def __init__(self): super(Net, self).__init__() self.embedding = torch.nn.Parameter(torch.Tensor(data.num_nodes, embedding)) self.embedding.data.normal_() self.conv1 = AGNNConv(requires_grad=False) self.conv2 = AGNNConv(requires_grad=True) self.mclp = multiClassInnerProductDecoder(embedding, data.num_classes)
def __init__(self): super(Net, self).__init__() self.embedding = Parameter(torch.Tensor(data.num_nodes, 256)) self.embedding.data.normal_() self.conv1 = GATConv(256, hidden_features, heads=heads) self.conv2 = GATConv(hidden_features * heads, embeddings, concat=False) self.mclp = multiClassInnerProductDecoder(embeddings, data.num_classes)
def __init__(self): super(Net, self).__init__() self.embedding = Parameter(torch.Tensor(data.num_nodes, 256)) self.embedding.data.normal_() self.conv1 = GCNConv(256, hidden_size) self.conv2 = GCNConv(hidden_size, args.embedding) self.mclp = multiClassInnerProductDecoder(args.embedding, data.num_classes)
def __init__(self): super(Net, self).__init__() self.embedding = torch.nn.Parameter( torch.Tensor(data.num_nodes, in_dim)) self.embedding.data.normal_() self.conv1 = RGCNConv(in_dim, hidden_size, data.num_relations, num_bases=data.num_relations) self.conv2 = RGCNConv(hidden_size, embedding, data.num_relations, num_bases=data.num_relations) self.mclp = multiClassInnerProductDecoder(embedding, data.num_classes)