc:.2f}%')

Question 7 (Optional): Experiment with the two other global pooling layers in Pytorch Geometric.

self.pool 에 gloabl_mean_pool 등을 이용하자.

GCN_graph class의 init 파라미터로 pool이 있으면 더 편할 것 같은데...