跟着官方文档学DGL框架第十天——训练图神经网络之链接预测_链接预测图神经网络-程序员宅基地

参考链接

https://docs.dgl.ai/en/latest/guide/training-link.html#guide-training-link-prediction

概述

什么是链接预测

链接预测就是预测图中给定节点间是否存在边，常用于推荐系统。

形式化地，给定节点 $u$ 和 $v$ ，链接预测的任务就是得到它们间存在链接的概率 $y_{u,v}=\phi \left ( u,v\right )$ 。具体到GNN上，我们通过L层的GNN得到节点 $u$ 和 $v$ 的表示 $h_{u}^{\left ( L\right )}$ 和 $h_{v}^{\left ( L\right )}$ ，然后通过预测模型得到存在链接的概率 $y_{u,v}=\phi \left ( h_{u}^{\left ( L\right )},h_{v}^{\left ( L\right )}\right )$ 。

链接预测的优化目标

链接预测的优化方式通常采用负采样。即给定一条链接 $u$ 和 $v$ 的边，我们希望 $u$ 与 $v$ 的得分（链接概率）高于 $u$ 与其他节点 ${v}'$ 的得分。而其他节点又太多了，为了提高效率，我们只从任意噪声分布 ${v}'\in P_{n}\left ( v\right )$ 采样一部分作为负样本。

常见的损失函数有：

交叉熵损失（Cross-entropy loss）： $L=-log\ \sigma \left ( y_{u,v}\right )-\sum_{v_{i}\sim P_{n}\left ( v\right ),i=1,\cdot \cdot \cdot ,k}^{}log\left [ 1-\sigma \left ( y_{u,v_{i}}\right )\right ]$
贝叶斯个性化排序损失（BPR loss）： $L=\sum_{v_{i}\sim P_{n}\left ( v\right ),i=1,\cdot \cdot \cdot ,k}-log\left ( y_{u,v}-y_{u,v_{i}}\right )$
间隔损失（Margin loss）： $L=\sum_{v_{i}\sim P_{n}\left ( v\right ),i=1,\cdot \cdot \cdot ,k}max\left ( 0,M-y_{u,v}+y_{u,v_{i}}\right )$

同构图上的链接预测

处理数据

依然使用DGL内置的数据集“Citeseer”：

dataset = dgl.data.CiteseerGraphDataset()

graph = dataset[0]

得分（链接概率）计算方式

我们将节点间的得分（链接概率）视为节点间连边的边特征“score”，通过节点表示计算得到，这里采用最简单的内积函数。

class DotProductPredictor(nn.Module):
    def forward(self, graph, h):
        with graph.local_scope():
            graph.ndata['h'] = h
            graph.apply_edges(fn.u_dot_v('h', 'h', 'score'))
            return graph.edata['score']

负采样

由上面的得分计算方式可知，得分的计算需要节点间存在连边。为了让节点与负样本间也存在连边，我们选择单独为负样本构建一个图。

def construct_negative_graph(graph, k):
    src, dst = graph.edges()

    neg_src = src.repeat_interleave(k)
    neg_dst = torch.randint(0, graph.num_nodes(), (len(src) * k,))
    return dgl.graph((neg_src, neg_dst), num_nodes=graph.num_nodes())

对于输入的原始图，我们将源节点复制k份，但目标节点由随机采样得到，如此，每条边有k个负样本，将它们连接起来构成负采样图。

节点表示模型

还是使用两层GraphSAGE。

class SAGE(nn.Module):
    def __init__(self, in_feats, hid_feats, out_feats):
        super().__init__()
        self.conv1 = dglnn.SAGEConv(
            in_feats=in_feats, out_feats=hid_feats, aggregator_type='mean')
        self.conv2 = dglnn.SAGEConv(
            in_feats=hid_feats, out_feats=out_feats, aggregator_type='mean')

    def forward(self, graph, inputs):
        h = self.conv1(graph, inputs)
        h = F.relu(h)
        h = self.conv2(graph, h)
        return h

预测得分模型

通过“SAGE()”得到节点表示后，分别计算正样本的得分和负样本的得分。

class Model(nn.Module):
    def __init__(self, in_features, hidden_features, out_features):
        super().__init__()
        self.sage = SAGE(in_features, hidden_features, out_features)
        self.pred = DotProductPredictor()
    def forward(self, g, neg_g, x):
        h = self.sage(g, x)
        return self.pred(g, h), self.pred(neg_g, h)

损失函数

这里采用间隔损失，由于一个正样本对应多个负样本，所以这里调整了张量的shape，以利用广播机制。

def compute_loss(pos_score, neg_score):
    n_edges = pos_score.shape[0]
    return (1 - pos_score.unsqueeze(1) + neg_score.view(n_edges, -1)).clamp(min=0).mean()

开始训练

node_features = graph.ndata['feat']
n_features = node_features.shape[1]
k = 5
model = Model(n_features, 100, 100)
opt = torch.optim.Adam(model.parameters())
for epoch in range(10):
    negative_graph = construct_negative_graph(graph, k)
    pos_score, neg_score = model(graph, negative_graph, node_features)
    loss = compute_loss(pos_score, neg_score)
    opt.zero_grad()
    loss.backward()
    opt.step()
    print(loss.item())

获取节点表示

如果想得到节点的表示，只需要调用模型的模型表示模块即可。

node_embeddings = model.sage(graph, node_features)

异构图上的链接预测

处理数据

使用“跟着官方文档学DGL框架第八天”中人工构建的异构图数据集，包含两种类型的结点和六种类型的边。

n_users = 1000
n_items = 500
n_follows = 3000
n_clicks = 5000
n_dislikes = 500
n_hetero_features = 10
n_user_classes = 5
n_max_clicks = 10

follow_src = np.random.randint(0, n_users, n_follows)
follow_dst = np.random.randint(0, n_users, n_follows)
click_src = np.random.randint(0, n_users, n_clicks)
click_dst = np.random.randint(0, n_items, n_clicks)
dislike_src = np.random.randint(0, n_users, n_dislikes)
dislike_dst = np.random.randint(0, n_items, n_dislikes)

hetero_graph = dgl.heterograph({
    
    ('user', 'follow', 'user'): (follow_src, follow_dst),
    ('user', 'followed-by', 'user'): (follow_dst, follow_src),
    ('user', 'click', 'item'): (click_src, click_dst),
    ('item', 'clicked-by', 'user'): (click_dst, click_src),
    ('user', 'dislike', 'item'): (dislike_src, dislike_dst),
    ('item', 'disliked-by', 'user'): (dislike_dst, dislike_src)})

hetero_graph.nodes['user'].data['feature'] = torch.randn(n_users, n_hetero_features)
hetero_graph.nodes['item'].data['feature'] = torch.randn(n_items, n_hetero_features)
hetero_graph.nodes['user'].data['label'] = torch.randint(0, n_user_classes, (n_users,))
hetero_graph.edges['click'].data['label'] = torch.randint(1, n_max_clicks, (n_clicks,)).float()
# randomly generate training masks on user nodes and click edges
hetero_graph.nodes['user'].data['train_mask'] = torch.zeros(n_users, dtype=torch.bool).bernoulli(0.6)
hetero_graph.edges['click'].data['train_mask'] = torch.zeros(n_clicks, dtype=torch.bool).bernoulli(0.6)

得分（链接概率）计算方式

与同构图不同的是，计算得分时需要指定边的类型，我们只计算一种边上的得分。

class HeteroDotProductPredictor(nn.Module):
    def forward(self, graph, h, etype):
        with graph.local_scope():
            graph.ndata['h'] = h
            graph.apply_edges(fn.u_dot_v('h', 'h', 'score'), etype=etype)
            return graph.edges[etype].data['score']

负采样

对要进行链接预测的边类型构造一个负采样图。

def construct_negative_graph(graph, k, etype):
    utype, _, vtype = etype
    src, dst = graph.edges(etype=etype)
    neg_src = src.repeat_interleave(k)
    neg_dst = torch.randint(0, graph.num_nodes(vtype), (len(src) * k,))
    return dgl.heterograph(
        {
    etype: (neg_src, neg_dst)},
        num_nodes_dict={
    ntype: graph.num_nodes(ntype) for ntype in graph.ntypes})

节点表示模型

老办法，“RGCN()”：

class RGCN(nn.Module):
    def __init__(self, in_feats, hid_feats, out_feats, rel_names):
        super().__init__()
        self.conv1 = dglnn.HeteroGraphConv({
    
            rel: dglnn.GraphConv(in_feats, hid_feats)
            for rel in rel_names}, aggregate='sum')
        self.conv2 = dglnn.HeteroGraphConv({
    
            rel: dglnn.GraphConv(hid_feats, out_feats)
            for rel in rel_names}, aggregate='sum')

    def forward(self, graph, inputs):
        h = self.conv1(graph, inputs)
        h = {
    k: F.relu(v) for k, v in h.items()}
        h = self.conv2(graph, h)
        return h

预测得分模型

class Model(nn.Module):
    def __init__(self, in_features, hidden_features, out_features, rel_names):
        super().__init__()
        self.sage = RGCN(in_features, hidden_features, out_features, rel_names)
        self.pred = HeteroDotProductPredictor()
    def forward(self, g, neg_g, x, etype):
        h = self.sage(g, x)
        return self.pred(g, h, etype), self.pred(neg_g, h, etype)

损失函数

def compute_loss(pos_score, neg_score):
    n_edges = pos_score.shape[0]
    return (1 - pos_score.unsqueeze(1) + neg_score.view(n_edges, -1)).clamp(min=0).mean()

开始训练

model = Model(10, 20, 5, hetero_graph.etypes)
user_feats = hetero_graph.nodes['user'].data['feature']
item_feats = hetero_graph.nodes['item'].data['feature']
node_features = {
    'user': user_feats, 'item': item_feats}
opt = torch.optim.Adam(model.parameters())
for epoch in range(10):
    negative_graph = construct_negative_graph(hetero_graph, k, ('user', 'click', 'item'))
    pos_score, neg_score = model(hetero_graph, negative_graph, node_features, ('user', 'click', 'item'))
    loss = compute_loss(pos_score, neg_score)
    opt.zero_grad()
    loss.backward()
    opt.step()
    print(loss.item())

完整代码

同构图上的链接预测

import dgl
import dgl.nn as dglnn
import dgl.function as fn
import torch.nn as nn
import torch.nn.functional as F
import torch

class DotProductPredictor(nn.Module):
    def forward(self, graph, h):
        with graph.local_scope():
            graph.ndata['h'] = h
            graph.apply_edges(fn.u_dot_v('h', 'h', 'score'))
            return graph.edata['score']


def construct_negative_graph(graph, k):
    src, dst = graph.edges()

    neg_src = src.repeat_interleave(k)
    neg_dst = torch.randint(0, graph.num_nodes(), (len(src) * k,))
    return dgl.graph((neg_src, neg_dst), num_nodes=graph.num_nodes())

class SAGE(nn.Module):
    def __init__(self, in_feats, hid_feats, out_feats):
        super().__init__()
        self.conv1 = dglnn.SAGEConv(
            in_feats=in_feats, out_feats=hid_feats, aggregator_type='mean')
        self.conv2 = dglnn.SAGEConv(
            in_feats=hid_feats, out_feats=out_feats, aggregator_type='mean')

    def forward(self, graph, inputs):
        h = self.conv1(graph, inputs)
        h = F.relu(h)
        h = self.conv2(graph, h)
        return h

class Model(nn.Module):
    def __init__(self, in_features, hidden_features, out_features):
        super().__init__()
        self.sage = SAGE(in_features, hidden_features, out_features)
        self.pred = DotProductPredictor()
    def forward(self, g, neg_g, x):
        h = self.sage(g, x)
        return self.pred(g, h), self.pred(neg_g, h)

def compute_loss(pos_score, neg_score):
    n_edges = pos_score.shape[0]
    return (1 - pos_score.unsqueeze(1) + neg_score.view(n_edges, -1)).clamp(min=0).mean()

dataset = dgl.data.CiteseerGraphDataset()

graph = dataset[0]
node_features = graph.ndata['feat']
n_features = node_features.shape[1]
k = 5
model = Model(n_features, 100, 100)
opt = torch.optim.Adam(model.parameters())
for epoch in range(10):
    negative_graph = construct_negative_graph(graph, k)
    pos_score, neg_score = model(graph, negative_graph, node_features)
    loss = compute_loss(pos_score, neg_score)
    opt.zero_grad()
    loss.backward()
    opt.step()
    print(loss.item())

node_embeddings = model.sage(graph, node_features)

异构图上的链接预测

import dgl
import dgl.nn as dglnn
import dgl.function as fn
import torch.nn as nn
import torch.nn.functional as F
import torch
import numpy as np

n_users = 1000
n_items = 500
n_follows = 3000
n_clicks = 5000
n_dislikes = 500
n_hetero_features = 10
n_user_classes = 5
n_max_clicks = 10

follow_src = np.random.randint(0, n_users, n_follows)
follow_dst = np.random.randint(0, n_users, n_follows)
click_src = np.random.randint(0, n_users, n_clicks)
click_dst = np.random.randint(0, n_items, n_clicks)
dislike_src = np.random.randint(0, n_users, n_dislikes)
dislike_dst = np.random.randint(0, n_items, n_dislikes)

hetero_graph = dgl.heterograph({
    
    ('user', 'follow', 'user'): (follow_src, follow_dst),
    ('user', 'followed-by', 'user'): (follow_dst, follow_src),
    ('user', 'click', 'item'): (click_src, click_dst),
    ('item', 'clicked-by', 'user'): (click_dst, click_src),
    ('user', 'dislike', 'item'): (dislike_src, dislike_dst),
    ('item', 'disliked-by', 'user'): (dislike_dst, dislike_src)})

hetero_graph.nodes['user'].data['feature'] = torch.randn(n_users, n_hetero_features)
hetero_graph.nodes['item'].data['feature'] = torch.randn(n_items, n_hetero_features)
hetero_graph.nodes['user'].data['label'] = torch.randint(0, n_user_classes, (n_users,))
hetero_graph.edges['click'].data['label'] = torch.randint(1, n_max_clicks, (n_clicks,)).float()
# randomly generate training masks on user nodes and click edges
hetero_graph.nodes['user'].data['train_mask'] = torch.zeros(n_users, dtype=torch.bool).bernoulli(0.6)
hetero_graph.edges['click'].data['train_mask'] = torch.zeros(n_clicks, dtype=torch.bool).bernoulli(0.6)

class HeteroDotProductPredictor(nn.Module):
    def forward(self, graph, h, etype):
        with graph.local_scope():
            graph.ndata['h'] = h
            graph.apply_edges(fn.u_dot_v('h', 'h', 'score'), etype=etype)
            return graph.edges[etype].data['score']

def construct_negative_graph(graph, k, etype):
    utype, _, vtype = etype
    src, dst = graph.edges(etype=etype)
    neg_src = src.repeat_interleave(k)
    neg_dst = torch.randint(0, graph.num_nodes(vtype), (len(src) * k,))
    return dgl.heterograph(
        {
    etype: (neg_src, neg_dst)},
        num_nodes_dict={
    ntype: graph.num_nodes(ntype) for ntype in graph.ntypes})


class RGCN(nn.Module):
    def __init__(self, in_feats, hid_feats, out_feats, rel_names):
        super().__init__()
        self.conv1 = dglnn.HeteroGraphConv({
    
            rel: dglnn.GraphConv(in_feats, hid_feats)
            for rel in rel_names}, aggregate='sum')
        self.conv2 = dglnn.HeteroGraphConv({
    
            rel: dglnn.GraphConv(hid_feats, out_feats)
            for rel in rel_names}, aggregate='sum')

    def forward(self, graph, inputs):
        h = self.conv1(graph, inputs)
        h = {
    k: F.relu(v) for k, v in h.items()}
        h = self.conv2(graph, h)
        return h

class Model(nn.Module):
    def __init__(self, in_features, hidden_features, out_features, rel_names):
        super().__init__()
        self.sage = RGCN(in_features, hidden_features, out_features, rel_names)
        self.pred = HeteroDotProductPredictor()
    def forward(self, g, neg_g, x, etype):
        h = self.sage(g, x)
        return self.pred(g, h, etype), self.pred(neg_g, h, etype)

def compute_loss(pos_score, neg_score):
    n_edges = pos_score.shape[0]
    return (1 - pos_score.unsqueeze(1) + neg_score.view(n_edges, -1)).clamp(min=0).mean()

k = 5
model = Model(10, 20, 5, hetero_graph.etypes)
user_feats = hetero_graph.nodes['user'].data['feature']
item_feats = hetero_graph.nodes['item'].data['feature']
node_features = {
    'user': user_feats, 'item': item_feats}
opt = torch.optim.Adam(model.parameters())
for epoch in range(10):
    negative_graph = construct_negative_graph(hetero_graph, k, ('user', 'click', 'item'))
    pos_score, neg_score = model(hetero_graph, negative_graph, node_features, ('user', 'click', 'item'))
    loss = compute_loss(pos_score, neg_score)
    opt.zero_grad()
    loss.backward()
    opt.step()
    print(loss.item())

本文链接：https://blog.csdn.net/beilizhang/article/details/111878171

原作者删帖不实内容删帖广告或垃圾文章投诉

智能推荐

c# 调用c++ lib静态库_c#调用lib-程序员宅基地

文章浏览阅读2w次，点赞7次，收藏51次。四个步骤1.创建C++ Win32项目动态库dll 2.在Win32项目动态库中添加外部依赖项 lib头文件和lib库3.导出C接口4.c#调用c++动态库开始你的表演...①创建一个空白的解决方案，在解决方案中添加 Visual C++ , Win32 项目空白解决方案的创建：添加Visual C++ , Win32 项目这......_c#调用lib

deepin/ubuntu安装苹方字体-程序员宅基地

文章浏览阅读4.6k次。苹方字体是苹果系统上的黑体，挺好看的。注重颜值的网站都会使用，例如知乎：font-family: -apple-system, BlinkMacSystemFont, Helvetica Neue, PingFang SC, Microsoft YaHei, Source Han Sans SC, Noto Sans CJK SC, W..._ubuntu pingfang

html表单常见操作汇总_html表单的处理程序有那些-程序员宅基地

文章浏览阅读159次。表单表单概述表单标签表单域按钮控件demo表单标签表单标签基本语法结构<form action="处理数据程序的url地址“ method=”get|post“ name="表单名称”></form><!--method将表单中的数据传送给服务器处理，get方式直接显示在url地址中，数据可以被缓存，且长度有限制；而post方式数据隐藏传输，_html表单的处理程序有那些

PHP设置谷歌验证器（Google Authenticator）实现操作二步验证_php otp 验证器-程序员宅基地

文章浏览阅读1.2k次。使用说明:开启Google的登陆二步验证（即Google Authenticator服务）后用户登陆时需要输入额外由手机客户端生成的一次性密码。实现Google Authenticator功能需要服务器端和客户端的支持。服务器端负责密钥的生成、验证一次性密码是否正确。客户端记录密钥后生成一次性密码。下载谷歌验证类库文件放到项目合适位置(我这边放在项目Vender下面)https://github.com/PHPGangsta/GoogleAuthenticatorPHP代码示例://引入谷_php otp 验证器

【Python】matplotlib.plot画图横坐标混乱及间隔处理_matplotlib更改横轴间距-程序员宅基地

文章浏览阅读4.3k次，点赞5次，收藏11次。matplotlib.plot画图横坐标混乱及间隔处理_matplotlib更改横轴间距

docker — 容器存储_docker 保存容器-程序员宅基地

文章浏览阅读2.2k次。①Storage driver 处理各镜像层及容器层的处理细节，实现了多层数据的堆叠，为用户提供了多层数据合并后的统一视图②所有 Storage driver 都使用可堆叠图像层和写时复制（CoW）策略③docker info 命令可查看当系统上的 storage driver主要用于测试目的，不建议用于生成环境。_docker 保存容器

随便推点

网络拓扑结构_网络拓扑csdn-程序员宅基地

文章浏览阅读834次，点赞27次，收藏13次。网络拓扑结构是指计算机网络中各组件（如计算机、服务器、打印机、路由器、交换机等设备）及其连接线路在物理布局或逻辑构型上的排列形式。这种布局不仅描述了设备间的实际物理连接方式，也决定了数据在网络中流动的路径和方式。不同的网络拓扑结构影响着网络的性能、可靠性、可扩展性及管理维护的难易程度。_网络拓扑csdn

JS重写Date函数，兼容IOS系统_date.prototype 将所有 ios-程序员宅基地

文章浏览阅读1.8k次，点赞5次，收藏8次。IOS系统Date的坑要创建一个指定时间的new Date对象时，通常的做法是：new Date("2020-09-21 11:11:00")这行代码在 PC 端和安卓端都是正常的，而在 iOS 端则会提示 Invalid Date 无效日期。在IOS年月日中间的横岗许换成斜杠，也就是new Date("2020/09/21 11:11:00")通常为了兼容IOS的这个坑，需要做一些额外的特殊处理，笔者在开发的时候经常会忘了兼容IOS系统。所以就想试着重写Date函数，一劳永逸，避免每次ne_date.prototype 将所有 ios