【PyG】图神经网络GAT代码自学

图方法分为谱方法和空间方法，空间方法是直接在图上进行操作，代表方法之一GAT；谱方法是将图映射到谱域上，例如拉普拉斯矩阵经过特征分解得到的空间，代表方法之一是GCN。本文介绍GAT的代码实现。

本文参考论文原作者代码https://github.com/PetarV-/GAT

论文原图与核心公式

utils相关代码分析

见之前写的GCN那篇博客

https://blog.csdn.net/qq_42859088/article/details/124669794?spm=1001.2014.3001.5501

train相关代码分析

train.py

感觉和之前的gcn没有区别，先setting，再cuda，load_data，然后train，eval，test

from __future__ import division
from __future__ import print_function

import os
import glob
import time
import random
import argparse
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torch.autograd import Variable

from utils import load_data, accuracy
from models import GAT, SpGAT

# Training settings
parser = argparse.ArgumentParser()
parser.add_argument('--no-cuda', action='store_true', default=False, help='Disables CUDA training.')
parser.add_argument('--fastmode', action='store_true', default=False, help='Validate during training pass.')
parser.add_argument('--sparse', action='store_true', default=False, help='GAT with sparse version or not.')
parser.add_argument('--seed', type=int, default=72, help='Random seed.')
parser.add_argument('--epochs', type=int, default=200, help='Number of epochs to train.')
parser.add_argument('--lr', type=float, default=0.005, help='Initial learning rate.')
parser.add_argument('--weight_decay', type=float, default=5e-4, help='Weight decay (L2 loss on parameters).')
parser.add_argument('--hidden', type=int, default=8, help='Number of hidden units.')
parser.add_argument('--nb_heads', type=int, default=8, help='Number of head attentions.')
parser.add_argument('--dropout', type=float, default=0.6, help='Dropout rate (1 - keep probability).')
parser.add_argument('--alpha', type=float, default=0.2, help='Alpha for the leaky_relu.')
parser.add_argument('--patience', type=int, default=100, help='Patience')

args = parser.parse_args()
args.cuda = not args.no_cuda and torch.cuda.is_available()

random.seed(args.seed)
np.random.seed(args.seed)
torch.manual_seed(args.seed)
if args.cuda:
    torch.cuda.manual_seed(args.seed)

# Load data
adj, features, labels, idx_train, idx_val, idx_test = load_data()

# Model and optimizer
args.sparse = False
if args.sparse:
    model = SpGAT(nfeat=features.shape[1], 
                nhid=args.hidden, 
                nclass=int(labels.max()) + 1, 
                dropout=args.dropout, 
                nheads=args.nb_heads, 
                alpha=args.alpha)
else:
    model = GAT(nfeat=features.shape[1], 
                nhid=args.hidden, 
                nclass=int(labels.max()) + 1, 
                dropout=args.dropout, 
                nheads=args.nb_heads, 
                alpha=args.alpha)
optimizer = optim.Adam(model.parameters(), 
                       lr=args.lr, 
                       weight_decay=args.weight_decay)

if args.cuda:
    model.cuda()
    features = features.cuda()
    adj = adj.cuda()
    labels = labels.cuda()
    idx_train = idx_train.cuda()
    idx_val = idx_val.cuda()
    idx_test = idx_test.cuda()

# features, adj, labels = Variable(features), Variable(adj), Variable(labels)


def train(epoch):
    t = time.time()
    model.train()
    optimizer.zero_grad()
    output = model(features, adj)  # GAT模块
    loss_train = F.nll_loss(output[idx_train], labels[idx_train])
    acc_train = accuracy(output[idx_train], labels[idx_train])
    loss_train.backward()
    optimizer.step()

    if not args.fastmode