数据完整存储与内存的数据集类+节点预测与边预测任务实践

数据完全存于内存的数据集类

本文为学习记录，完整笔记见DataWhale

InMemoryDataset基类简介

class InMemoryDataset(root: Optional[str] = None, transform: Optional[Callable] = None, pre_transform: Optional[Callable] = None, pre_filter: Optional[Callable] = None)

import torch
from torch_geometric.data import InMemoryDataset, download_url

class MyOwnDataset(InMemoryDataset):
    def __init__(self, root, transform=None, pre_transform=None, pre_filter=None):
        super().__init__(root=root, transform=transform, pre_transform=pre_transform, pre_filter=pre_filter)
        self.data, self.slices = torch.load(self.processed_paths[0])

    @property
    def raw_file_names(self):
        return ['some_file_1', 'some_file_2', ...]

    @property
    def processed_file_names(self):
        return ['data.pt']

    def download(self):
        # Download to `self.raw_dir`.
        download_url(url, self.raw_dir)
        ...

    def process(self):
        # Read data into huge `Data` list.
        data_list = [...]

        if self.pre_filter is not None:
            data_list = [data for data in data_list if self.pre_filter(data)]

        if self.pre_transform is not None:
            data_list = [self.pre_transform(data) for data in data_list]

        data, slices = self.collate(data_list)
        torch.save((data, slices), self.processed_paths[0])

定义InMemoryDataset子类

以公开数据集PubMed为例子。PubMed数据集存储的是文章引用网络，文章对应图的结点，如果两篇文章存在引用关系（无论引用与被引），则这两篇文章对应的结点之间存在边。该数据集来源于论文Revisiting Semi-Supervised Learning with Graph Embeddings。我们直接基于PyG中的Planetoid类修改得到下面的PlanetoidPubMed数据集类。

import os.path as osp

import torch
from torch_geometric.data import (InMemoryDataset, download_url)
from torch_geometric.io import read_planetoid_data

class PlanetoidPubMed(InMemoryDataset):
    r"""The citation network datasets "PubMed" from the
    `"Revisiting Semi-Supervised Learning with Graph Embeddings"
    <https://arxiv.org/abs/1603.08861>`_ paper.
    Nodes represent documents and edges represent citation links.
    Training, validation and test splits are given by binary masks.

    Args:
        root (string): Root directory where the dataset should be saved.
        split (string): The type of dataset split
            (:obj:`"public"`, :obj:`"full"`, :obj:`"random"`).
            If set to :obj:`"public"`, the split will be the public fixed split
            from the
            `"Revisiting Semi-Supervised Learning with Graph Embeddings"
            <https://arxiv.org/abs/1603.08861>`_ paper.
            If set to :obj:`"full"`, all nodes except those in the validation
            and test sets will be used for training (as in the
            `"FastGCN: Fast Learning with Graph Convolutional Networks via
            Importance Sampling" <https://arxiv.org/abs/1801.10247>`_ paper).
            If set to :obj:`"random"`, train, validation, and test sets will be
            randomly generated, according to :obj:`num_train_per_class`,
            :obj:`num_val` and :obj:`num_test`. (default: :obj:`"public"`)
        num_train_per_class (int, optional): The number of training samples
            per class in case of :obj:`"random"` split. (default: :obj:`20`)
        num_val (int, optional): The number of validation samples in case of
            :obj:`"random"` split. (default: :obj:`500`)
        num_test (int, optional): The number of test samples in case of
            :obj:`"random"` split. (default: :obj:`1000`)
        transform (callable, optional): A function/transform that takes in an
            :obj:`torch_geometric.data.Data` object and returns a transformed
            version. The data object will be transformed before every access.
            (default: :obj:`None`)
        pre_transform (callable, optional): A function/transform that takes in
            an :obj:`torch_geometric.data.Data` object and returns a
            transformed version. The data object will be transformed before
            being saved to disk. (default: :obj:`None`)
    """

    url = 'https://github.com/kimiyoung/planetoid/raw/master/data'

    def __init__(self, root, split="public", num_train_per_class=20,
                 num_val=500, num_test=1000, transform=None,
                 pre_transform=None):

        super(PlanetoidPubMed, self).__init__(root, transform, pre_transform)
        self.data, self.slices = torch.load(self.processed_paths[0])

        self.split = split
        assert self.split in ['public', 'full', 'random']

        if split == 'full':
            data = self.get(0)
            data.train_mask.fill_(True)
            data.train_mask[data.val_mask | data.test_mask] = False
            self.data, self.slices = self.collate([data])

        elif split == 'random':
            data = self.get(0)
            data.train_mask.fill_(False)
            for c in range(self.num_classes):
                idx = (data.y == c).nonzero(as_tuple=False).view(-1)
                idx = idx[torch.randperm(idx.size(0))[:num_train_per_class]]
                data.train_mask[idx] = True

            remaining = (~data.train_mask).nonzero(as_tuple=False).view(-1)
            remaining = remaining[torch.randperm(remaining.size(0))]

            data.val_mask.fill_(False)
            data.val_mask[remaining[:num_val]] = True

            data.test_mask.fill_(False)
            data.test_mask[remaining[num_val:num_val + num_test]] = True

            self.data, self.slices = self.collate([data])

    @property
    def raw_dir(self):
        return osp.join(self.root, 'raw')

    @property
    def processed_dir(self):
        return osp.join(self.root, 'processed')

    @property
    def raw_file_names(self):
        names = ['x', 'tx', 'allx', 'y', 'ty', 'ally', 'graph', 'test.index']
        return ['ind.pubmed.{}'.format(name) for name in names]

    @property
    def processed_file_names(self):
        return 'data.pt'

    def download(self):
        for name in self.raw_file_names:
            download_url('{}/{}'.format(self.url, name), self.raw_dir)

    def process(self):
        data = read_planetoid_data(self.raw_dir, 'pubmed')
        data = data if self.pre_transform is None else self.pre_transform(data)
        torch.save(self.collate([data]), self.processed_paths[0])

    def __repr__(self):
        return '{}()'.format(self.name)

查看这个数据集：

dataset = PlanetoidPubMed('../dataset/Planetoid/PubMed')
print(dataset.num_classes)
print(dataset[0].num_nodes)
print(dataset[0].num_edges)
print(dataset[0].num_features)

# 3
# 19717
# 88648
# 500

可以看到这个数据集包含三个分类任务，共19,717个结点，88,648条边，节点特征维度为500。

节点预测与边预测任务实践

节点预测任务实践

重定义一个GAT神经网络，使其能够通过参数定义GATConv的层数，以及每一层GATConv的out_channels。神经网络模型定义如下：

class GAT(torch.nn.Module):
    def __init__(self, num_features, hidden_channels_list, num_classes):
        super(GAT, self).__init__()
        torch.manual_seed(12345)
        hns = [num_features] + hidden_channels_list
        conv_list = []
        for idx in range(len(hidden_channels_list)):
            conv_list.append((GATConv(hns[idx], hns[idx+1]), 'x, edge_index -> x'))
            conv_list.append(ReLU(inplace=True),)

        self.convseq = Sequential('x, edge_index', conv_list)
        self.linear = Linear(hidden_channels_list[-1], num_classes)

    def forward(self, x, edge_index):
        x = self.convseq(x, edge_index)
        x = F.dropout(x, p=0.5, training=self.training)
        x = self.linear(x)
        return x

完整的代码可见于codes/node_classification.py

边预测任务实践

边预测任务，如果是预测两个节点之间是否存在边。拿到一个图数据集，我们有节点特征矩阵x，和哪些节点之间存在边的信息edge_index。edge_index存储的便是正样本，为了构建边预测任务，我们需要生成一些负样本，即采样一些不存在边的节点对作为负样本边，正负样本应平衡。此外要将样本分为训练集、验证集和测试集三个集合。

PyG中为我们提供了现成的方法，train_test_split_edges(data, val_ratio=0.05, test_ratio=0.1)，其第一个参数为torch_geometric.data.Data对象，第二参数为验证集所占比例，第三个参数为测试集所占比例。该函数将自动地采样得到负样本，并将正负样本分成训练集、验证集和测试集三个集合。
下面使用Cora数据集作为例子进行边预测任务说明。

首先是获取数据集并进行分析：

import os.path as osp

from torch_geometric.utils import negative_sampling
from torch_geometric.datasets import Planetoid
import torch_geometric.transforms as T
from torch_geometric.utils import train_test_split_edges

dataset = 'Cora'
path = osp.join(osp.dirname(osp.realpath(__file__)), '..', 'data', dataset)
dataset = Planetoid(path, dataset, transform=T.NormalizeFeatures())
data = dataset[0]
data.train_mask = data.val_mask = data.test_mask = data.y = None
data = train_test_split_edges(data)

print(data.edge_index.shape)
# torch.Size([2, 10556])

for key in data.keys:
    print(key, getattr(data, key).shape)

# x torch.Size([2708, 1433])
# val_pos_edge_index torch.Size([2, 263])
# test_pos_edge_index torch.Size([2, 527])
# train_pos_edge_index torch.Size([2, 8976])
# train_neg_adj_mask torch.Size([2708, 2708])
# val_neg_edge_index torch.Size([2, 263])
# test_neg_edge_index torch.Size([2, 527])
# 263 + 527 + 8976 = 9766 != 10556
# 263 + 527 + 8976/2 = 5278 = 10556/2

接下来构建神经网络模型：

import torch
from torch_geometric.nn import GCNConv

class Net(torch.nn.Module):
    def __init__(self, in_channels, out_channels):
        super(Net, self).__init__()
        self.conv1 = GCNConv(in_channels, 128)
        self.conv2 = GCNConv(128, out_channels)

    def encode(self, x, edge_index):
        x = self.conv1(x, edge_index)
        x = x.relu()
        return self.conv2(x, edge_index)

    def decode(self, z, pos_edge_index, neg_edge_index):
        edge_index = torch.cat([pos_edge_index, neg_edge_index], dim=-1)
        return (z[edge_index[0]] * z[edge_index[1]]).sum(dim=-1)

    def decode_all(self, z):
        prob_adj = z @ z.t()
        return (prob_adj > 0).nonzero(as_tuple=False).t()

用于做边预测的神经网络主要由两部分组成：其一是编码（encode）；其二是解码（decode），它边两端节点的表征生成边为真的几率（odds）。

待完成！立flag！！

参考资料

• InMemoryDataset官方文档：torch_geometric.data.InMemoryDataset
• Data官方文档：torch_geometric.data.Data
• 提出PubMed数据集的论文：Revisiting Semi-Supervised Learning with Graph Embeddings
• Planetoid官方文档：[torch_geometric.datasets.Planetoid](torch_geometric.datasets — pytorch_geometric 1.7.0 documentation (pytorch-geometric.readthedocs.io))
• Sequential官网文档：torch_geometric.nn.Sequential