[Doc] Minor fix on the distributed training doc. (#2968)

Co-authored-by: Zheng <dzzhen@3c22fba32af5.ant.amazon.com>

python/dgl/distributed/dist_graph.py

@@ -422,12 +422,6 @@ class DistGraph:
     ...     labels = g.ndata['labels'][block.dstdata[dgl.NID]]
     ...     pred = model(block, feat)
 
-    Note
-    ----
-    ``DistGraph`` currently only supports graphs with only one node type and one edge type.
-    For heterogeneous graphs, users need to convert them into DGL graphs with one node type and
-    one edge type and store the actual node types and edge types as node data and edge data.
-
     Note
     ----
     DGL's distributed training by default runs server processes and trainer processes on the same