使用DGL实现GAT（并在6个节点的2分类图中进行简单应用）

い☞殘風☜、™2023-12-12 18:50

formal文件（在cora数据集上的应用）

python 复制代码 
import torch
import torch.nn as nn
import torch.nn.functional as F
from dgl.data import CoraGraphDataset
import time
import numpy as np
from visdom import Visdom
import dgl
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')


class GATLayer(nn.Module):
    def __init__(self, g, in_dim, out_dim):
        super(GATLayer, self).__init__()
        self.g = g
        # 公式 (1)
        self.fc = nn.Linear(in_dim, out_dim, bias=False)
        # 公式 (2)
        self.attn_fc = nn.Linear(2 * out_dim, 1, bias=False)

    def edge_attention(self, edges):
        # 公式 (2) 所需，边上的用户定义函数
        z2 = torch.cat([edges.src['z'], edges.dst['z']], dim=1)
        a = self.attn_fc(z2)
        return {'e': F.leaky_relu(a)}

    def message_func(self, edges):
        # 公式 (3), (4)所需，传递消息用的用户定义函数
        return {'z': edges.src['z'], 'e': edges.data['e']}

    def reduce_func(self, nodes):
        # 公式 (3), (4)所需, 归约用的用户定义函数
        # 公式 (3)
        alpha = F.softmax(nodes.mailbox['e'], dim=1)
        # 公式 (4)
        h = torch.sum(alpha * nodes.mailbox['z'], dim=1)
        return {'h': h}

    def forward(self, h):
        # 公式 (1)
        z = self.fc(h)
        self.g.ndata['z'] = z
        # 公式 (2)
        self.g.apply_edges(self.edge_attention)
        # 公式 (3) & (4)
        self.g.update_all(self.message_func, self.reduce_func)
        return self.g.ndata.pop('h')


class MultiHeadGATLayer(nn.Module):
    def __init__(self, g, in_dim, out_dim, num_heads, merge='cat'):
        super(MultiHeadGATLayer, self).__init__()
        self.heads = nn.ModuleList()
        for i in range(num_heads):
            self.heads.append(GATLayer(g, in_dim, out_dim))
        self.merge = merge

    def forward(self, h):
        head_outs = [attn_head(h) for attn_head in self.heads]
        if self.merge == 'cat':
            # 对输出特征维度（第1维）做拼接
            return torch.cat(head_outs, dim=1)
        else:
            # 用求平均整合多头结果
            return torch.mean(torch.stack(head_outs))


class GAT(nn.Module):
    def __init__(self, g, in_dim, hidden_dim, out_dim, num_heads):
        super(GAT, self).__init__()
        self.layer1 = MultiHeadGATLayer(g, in_dim, hidden_dim, num_heads)
        # 注意输入的维度是 hidden_dim * num_heads 因为多头的结果都被拼接在了
        # 一起。 此外输出层只有一个头。
        self.layer2 = MultiHeadGATLayer(g, hidden_dim * num_heads, out_dim, 1)

    def forward(self, h):
        h = self.layer1(h)
        h = F.elu(h)
        h = self.layer2(h)
        return h


def evaluate(model, features, labels, mask):
    model.eval()
    with torch.no_grad():
        logits = model(features)
        logits = logits[mask]
        labels = labels[mask]
        _, indices = torch.max(logits, dim=1)
        correct = torch.sum(indices == labels)
        return correct.item() * 1.0 / len(labels)


# 加载数据集
dataset = CoraGraphDataset('./cora')
graph = dataset[0]
graph = dgl.remove_self_loop(graph)
graph = dgl.add_self_loop(graph)
# 把graph搬到gpu上
graph = graph.to(device)

train_mask = graph.ndata['train_mask']
val_mask = graph.ndata['val_mask']
test_mask = graph.ndata['test_mask']
label = graph.ndata['label']
features = graph.ndata['feat']

in_feats = features.shape[1]
n_hidden = 8
n_classes = dataset.num_classes
num_heads = 3
feat_drop = 0.6
attn_drop = 0.5
lr = 0.02
weight_deacy = 3e-4
num_epochs = 31

model = GAT(graph,
            in_dim=features.shape[1],
            hidden_dim=n_hidden,
            out_dim=7,
            num_heads=num_heads)
model = model.to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=lr, weight_decay=weight_deacy)

dur = []

# 使用visdom进行可视化
vis = Visdom()
x = []
y = []

opt = {
    'title': 'GAT on Cora',
    'xlabel': 'epoch',
    'ylabel': 'loss / acc',
    'legend': ['loss', 'val_accuracy']
}

for epoch in range(num_epochs):
    if epoch >= 3:
        t0 = time.time()

    logits = model(features)
    logp = F.log_softmax(logits, 1)
    loss = F.nll_loss(logp[train_mask], label[train_mask])

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    acc_val = evaluate(model, features, label, val_mask)

    x = epoch
    y_loss = loss.cpu().detach().numpy()
    y_acc = acc_val
    vis.line(
        X=[x],
        Y=[[y_loss, y_acc]],
        win='GAT',
        update='append',
        opts=opt
    )
    if epoch >= 3:
        dur.append(time.time() - t0)

    print("Epoch {:05d} | Loss {:.4f} | Time(s) {:.4f} | Accuracy {:.4f}".format(
        epoch, loss.item(), np.mean(dur), acc_val))

acc_test = evaluate(model, features, label, test_mask)
print("Test Accuracy {:.4f}".format(acc_test))

test文件(在6个节点上的二分类应用）

python 复制代码 
import torch
import torch.nn as nn
import torch.nn.functional as F
from dgl.data import CoraGraphDataset
import time
import numpy as np
from visdom import Visdom
import dgl

print('----------test: DGL_GAT----------')

device = torch.device('cpu')


class GATLayer(nn.Module):
    def __init__(self, g, in_dim, out_dim):
        super(GATLayer, self).__init__()
        self.g = g
        # 公式 (1)
        self.fc = nn.Linear(in_dim, out_dim, bias=False)
        # 公式 (2)
        self.attn_fc = nn.Linear(2 * out_dim, 1, bias=False)

    def edge_attention(self, edges):
        # 公式 (2) 所需，边上的用户定义函数
        # 在我们的实验中，注意力机制α是一个单层前馈神经网络，由权重向量a参数化，并应用LeakyReLU非线性（
        # 负输入斜率α = 0.2）。完全展开后，注意力机制计算的系数（由图1（左）所示）可以表示为：

        z2 = torch.cat([edges.src['z'], edges.dst['z']], dim=1)
        a = self.attn_fc(z2)
        return {'e': F.leaky_relu(a)}

    def message_func(self, edges):
        # 公式 (3), (4)所需，传递消息用的用户定义函数
        # 返回的z是源节点的z属性   e是边的e属性
        return {'z': edges.src['z'], 'e': edges.data['e']}

    def reduce_func(self, nodes):
        # 公式 (3), (4)所需, 归约用的用户定义函数
        # 公式 (3)
        alpha = F.softmax(nodes.mailbox['e'], dim=1)
        # 公式 (4)
        h = torch.sum(alpha * nodes.mailbox['z'], dim=1)
        return {'h': h}

    def forward(self, h):
        # 公式 (1)
        z = self.fc(h)
        self.g.ndata['z'] = z
        # 公式 (2)
        self.g.apply_edges(self.edge_attention)
        # 公式 (3) & (4)
        self.g.update_all(self.message_func, self.reduce_func)
        return self.g.ndata.pop('h')


class MultiHeadGATLayer(nn.Module):
    def __init__(self, g, in_dim, out_dim, num_heads, merge='cat'):
        super(MultiHeadGATLayer, self).__init__()
        self.heads = nn.ModuleList()
        for i in range(num_heads):
            self.heads.append(GATLayer(g, in_dim, out_dim))
        self.merge = merge

    def forward(self, h):
        head_outs = [attn_head(h) for attn_head in self.heads]
        if self.merge == 'cat':
            # 对输出特征维度（第1维）做拼接
            return torch.cat(head_outs, dim=1)
        else:
            # 用求平均整合多头结果
            return torch.mean(torch.stack(head_outs))


class GAT(nn.Module):
    def __init__(self, g, in_dim, hidden_dim, out_dim, num_heads):
        super(GAT, self).__init__()
        self.layer1 = MultiHeadGATLayer(g, in_dim, hidden_dim, num_heads)
        # 注意输入的维度是 hidden_dim * num_heads 因为多头的结果都被拼接在了
        # 一起。 此外输出层只有一个头。
        self.layer2 = MultiHeadGATLayer(g, hidden_dim * num_heads, out_dim, 1)

    def forward(self, h):
        h = self.layer1(h.float())
        h = F.elu(h)
        h = self.layer2(h.float())
        return h


def evaluate(model, features, labels, mask):
    model.eval()
    with torch.no_grad():
        logits = model(features)
        logits = logits[mask]
        labels = labels[mask]
        _, indices = torch.max(logits, dim=1)
        correct = torch.sum(indices == labels)
        return correct.item() * 1.0 / len(labels)


# 加载数据集
# dataset = CoraGraphDataset('./cora')
# graph = dataset[0]
# graph = dgl.remove_self_loop(graph)
graph = dgl.graph((torch.tensor([0, 0, 0, 0, 0, 0,
                             1, 1, 1, 1, 1, 1,
                             2, 2, 2, 2, 2, 2,
                             3, 3, 3, 3, 3, 3,
                             4, 4, 4, 4, 4, 4,
                             5, 5, 5, 5, 5, 5,]),
               torch.tensor([0, 1, 2, 3, 4, 5,
                             0, 1, 2, 3,4, 5,
                             0, 1, 2, 3, 4, 5,
                             0, 1, 2, 3, 4, 5,
                             0, 1, 2, 3, 4, 5,
                             0, 1, 2, 3, 4, 5,])))
# graph = dgl.add_self_loop(graph)
# 节点1,2,3
graph.ndata['train_mask'] = torch.tensor([False,True,True,True,False,False])
# 节点0
graph.ndata['val_mask'] = torch.tensor([True,False,False,False,False,False])
# 节点4,5
graph.ndata['test_mask'] = torch.tensor([False,False,False,False,True,True])

graph.ndata['feat'] = torch.tensor([[0,0,0,0,0,0],[1,1,1,1,1,1],[2,2,2,2,2,2],[3,3,3,3,3,3],[4,4,4,4,4,4],[5,5,5,5,5,5]])
graph.ndata['label'] = torch.tensor([1,2,1,1,2,1])
# 把graph搬到gpu上
graph = graph.to(device)

train_mask = graph.ndata['train_mask']
print(graph.ndata['train_mask'])


# print('train_mask:',train_mask)
val_mask = graph.ndata['val_mask']
print(graph.ndata['val_mask'])

test_mask = graph.ndata['test_mask']
print(graph.ndata['test_mask'])


label = graph.ndata['label']

features = graph.ndata['feat']


in_feats = features.shape[1]
print('in_feats:',in_feats)
n_hidden = 8
n_classes = 2
num_heads = 3
feat_drop = 0.6
attn_drop = 0.5
lr = 0.02
weight_deacy = 3e-4
num_epochs = 31

model = GAT(graph,
            in_dim=features.shape[1],
            hidden_dim=n_hidden,
            out_dim=7,
            num_heads=num_heads)
model = model.to(device)
optimizer = torch.optim.Adam(model.parameters(), lr=lr, weight_decay=weight_deacy)

dur = []

# 使用visdom进行可视化
vis = Visdom()
x = []
y = []

opt = {
    'title': 'GAT on Cora',
    'xlabel': 'epoch',
    'ylabel': 'loss / acc',
    'legend': ['loss', 'val_accuracy']
}

for epoch in range(num_epochs):
    if epoch >= 3:
        t0 = time.time()

    logits = model(features)
    logp = F.log_softmax(logits, 1)
    loss = F.nll_loss(logp[train_mask], label[train_mask])

    optimizer.zero_grad()
    loss.backward()
    optimizer.step()
    acc_val = evaluate(model, features, label, val_mask)

    x = epoch
    y_loss = loss.cpu().detach().numpy()
    y_acc = acc_val
    vis.line(
        X=[x],
        Y=[[y_loss, y_acc]],
        win='GAT',
        update='append',
        opts=opt
    )
    if epoch >= 3:
        dur.append(time.time() - t0)

    print("Epoch {:05d} | Loss {:.4f} | Time(s) {:.4f} | Accuracy {:.4f}".format(
        epoch, loss.item(), np.mean(dur), acc_val))

acc_test = evaluate(model, features, label, test_mask)
print("Test Accuracy {:.4f}".format(acc_test))

# print(graph.ndata['h'][1])

print(graph.ndata['z'][1])
相关推荐
江瀚视野19 分钟前
Q3净利增长超预期，文心大模型调用量大增，百度未来如何分析？
人工智能
陪学27 分钟前
百度遭初创企业指控抄袭，维权还是碰瓷？
人工智能·百度·面试·职场和发展·产品运营
QCN_30 分钟前
湘潭大学人工智能考试复习1（软件工程）
人工智能
Landy_Jay31 分钟前
深度学习：GPT-1的MindSpore实践
人工智能·gpt·深度学习
白光白光39 分钟前
量子神经网络
人工智能·深度学习·神经网络
全域观察43 分钟前
如何复制只读模式下的腾讯文档
人工智能·新媒体运营·媒体·内容运营·程序员创富
panpantt3211 小时前
【参会邀请】第二届大数据与数据挖掘国际会议（BDDM 2024）邀您相聚江城！
大数据·人工智能·数据挖掘
lindsayshuo1 小时前
jetson orin系列开发版安装cuda的gpu版本的opencv
人工智能·opencv
向阳逐梦1 小时前
ROS机器视觉入门：从基础到人脸识别与目标检测
人工智能·目标检测·计算机视觉
陈鋆1 小时前
智慧城市初探与解决方案
人工智能·智慧城市
热门推荐
01(欧拉)openEuler系统添加网卡文件配置流程、(欧拉)openEuler系统手动配置ipv6地址流程、(欧拉)openEuler系统网络管理说明02PyTorch机器学习实现液态神经网络03【HarmonyOS】HUAWEI DevEco Studio 下载地址汇总04玄机平台应急响应—webshell查杀05Coze扣子平台完整体验和实践（附国内和国际版对比）06Ubuntu 20.04使用Livox mid 360 测试 FAST_LIO07【目标跟踪】相机运动补偿08Unity中PICO实现 隔空取物 和 接触抓取物体09RAG 实践- Ollama+RagFlow 部署本地知识库10怎样让音频速度变慢？请跟随以下方法进行操作