如何在 pytorch 中创建一个共享知识图嵌入(KGE) 模型、TuckER(如下所示)和GloVe(假设共现矩阵以及维度已经可用)的参数的联合模型?
换句话说,联合模型必须遵守 CMTF(耦合矩阵和张量因子因子化)框架的标准,并且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(主体、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, 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, 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。你能建议我如何做到这一点吗?
重要资源:
- TuckER 的代码 - https://github.com/ibalazevic/TuckER