基于图神经网络的图表示学习方法

基于GIN的图表征网络的实现

基于图同构网络的图表征学习包含以下过程：

1. 首先计算得到节点表征；
2. 然后对图上各个节点的表征做图池化，得到图的表征。

基于图同构网络的图表征模块（GINGraphRepr Module）

import torch
from torch import nn
from torch_geometric.nn import global_add_pool, global_mean_pool, global_max_pool, GlobalAttention, Set2Set
from gin_node import GINNodeEmbedding

class GINGraphRepr(nn.Module):
    def __init__(self, num_tasks=1, num_layers=5, emb_dim=300, residual=False, drop_ratio=0, JK="last", graph_pooling="sum"):
        super(GINGraphPooling, self).__init__()
        self.num_layers = num_layers
        self.drop_ratio = drop_ratio
        self.JK = JK
        self.emb_dim = emb_dim
        self.num_tasks = num_tasks

        if self.num_layers < 2:
            raise ValueError("Number of GNN layers must be greater than 1.")

        self.gnn_node = GINNodeEmbedding(num_layers, emb_dim, JK=JK, drop_ratio=drop_ratio, residual=residual)

        # Pooling function to generate whole-graph embeddings
        if graph_pooling == "sum":
            self.pool = global_add_pool
        elif graph_pooling == "mean":
            self.pool = global_mean_pool
        elif graph_pooling == "max":
            self.pool = global_max_pool
        elif graph_pooling == "attention":
            self.pool = GlobalAttention(gate_nn=nn.Sequential(
                nn.Linear(emb_dim, emb_dim), nn.BatchNorm1d(emb_dim), nn.ReLU(), nn.Linear(emb_dim, 1)))
        elif graph_pooling == "set2set":
            self.pool = Set2Set(emb_dim, processing_steps=2)
        else:
            raise ValueError("Invalid graph pooling type.")

        if graph_pooling == "set2set":
            self.graph_pred_linear = nn.Linear(2*self.emb_dim, self.num_tasks)
        else:
            self.graph_pred_linear = nn.Linear(self.emb_dim, self.num_tasks)

    def forward(self, batched_data):
        h_node = self.gnn_node(batched_data)

        h_graph = self.pool(h_node, batched_data.batch)
        output = self.graph_pred_linear(h_graph)

        if self.training:
            return output
        else:
            # At inference time, relu is applied to output to ensure positivity
            # 因为预测目标的取值范围就在 (0, 50] 内
            return torch.clamp(output, min=0, max=50)

• sum:：对节点表征求和
• mean：对节点表征求平均
• max：取节点表征的最大值
• attention：基于Attention对节点表征加权求和
• set2set：另一种基于Attention对节点表征加权求和

基于图同构网络的节点嵌入模块（GINNodeEmbedding Module）

import torch
from mol_encoder import AtomEncoder
from gin_conv import GINConv
import torch.nn.functional as F

# GNN to generate node embedding
class GINNodeEmbedding(torch.nn.Module):
    """
    Output:
        node representations
    """

    def __init__(self, num_layers, emb_dim, drop_ratio=0.5, JK="last", residual=False):
        """GIN Node Embedding Module"""

        super(GINNodeEmbedding, self).__init__()
        self.num_layers = num_layers
        self.drop_ratio = drop_ratio
        self.JK = JK
        # add residual connection or not
        self.residual = residual

        if self.num_layers < 2:
            raise ValueError("Number of GNN layers must be greater than 1.")
		
		# 首先用AtomEncoder做嵌入得到第0层节点表征
        self.atom_encoder = AtomEncoder(emb_dim)

        # List of GNNs
        self.convs = torch.nn.ModuleList()
        self.batch_norms = torch.nn.ModuleList()

		# 从第1层到第num_layers层，点表征的计算都以上一层的节点表征、边和边的属性为输入
        for layer in range(num_layers):
            self.convs.append(GINConv(emb_dim))
            self.batch_norms.append(torch.nn.BatchNorm1d(emb_dim))

    def forward(self, batched_data):
        x, edge_index, edge_attr = batched_data.x, batched_data.edge_index, batched_data.edge_attr

        # computing input node embedding
        h_list = [self.atom_encoder(x)]  # 先将类别型原子属性转化为原子表征
        for layer in range(self.num_layers):
            h = self.convs[layer](h_list[layer], edge_index, edge_attr)
            h = self.batch_norms[layer](h)
            if layer == self.num_layers - 1:
                # remove relu for the last layer
                h = F.dropout(h, self.drop_ratio, training=self.training)
            else:
                h = F.dropout(F.relu(h), self.drop_ratio, training=self.training)

            if self.residual:
                h += h_list[layer]

            h_list.append(h)

        # Different implementations of Jk-concat
        if self.JK == "last":
            node_representation = h_list[-1]
        elif self.JK == "sum":
            node_representation = 0
            for layer in range(self.num_layers + 1):
                node_representation += h_list[layer]

        return node_representation

GINConv的层数越多，此节点嵌入模块的感受野越大，节点i的表征最远能捕获到节点i的距离为num_layers的邻接节点的信息。

图同构网络的关键组件GINConv

import torch
from torch import nn
from torch_geometric.nn import MessagePassing
import torch.nn.functional as F
from ogb.graphproppred.mol_encoder import BondEncoder


### GIN convolution along the graph structure
class GINConv(MessagePassing):
    def __init__(self, emb_dim):
        '''
            emb_dim (int): node embedding dimensionality
        '''
        super(GINConv, self).__init__(aggr = "add")

        self.mlp = nn.Sequential(nn.Linear(emb_dim, emb_dim), nn.BatchNorm1d(emb_dim), nn.ReLU(), nn.Linear(emb_dim, emb_dim))
        self.eps = nn.Parameter(torch.Tensor([0]))
        self.bond_encoder = BondEncoder(emb_dim = emb_dim)

    def forward(self, x, edge_index, edge_attr):
        edge_embedding = self.bond_encoder(edge_attr) # 先将类别型边属性转换为边表征
        out = self.mlp((1 + self.eps) *x + self.propagate(edge_index, x=x, edge_attr=edge_embedding))
        return out

    def message(self, x_j, edge_attr):
        return F.relu(x_j + edge_attr)
        
    def update(self, aggr_out):
        return aggr_out

GINConv模块遵循“消息传递、消息聚合、消息更新”这一过程：

• 首先self.propagate()方法开始执行，该方法接收edge_index, x, edge_attr三个参数，edge_index是形状为[2,num_edges]的张量。
• 在消息传递过程中，此张量先按行拆分为x_i和x_j张量，x_j表示消息传递的源节点，x_i表示消息传递的目标节点。
• 接着message()方法被调用，此方法定义了从源节点到目标节点的消息，这里要传递的消息是源节点表征与边表征之和的relu()的输出。我们在初始化时用aggr="add"定义了消息聚合方式，那么传入一个目标节点的消息被求和得到aggr_out，它还是目标节点的中间过程的消息。
• 然后执行消息更新过程，update()方法被调用。我们希望在更新中加入目标节点自身的消息，因此在update方法中只返回输入的aggr_out。
• 最后在forward()方法中执行消息的更新。

原文地址