PyTorch 图神经网络训练代码：使用早停机制优化模型性能

for epoch in range(args.epochs):
    t = time.time()

    #   for train
    model.train()
    optimizer.zero_grad()

    output = model(features, adjtensor)

    # 平均输出
    areout = output[1]

    loss_xy = 0
    loss_ncl = 0

    for k in range(len(output[0])):
        # print('k = ' + str(k))
        # print(F.nll_loss(output[0][k][idx_train], labels[idx_train]))
        # print(F.mse_loss(output[0][k][idx_unlabel], areout[idx_unlabel]))
        loss_xy += F.nll_loss(output[0][k][idx_train], labels[idx_train])
        loss_ncl += F.mse_loss(output[0][k][idx_unlabel], areout[idx_unlabel])


    loss_train = (1-args.lamd)* loss_xy - args.lamd * loss_ncl
    # loss_train = (1 - args.lamd) * loss_xy + args.lamd * 1 / loss_ncl



    # loss_train = (1 - args.lamd) * loss_xy + args.lamd * (torch.exp(-loss_ncl))


    print(loss_xy)
    print(loss_ncl)

    print(torch.exp(-loss_ncl))

    print((1 - args.lamd) * loss_xy)
    print(args.lamd * (torch.exp(-loss_ncl)))



    print(epoch)
    print(loss_train)
    print('.............')
    acc_train = accuracy(areout[idx_train], labels[idx_train])

    loss_train.backward()
    optimizer.step()

    #   for val
    if validate:
        # print('no')
        model.eval()
        output = model(features, adjtensor)
        areout = output[1]
        vl_step = len(idx_val)
        loss_val = F.nll_loss(areout[idx_val], labels[idx_val])
        acc_val = accuracy(areout[idx_val], labels[idx_val])
        # vl_step = len(idx_train)
        # loss_val = F.nll_loss(areout[idx_train], labels[idx_train])
        # acc_val = accuracy(areout[idx_train], labels[idx_train])

        cost_val.append(loss_val)

        # 原始GCN的验证
        # if epoch > args.early_stopping and cost_val[-1] > torch.mean(torch.stack(cost_val[-(args.early_stopping + 1):-1])):
        #     # print('Early stopping...')
        #     print(epoch)
        #     break
        # print(epoch)
        # GAT的验证
        if acc_val/vl_step >= vacc_mx or loss_val/vl_step <= vlss_mn:
            if acc_val/vl_step >= vacc_mx and loss_val/vl_step <= vlss_mn:
                vacc_early_model = acc_val/vl_step
                vlss_early_model = loss_val/vl_step
                torch.save(model, checkpt_file)

            vacc_mx = np.max((vacc_early_model, vacc_mx))
            vlss_mn = np.min((vlss_early_model, vlss_mn))
            curr_step = 0

        else:
            curr_step += 1

            # print(curr_step)
            if curr_step == args.early_stopping:
                # print('Early stop! Min loss: ', vlss_mn, ', Max accuracy: ', vacc_mx)
                # print('Early stop model validation loss: ', vlss_early_model, ', accuracy: ', vacc_early_model)
                break


# `cost_val.append(loss_val)`的作用是在每个epoch的验证过程中，记录当前模型在验证集上的损失值，以便后续用于判断是否进行early stopping。如果当前epoch的模型在验证集上的损失值比之前所有epoch的模型都要小，则将当前模型保存下来作为最优模型，并更新最优模型的验证集准确率和损失值。如果当前模型在验证集上的损失值连续多个epoch都没有改善，则进行early stopping，停止训练，返回最优模型。