1 节点属性重构
MethodGraphBertNodeConstruct(
(bert): MethodGraphBert(
(embeddings): BertEmbeddings(
(raw_feature_embeddings): Linear(in_features=1433, out_features=32, bias=True)
(wl_role_embeddings): Embedding(100, 32)
(inti_pos_embeddings): Embedding(100, 32)
(hop_dis_embeddings): Embedding(100, 32)
(LayerNorm): LayerNorm((32,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.5, inplace=False)
)
(encoder): BertEncoder(
(layer): ModuleList(
(0): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=32, out_features=32, bias=True)
(key): Linear(in_features=32, out_features=32, bias=True)
(value): Linear(in_features=32, out_features=32, bias=True)
(dropout): Dropout(p=0.3, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=32, out_features=32, bias=True)
(LayerNorm): LayerNorm((32,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.5, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=32, out_features=32, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=32, out_features=32, bias=True)
(LayerNorm): LayerNorm((32,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.5, inplace=False)
)
)
(1): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=32, out_features=32, bias=True)
(key): Linear(in_features=32, out_features=32, bias=True)
(value): Linear(in_features=32, out_features=32, bias=True)
(dropout): Dropout(p=0.3, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=32, out_features=32, bias=True)
(LayerNorm): LayerNorm((32,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.5, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=32, out_features=32, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=32, out_features=32, bias=True)
(LayerNorm): LayerNorm((32,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.5, inplace=False)
)
)
)
)
(pooler): BertPooler(
(dense): Linear(in_features=32, out_features=32, bias=True)
(activation): Tanh()
)
)
(cls_y): Linear(in_features=32, out_features=1433, bias=True)
)
2网络结构恢复
MethodGraphBertGraphRecovery(
(bert): MethodGraphBert(
(embeddings): BertEmbeddings(
(raw_feature_embeddings): Linear(in_features=1433, out_features=32, bias=True)
(wl_role_embeddings): Embedding(100, 32)
(inti_pos_embeddings): Embedding(100, 32)
(hop_dis_embeddings): Embedding(100, 32)
(LayerNorm): LayerNorm((32,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.5, inplace=False)
)
(encoder): BertEncoder(
(layer): ModuleList(
(0): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=32, out_features=32, bias=True)
(key): Linear(in_features=32, out_features=32, bias=True)
(value): Linear(in_features=32, out_features=32, bias=True)
(dropout): Dropout(p=0.3, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=32, out_features=32, bias=True)
(LayerNorm): LayerNorm((32,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.5, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=32, out_features=32, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=32, out_features=32, bias=True)
(LayerNorm): LayerNorm((32,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.5, inplace=False)
)
)
(1): BertLayer(
(attention): BertAttention(
(self): BertSelfAttention(
(query): Linear(in_features=32, out_features=32, bias=True)
(key): Linear(in_features=32, out_features=32, bias=True)
(value): Linear(in_features=32, out_features=32, bias=True)
(dropout): Dropout(p=0.3, inplace=False)
)
(output): BertSelfOutput(
(dense): Linear(in_features=32, out_features=32, bias=True)
(LayerNorm): LayerNorm((32,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.5, inplace=False)
)
)
(intermediate): BertIntermediate(
(dense): Linear(in_features=32, out_features=32, bias=True)
)
(output): BertOutput(
(dense): Linear(in_features=32, out_features=32, bias=True)
(LayerNorm): LayerNorm((32,), eps=1e-12, elementwise_affine=True)
(dropout): Dropout(p=0.5, inplace=False)
)
)
)
)
(pooler): BertPooler(
(dense): Linear(in_features=32, out_features=32, bias=True)
(activation): Tanh()
)
)
)
运行后意识到之前运行主程序时并没有用到这些预训练的过程和结果,那么这一步的作用如何体现呢?