[Doc] Fix typos in minibatch-edge.rst (#5308)

docs/source/guide/minibatch-edge.rst

@@ -130,7 +130,7 @@ layer.
             self.W = nn.Linear(2 * in_features, num_classes)
     
         def apply_edges(self, edges):
-            data = torch.cat([edges.src['x'], edges.dst['x']])
+            data = torch.cat([edges.src['x'], edges.dst['x']], 1)
             return {'score': self.W(data)}
     
         def forward(self, edge_subgraph, x):
@@ -222,7 +222,7 @@ over the edge types for :meth:`~dgl.DGLGraph.apply_edges`.
             self.W = nn.Linear(2 * in_features, num_classes)
     
         def apply_edges(self, edges):
-            data = torch.cat([edges.src['x'], edges.dst['x']])
+            data = torch.cat([edges.src['x'], edges.dst['x']], 1)
             return {'score': self.W(data)}
     
         def forward(self, edge_subgraph, x):

docs/source/guide_cn/minibatch-edge.rst

@@ -106,7 +106,7 @@
             self.W = nn.Linear(2 * in_features, num_classes)
     
         def apply_edges(self, edges):
-            data = torch.cat([edges.src['x'], edges.dst['x']])
+            data = torch.cat([edges.src['x'], edges.dst['x']], 1)
             return {'score': self.W(data)}
     
         def forward(self, edge_subgraph, x):
@@ -191,7 +191,7 @@ DGL保证边子图中的节点与生成的块列表中最后一个块的输出
             self.W = nn.Linear(2 * in_features, num_classes)
     
         def apply_edges(self, edges):
-            data = torch.cat([edges.src['x'], edges.dst['x']])
+            data = torch.cat([edges.src['x'], edges.dst['x']], 1)
             return {'score': self.W(data)}
     
         def forward(self, edge_subgraph, x):

docs/source/guide_ko/minibatch-edge.rst

@@ -97,7 +97,7 @@
             self.W = nn.Linear(2 * in_features, num_classes)
     
         def apply_edges(self, edges):
-            data = torch.cat([edges.src['x'], edges.dst['x']])
+            data = torch.cat([edges.src['x'], edges.dst['x']], 1)
             return {'score': self.W(data)}
     
         def forward(self, edge_subgraph, x):
@@ -179,7 +179,7 @@ Heterogeneous 그래프들의 노드 representation들을 계산하는 모델은
             self.W = nn.Linear(2 * in_features, num_classes)
     
         def apply_edges(self, edges):
-            data = torch.cat([edges.src['x'], edges.dst['x']])
+            data = torch.cat([edges.src['x'], edges.dst['x']], 1)
             return {'score': self.W(data)}
     
         def forward(self, edge_subgraph, x):