两个嵌入模型的联合训练KGE + GloVe

如何解决两个嵌入模型的联合训练KGE + GloVe

如何创建共享知识图嵌入 (KGE) 模型、TuckER（如下所示）和 glove（假设有一个共现矩阵以及维度）的参数的联合模型已经可用）在pytorch？

换句话说，联合模型必须遵守CMTF的准则（Coupled Matrix and Tensor F actorizations) 框架和来自两个嵌入的权重必须在训练期间绑定。这里的问题是 KGE 需要一个三元组（主题、关系、对象），而 glove 需要一个共现矩阵。此外，它们的损失函数的计算方式也不同。

class TuckER(torch.nn.Module):
    def __init__(self,d,d1,d2,**kwargs):
        super(TuckER,self).__init__()

        self.E = torch.nn.Embedding(len(d.entities),d1)
        self.R = torch.nn.Embedding(len(d.relations),d2)
        self.W = torch.nn.Parameter(torch.tensor(np.random.uniform(-1,1,(d2,d1)),dtype=torch.float,device="cuda",requires_grad=True))

        self.input_dropout = torch.nn.Dropout(kwargs["input_dropout"])
        self.hidden_dropout1 = torch.nn.Dropout(kwargs["hidden_dropout1"])
        self.hidden_dropout2 = torch.nn.Dropout(kwargs["hidden_dropout2"])
        self.loss = torch.nn.bceloss()

        self.bn0 = torch.nn.Batchnorm1d(d1)
        self.bn1 = torch.nn.Batchnorm1d(d1)
        
    def init(self):
        xavier_normal_(self.E.weight.data)
        xavier_normal_(self.R.weight.data)

    def forward(self,e1_idx,r_idx):
        e1 = self.E(e1_idx)
        x = self.bn0(e1)
        x = self.input_dropout(x)
        x = x.view(-1,e1.size(1))

        r = self.R(r_idx)
        W_mat = torch.mm(r,self.W.view(r.size(1),-1))
        W_mat = W_mat.view(-1,e1.size(1),e1.size(1))
        W_mat = self.hidden_dropout1(W_mat)

        x = torch.bmm(x,W_mat) 
        x = x.view(-1,e1.size(1))      
        x = self.bn1(x)
        x = self.hidden_dropout2(x)
        x = torch.mm(x,self.E.weight.transpose(1,0))
        pred = torch.sigmoid(x)
        return pred

我知道如何通过加载状态字典、获取实例、在两个模型上运行它们，然后在顶部应用前馈层来联合训练两个预训练模型。但我似乎无法弄清楚这种情况。你能建议我如何实现这一目标吗？

重要资源：

TuckER 代码 - https://github.com/ibalazevic/TuckER