【学习笔记】GNN - Task2

消息传递

1.消息传递（Message Passing）范式

• 节点嵌入（Node Embedding）- 神经网络的生成节点表征的操作

2.MessagePassing类

Pytorch Geometric(PyG)提供了MessagePassing基类，它封装了“消息传递”的运行流程。

3.GCNConv子类

GCNConv的数学定义为 $$\mathbf{x}{i}^{(k)}=\sum j\in \mathcal{N}(i)\cup i\frac{1}{\sqrt{\mathrm{deg}(i)}\cdot \sqrt{\mathrm{deg}(j)}}\cdot \left(\mathbf{\Theta }\cdot {\mathbf{x}}_j^{(k-1)}\right),$$ 其中，邻接节点的表征${\mathbf{x}}_j^{(k-1)}$首先通过与权重矩阵$\mathbf{\Theta }$相乘进行变换，然后按端点的度$\mathrm{deg}(i),\mathrm{deg}(j)$进行归一化处理，最后进行求和。这个公式可以分为以下几个步骤：

• 向邻接矩阵添加自环边。
• 对节点表征做线性转换。
• 计算归一化系数。
• 归一化邻接节点的节点表征。
• 将相邻节点表征相加（"求和 "聚合）。

步骤1-3通常是在消息传递发生之前计算的。步骤4-5可以使用MessagePassing基类轻松处理。

作业

• 总结MessagePassing基类的运行流程
• • 复现一个一层的图神经网络的构造，总结通过继承MessagePassing基类来构造自己的图神经网络类的规范。

def propagate(self, edge_index: Adj, size: Size = None, **kwargs):
    '''
    args
    '''
    size = self.__check_input__(edge_index, size)

    # Run "fused" message and aggregation (if applicable).
    if (isinstance(edge_index, SparseTensor) and self.fuse
            and not self.__explain__):
        coll_dict = self.__collect__(self.__fused_user_args__, edge_index,
                                     size, kwargs)

        msg_aggr_kwargs = self.inspector.distribute(
            'message_and_aggregate', coll_dict)
        out = self.message_and_aggregate(edge_index, **msg_aggr_kwargs)

        update_kwargs = self.inspector.distribute('update', coll_dict)
        return self.update(out, **update_kwargs)

    # Otherwise, run both functions in separation.
    elif isinstance(edge_index, Tensor) or not self.fuse:
        coll_dict = self.__collect__(self.__user_args__, edge_index, size,
                                     kwargs)

        msg_kwargs = self.inspector.distribute('message', coll_dict)
        out = self.message(**msg_kwargs)

        # For `GNNExplainer`, we require a separate message and aggregate
        # procedure since this allows us to inject the `edge_mask` into the
        # message passing computation scheme.
        if self.__explain__:
            edge_mask = self.__edge_mask__.sigmoid()
            # Some ops add self-loops to `edge_index`. We need to do the
            # same for `edge_mask` (but do not train those).
            if out.size(self.node_dim) != edge_mask.size(0):
                loop = edge_mask.new_ones(size[0])
                edge_mask = torch.cat([edge_mask, loop], dim=0)
            assert out.size(self.node_dim) == edge_mask.size(0)
            out = out * edge_mask.view([-1] + [1] * (out.dim() - 1))

        aggr_kwargs = self.inspector.distribute('aggregate', coll_dict)
        out = self.aggregate(out, **aggr_kwargs)

        update_kwargs = self.inspector.distribute('update', coll_dict)
        return self.update(out, **update_kwargs)

上面的代码中，propagate函数会进行信息的传播计算过程。当fuse时，执行message_and_aggregate和update，否则执行message、aggregate和update函数。

import torch
from torch_geometric.nn import MessagePassing
from torch_geometric.utils import add_self_loops, degree
from torch_sparse import SparseTensor

class GCNConv(MessagePassing):
    def __init__(self, in_channels, out_channels):
        super(GCNConv, self).__init__(aggr='add', flow='source_to_target')
        # "Add" aggregation (Step 5).
        # flow='source_to_target' 表示消息从源节点传播到目标节点
        print("`constructor` is called")
        self.lin = torch.nn.Linear(in_channels, out_channels)

    def forward(self, x, edge_index):
        # x has shape [N, in_channels]
        # edge_index has shape [2, E]

        # Step 1: Add self-loops to the adjacency matrix.
        edge_index, _ = add_self_loops(edge_index, num_nodes=x.size(0))

        # Step 2: Linearly transform node feature matrix.
        x = self.lin(x)

        # Step 3: Compute normalization.
        row, col = edge_index
        deg = degree(col, x.size(0), dtype=x.dtype)
        deg_inv_sqrt = deg.pow(-0.5)
        norm = deg_inv_sqrt[row] * deg_inv_sqrt[col]

        # Step 4-5: Start propagating messages.
        adjmat = SparseTensor(row=edge_index[0], col=edge_index[1], value=torch.ones(edge_index.shape[1]))
        # 此处传的不再是edge_idex，而是SparseTensor类型的Adjancency Matrix
        print("`forward` is called")
        return self.propagate(adjmat, x=x, norm=norm, deg=deg.view((-1, 1)))

    def message(self, x_j, norm, deg_i):
        # x_j has shape [E, out_channels]
        # deg_i has shape [E, 1]
        # Step 4: Normalize node features.
        print("`message` is called")
        return norm.view(-1, 1) * x_j * deg_i

    def aggregate(self, inputs, index, ptr, dim_size):
        #print('self.aggr:', self.aggr)
        print("`aggregate` is called")
        return super().aggregate(inputs, index, ptr=ptr, dim_size=dim_size)

    '''
    def message_and_aggregate(self, adj_t, x, norm):
        print('`message_and_aggregate` is called')
        # 没有实现真实的消息传递与消息聚合的操作
    '''
    def update(self, inputs, deg):
        print("`update` is called")
        return inputs
        
from torch_geometric.datasets import Planetoid

dataset = Planetoid(root='dataset/Cora', name='Cora')
data = dataset[0]

net = GCNConv(data.num_features, 64)
h_nodes = net(data.x, data.edge_index)
print(h_nodes.shape)